Generated by All in One SEO Pro v5.0.1.1, this is an llms-full.txt file, used by LLMs to index the site.
# Applied SmartFactory Solutions
Factory Automation
## Pages
### [Factory Automation | Applied SmartFactory Solutions](https://appliedsmartfactory.com/)
**Published:** June 24, 2021
**Author:** Applied Smartfactory
**Content:**
# Smarter Manufacturing.
Measurable Results.
Applied SmartFactory helps manufacturers increase yield, reduce operational risk, and boost productivity through AI‑powered automation and integrated manufacturing software.
[SmartFactory Semi Solutions](/semiconductor/)
Transform manufacturing with quality and productivityLearn More
1/4
[SmartFactory AI Solutions](/ai/)
Elevate autonomous manufacturing with insight and speedLearn More
2/4
[SmartFactory Battery Solutions](/battery/)
Steer manufacturing with power and precision Learn More
3/4
[SmartFactory Rx Solutions](/pharmaceutical/)
Drive Pharma manufacturing with compliance and confidenceLearn More
4/4
# Fully integrated solutions
Our SmartFactory portfolio offers integrated automation software solutions designed to maximize efficiency and empower manufacturing operations.
We provide comprehensive services, including productivity enhancement, process quality improvement, MES integration, and supply chain management—covering everything from enterprise planning to production control.
With AI-powered automation and advanced scheduling technologies, manufacturers can elevate performance, optimize production flow, minimize downtime, and drive continuous improvement. Our holistic approach enables seamless monitoring and control of operations.
Unlock your factory’s full potential with our dedicated automation team, achieving superior results and fostering sustainable growth in a dynamic manufacturing environment.
[ View Solutions ](/semiconductor/)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/02/applied-smartfactory-integrated-solutions-desktop-view.webp)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/02/applied-smartfactory-integrated-solutions-mobile-view.webp)
[ View minds.ai ](https://minds.ai/)
Announcement
### Applied Materials
Acquires minds.ai
minds.ai specializes in reinforcement learning and deep learning AI for semiconductor manufacturing and is now part of the **Applied SmartFactory®** portfolio.
COMPETITIVE ADVANTAGE
SmartFactory customers gain advanced AI built for semiconductor fabs — optimizing yield, accelerating decisions, and advancing toward autonomous factory operations.
## SmartFactory Blogs
Learn how automation experts are transforming manufacturing with SmartFactory autonomous solutions.
[Semi blog](/semiconductor-blog/) | [Battery blog](/battery-blog/)
## SmartFactory Events
Engage with our automation experts to fast-track advantages of smart manufacturing.
[Semi events](/semiconductor-events/) | [Battery events](/battery-events/)
## Measurable improvements
Deploying automated solutions enables your team to complete routine tasks more quickly, identify problems before they arise, and implement solutions without incurring significant waste. You can realize measurable improvements including, among others:
### Improved cycle time
### Increased yield
### Higher throughput
### Lower equipment downtime
### Lower risk
### Faster time to market
### Fewer defects
### More efficient scheduling
## Automation leaders
Our global team of experts are industry leaders who regularly present on manufacturing automation solutions. They use their expertise to develop scalable solutions that enable you to increase your factory’s automation based on your unique needs and timeline.
Whether you are just getting started on your automation journey or are ready to go lights out, our experts can provide the roadmap you’ll need to get there.
[ Connect with us to improve your unique KPIs ](/connect/)
## Industry insights from our experts
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)### Quality Quest: Insights from the Fab
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)### Performance Pioneers: Factory Innovations
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)### Smart Manufacturing: The Evolutionary Edge
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)### SPC Strategies: Realizing Excellence
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)### MES Integration: Uniquely SmartFactory
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)### Human-Centric Solutions: SmartFactory’s Approach
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)### Innovation Integration: Seizing New Opportunities
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)### Efficiency Unleashed: Optimizing the Fab
### Upcoming events
[ All Events ](/semiconductor/events/)
### [SmartFactory Symposium India 2026](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
September 18, 2026
A special event focused on advancing India’s semiconductor manufacturing ecosystem through technical sessions and an expert panel discussion.
[ Register Now ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
### [A New Design Mindset to Enable AI-Driven Factory Automation](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
October 15, 2026
Selim S. Nahas on the design changes required to make process tools autonomous at the wafer level — and what it takes to scale AI-driven automation factory-wide.
[ More Info ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
### [SEMICON Europa](https://www.semiconeuropa.org/)
November 10-13, 2026
| Munich, Germany
[ More Info ](https://www.semiconeuropa.org/)
### SmartFactory Symposium Japan 2026
December 8, 2026
A special event focused on exploring how AI advancing smart manufacturing in Japan, from intelligent equipment to faster decision-making. Details coming soon.
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2026/)
December 6-9, 2026
| Glasgow, Scotland
[ More Info ](https://meetings.informs.org/wordpress/wsc2026/)
### [SmartFactory Webinar Replays](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
Available 24/7
Gain valuable insights and strategies to enhance quality and productivity in semiconductor manufacturing.
[ More Info ](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
---
### [PROMIS](https://appliedsmartfactory.com/manufacturing-execution-solutions/promis/)
**Published:** October 5, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES PROMIS®
# Adapt to your evolving business needs
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
### PROMIS® on Red Hat® Enterprise Linux®
We remain fully committed to PROMIS as a strategic MES platform – and continue investing in its future through migration to Red Hat Enterprise Linux, so you can modernize your technology stack without replacing the platform your factory runs on.
[ **Learn more about PROMIS modernization** ](/manufacturing-execution-solutions/promis/red-hat-linux/)
## Have you looked at PROMIS lately?
SmartFactory MES PROMIS is a manufacturing execution system that continues to provide up‐to‐date features for improving manufacturing quality and productivity, new integration options, and user interface enhancements. If you no longer have a current version of PROMIS, we can provide services to get your implementation upgraded so you can take advantage of rich MES features, out-of-box capabilities, and efficient fab operation modeling.
## Why choose SmartFactory MES PROMIS?
### 80% reduction in effort to keep WIP on update flows
### >85% reduction in effort to maintain update flows
### >90% elimination of PROMIS customizations by using new features and new rules
## What can you gain from our approach?
### Regular enhancements
- Leverage major operational improvements
- Capture opportunity to greatly improve productivity for key users
- Reduce scrap due to mistakes that are preventable through updates
### Reduced user errors
- Eliminate risk of common errors in rework and process management
- Eliminate scrap due to certain types of common modeling errors by minimizing customizations
- Customize PROMIS behavior without the need to touch code—all on the fly
### Proven reliability
- Leverage the breadth of an MES deployed in over 270 semiconductor and precision electronics manufacturers worldwide
- Access the experience of a team adept at achieving the highest possible uptime while enabling redundancy and regular upgrades without losing production time
---
### [Support Contacts](https://appliedsmartfactory.com/support-contacts/)
**Published:** December 3, 2021
**Author:** Applied Smartfactory
**Content:**
Global Support
# Software Regional Contacts
## Full service global software support services
### Access to qualified global support engineers
- Troubleshoot software issues
- Address feature and functionality questions
- Assist with known BKMs
### Customer training
- Feature/function demos
- Hands-on instruction and training sessions
- Training options could potentially include:
- Classroom setting (at a customer or Applied site)
- Online/virtual live classroom
- Self-paced training materials
### Software portal enables users with current maintenance contracts to receive:
- Latest GA releases and patches
- Product related announcements
- Access to software support experts
## For additional support assistance, please select your local region:
North America
Europe
China
Japan
Korea
South East Asia
Taiwan
North America
### North America
Hours: 7:00 AM – 6:00 PM Mountain Time
#### Satish Baskaran, AMNA Regional Manager
[ satish\_baskaran@amat.com]()
[ +1-408-584-0022](tel:+14085840022)
[ +1-408-757-6851](tel:+14087576851)
#### 300works
[ 300works\_support@amat.com](mailto:300works_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoMod
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoSched AP
[ autoschedap\_support@amat.com](mailto:autoschedap_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### CELLworks
[ cellworks\_support@amat.com](mailto:cellworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### CLASS MCS 5
[ classmcs5\_support@amat.com](mailto:classmcs5_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### E3 Platform / FDC / R2R
[ e3\_support@amat.com](mailto:e3_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### FAB300
9:00 AM – 6:00 PM PT
[ crc\_fab300@amat.com](mailto:crc_fab300@amat.com)
*For FAB-down situations, Platinum customers should use the contact number given by Support*
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### iDurables
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Maintenance Management (Xsite)
[ xsite\_support@amat.com](mailto:xsite_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Productivity Solutions
[ productivity\_support@amat.com](mailto:productivity_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### PROMIS
8:00 AM – 8:00 PM ET
[ promis\_support@amat.com](mailto:promis_support@amat.com)
[ 800-784-6778](tel:8007846778)
#### Sentinel
[ sentinel\_support@amat.com](mailto:sentinel_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SF Rx Support
[ SF\_Rx\_Support@amat.com](mailto:SF_Rx_Support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SPACE
[ space\_support@amat.com](mailto:space_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### STATIONworks
[ stationworks\_support@amat.com](mailto:stationworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
Europe
### Europe
Hours: 8:00 AM – 5:00 PM GMT
#### Antoine Carlier, AME Regional Manager
[ antoine\_carlier@amat.com]()
[ +33-476-04-29-19](tel:tel:+33476042919)
[ +33-607-87-77-76](tel:+33607877776)
#### All Products
[ eur\_customersupport@amat.com](mailto:eur_customersupport@amat.com)
[ +44-118-931-5678](tel:+441189315678)
China
### China
Hours: 8:30 AM – 5:00 PM
#### Michael Gao, AMC Regional Manager
[ michael\_gao@amat.com]()
[ +86-29-68917000](tel:+862968917000)
[ +86-29-68917138](tel:+862968917138)
[ +86-18101883550](tel:+8618101883550)
#### All Products
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +86-21-58958985 x 1190](tel:+862158958985x1190)
Japan
### Japan
Hours: 9:00 AM – 5:30 PM (GMT +9, No Daylight Savings)
#### Yoshio Oikawa, AMJ Regional Manager
[ Yoshio\_oikawa@amat.com]()
[ +81-3-6812-6293](tel:+81368126293)
[ +81-90-5197-0014](tel:+819051970014)
#### AutoMod/AutoSched
[ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support\_jp@amat.com](mailto:apf_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### E3 Platform / FDC / R2R
[ e3\_support\_jp@amat.com](mailto:e3_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### CLASS MCS 5
[ mcs\_support\_jp@amat.com](mailto:mcs_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### MES Products
[ mes\_support\_jp@amat.com]()
[ +81-52-238-2801](tel:+81522382801)
#### All Products
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
[ +81-52-238-2801](tel:+81522382801)
Korea
### Korea
Hours: 8:30 AM – 5:30 PM (GMT +9, No Daylight Savings)
#### William Kang, AMK Regional Manager
[ William\_Kang@amat.com]()
[ +82-31-724-5000](tel:+82317245000)
[ +82-10-6340-2706](tel:+821063402706)
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ +82-31-724-5000](tel:+82317245000)
#### All Other Products
[ MAS\_JKR\_SWsupport@amat.com](mailto:MAS_JKR_SWsupport@amat.com)
[ +82-31-724-5000](tel:+82317245000)
South East Asia
### South East Asia
Hours: 9:00 AM – 5:00 PM
#### Kwee Thiam Lim, AMSEA Regional Manager
[ kwee-thiam\_lim@amat.com](mailto:kwee-thiam_lim@amat.com)
[ +65-63117306](tel:+6563117306)
[ +65-97843991](tel:+6597843991)
#### All Products
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +65-63117311](tel:+6563117311)
Taiwan
### Taiwan
Hours: 8:30 AM – 5:30 PM
#### James Chang, AMT Regional Manager
[ James\_SC\_Chang@amat.com ]()
[ +886 35793185](tel:+88635793185)
[ +886 936259648](tel:+886936259648)
#### All Products
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +886-3-5793111](tel:+88635793111)
## For additional support assistance, please select your local region:
North America
### North America
Hours: 7:00 AM – 6:00 PM Mountain Time
#### Satish Baskaran, AMNA Regional Manager
[ satish\_baskaran@amat.com](mailto:satish_baskaran@amat.com)
[ +1-408-584-0022](tel:+14085840022)
[ +1-408-757-6851](tel:+14087576851)
#### 300works
[ 300works\_support@amat.com](mailto:300works_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoMod
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoSched AP
[ autoschedap\_support@amat.com](mailto:autoschedap_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### CELLworks
[ cellworks\_support@amat.com](mailto:cellworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### CLASS MCS 5
[ classmcs5\_support@amat.com](mailto:classmcs5_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### E3 Platform / FDC / R2R
[ e3\_support@amat.com](mailto:e3_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### FAB300
9:00 AM – 6:00 PM PT
[ crc\_fab300@amat.com](mailto:crc_fab300@amat.com)
*For FAB-down situations, Platinum customers should use the contact number given by Support*
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### iDurables
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Maintenance Management (Xsite)
[ xsite\_support@amat.com](mailto:xsite_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Productivity Solutions
[ productivity\_support@amat.com](mailto:productivity_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### PROMIS
8:00 AM – 8:00 PM ET
[ promis\_support@amat.com](mailto:promis_support@amat.com)
[ 800-784-6778](tel:8007846778)
#### Sentinel
[ sentinel\_support@amat.com](mailto:sentinel_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SF Rx Support
[ SF\_Rx\_Support@amat.com](mailto:SF_Rx_Support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SPACE
[ space\_support@amat.com](mailto:space_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### STATIONworks
[ stationworks\_support@amat.com](mailto:stationworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
Europe
### Europe
Hours: 8:00 AM – 5:00 PM GMT
#### Antoine Carlier, AME Regional Manager
[ antoine\_carlier@amat.com](mailto:antoine_carlier@amat.com)
[ +33-476-04-29-19](tel:+33476042919)
[ +33-607-87-77-76](tel:+33607877776)
#### All Products
[ eur\_customersupport@amat.com](mailto:eur_customersupport@amat.com)
[ +44-118-931-5678](tel:+441189315678)
China
### China
Hours: 8:30 AM – 5:00 PM
#### Michael Gao, AMC Regional Manager
[ michael\_gao@amat.com](mailto:michael_gao@amat.com)
[ +86-29-68917000](tel:+862968917000)
[ +86-29-68917138](tel:+862968917138)
[ +86-18101883550](tel:+8618101883550)
#### All Products
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +86-21-58958985 x 1190](tel:+862158958985x1190)
Japan
### Japan
Hours: 9:00 AM – 5:30 PM (GMT +9, No Daylight Savings)
#### Yoshio Oikawa, AMJ Regional Manager
[ Yoshio\_oikawa@amat.com](mailto:Yoshio_oikawa@amat.com)
[ +81-3-6812-6293](tel:+81368126293)
[ +81-90-5197-0014](tel:+819051970014)
#### AutoMod/AutoSched
[ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support\_jp@amat.com](mailto:apf_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### E3 Platform / FDC / R2R
[ e3\_support\_jp@amat.com](mailto:e3_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### CLASS MCS 5
[ mcs\_support\_jp@amat.com](mailto:mcs_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### MES Products
[ mes\_support\_jp@amat.com](mailto:mes_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### All Products
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
[ +81-52-238-2801](tel:+81522382801)
Korea
### Korea
Hours: 8:30 AM – 5:30 PM (GMT +9, No Daylight Savings)
#### William Kang, AMK Regional Manager
[ William\_Kang@amat.com](mailto:William_Kang@amat.com)
[ +82-31-724-5000](tel:+82317245000)
[ +82-10-6340-2706](tel:+821063402706)
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ +82-31-724-5000](tel:+82317245000)
#### All Other Products
[ MAS\_JKR\_SWsupport@amat.com](mailto:MAS_JKR_SWsupport@amat.com)
[ +82-31-724-5000](tel:+82317245000)
South East Asia
### South East Asia
Hours: 9:00 AM – 5:00 PM
#### Kwee Thiam Lim, AMSEA Regional Manager
[ kwee-thiam\_lim@amat.com](mailto:kwee-thiam_lim@amat.com)
[ +65-63117306](tel:+6563117306)
[ +65-97843991](tel:+6597843991)
#### All Products
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +65-63117311](tel:+6563117311)
Taiwan
### Taiwan
Hours: 8:30 AM – 5:30 PM
#### James Chang, AMT Regional Manager
[ James\_SC\_Chang@amat.com ](mailto:James_SC_Chang@amat.com)
[ +886 35793185](tel:+88635793185)
[ +886 936259648](tel:+886936259648)
#### All Products
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +886-3-5793111](tel:+88635793111)
---
### [AutoMod Resellers](https://appliedsmartfactory.com/worldwide-automod-distributors/)
**Published:** January 10, 2022
**Author:** Applied Smartfactory
**Content:**
AutoMod® Resellers
# Global Reseller Contacts
## Worldwide AutoMod Distributors
Not all simulation modeling tools are created equal. For 30 years, top material handling providers and systems integrators worldwide have relied on SmartFactory Simulation AutoMod to handle modeling, analyzing, and emulating complex manufacturing and handling systems to get the high quality level of detail required to reflect reality in their models. Ready to find a distributor for sales, integration or services near you? View our global resellers by region.
North America
Asia
Europe
South America
Australia & New Zealand
North America
### USA
All Regions
#### Matthew Hobson-Rohrer
#### Roar Simulation
Salt Lake City, Utah
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[801-829-7067](tel:8018297067)
Canada
#### Vincent Santiguida
#### MultiCIM
16 Westminster Ave. N suite 306C
Montreal-West, Quebec H4X 1Z1
Canada
[ admin@multicim.com](mailto:admin@multicim.com)
Support:
[ 514-633-6401](tel:5146336401)
[ 514-633-6495](tel:5146336495)
[ www.multicim.com](http://www.multicim.com/)
Asia
### Asia
China
#### Lixin Qu
#### Beijing Etech Technology Ltd., Com
Room 1001, Building E, Longqi Plaza
No. 19 of Huangpin Road
Changping District, Beijing, China
Post code: 100096
[ qulx@etech.com.cn](mailto:qulx@etech.com.cn)
[ 86-10-88878250](tel:861088878250), [86-18601153747]()
[ www.etech.com.cn](http://www.etech.com.cn/)
Japan
#### Applied Materials Japan, Inc.
AGS/Manufacturing Automation Services
Yokoso Rainbow Tower,
3-20-20, Kaigan, Minato, Tokyo, 108-8444, Japan
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
Support: [ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-6812-6866](tel:+8168126866)
Support: [ +81-52-238-2801](tel:+81522382801)
[ www.brookssoftware.jp](https://www.brookssoftware.jp/)
India
#### Vikram Ramnath
#### Larvik Engineering Consultants Pvt. Ltd.
705, B Wing, Great Eastern Summit,
Plot 66, Sector 15,
CBD Belapur, Navi Mumbai 400 614
[ info@larvik.co.in](mailto:info@larvik.co.in)
Support: [ support@larvik.co.in](mailto:support@larvik.co.in)
[ 91-22-2758-1054](tel:912227581054)
[ larvik.co.in](https://larvik.co.in/)
Korea
#### SCA Inc.
\#805,E&C DreamTower-5,197-13
Guro3-Dong,Guro-Gu,Seoul
Korea(ZIP:152-050)
[ admin@scacompany.co.kr](mailto:admin@scacompany.co.kr)
Support: [ Support@scacompany.co.kr](mailto:Support@scacompany.co.kr)
[ +82-2-3281-5222](tel:82232815222)
[ www.scacompany.co.kr](http://www.scacompany.co.kr/)
Malaysia, Vietnam, Thailand, Indonesia, Philippines and Singapore
#### SCA Globals Co.,Ltd.
422 Nguyen Thi Thap, Tan Quy Ward, District 7,
Ho Chi Minh City, Vietnam
Support: [ support@scaglobals.com](mailto:support@scaglobals.com)
[ 8210-4743-5222](tel:821047435222)
[ www.scaglobals.com](https://www.scaglobals.com/)
Europe
### Europe
Belgium
#### SIMCORE Belgium
Bastion Tower, Floors 20&21
5 place du Champ de Mars
B-1050 BRUSSELS
[ info@simcore.be](mailto:info@simcore.be)
[ +32 2 550 37 69](tel:+3225503769)
[ +32 2 550 37 70](tel:+3225503770)
Denmark
#### Bent Aksel Jørgensen
Ivan Søndergaard Jensen
SIMCON A/S
Rugaardsvej 5
DK-8680 Ry
Denmark
[ info@simcon.dk](mailto:info@simcon.dk), [ automod@simcon.dk](mailto:automod@simcon.dk), [ simul8@simcon.dk](mailto:simul8@simcon.dk)
Support: [ automodsupport@simcon.dk](mailto:automodsupport@simcon.dk), [ simul8support@simcon.dk](mailto:simul8support@simcon.dk)
[ +45-86-89-03-22](tel:+4586890322)
[ +45-86-89-03-99](tel:+4586890399)
Support: [ 45-86-89-03-42](tel:4586890342)
France and French-speaking Switzerland
#### SIMCORE France
Parc Monier Immeuble Le Cassiopée
167 route de Lorient
F-35000 RENNES
[ info@simcore.fr](mailto:info@simcore.fr)
Support: [ support@simcore.fr](mailto:support@simcore.fr)
[ +33 2 99 14 88 50](tel:+33299148850)
[ +33 2 99 14 88 51](tel:+33299148851)
[ www.simcore.fr](https://www.simcore.fr/)
Germany, Holland, Austria and German-speaking Switzerland
#### Steffen Hertling
SimPlan AG
Niederlassung München
Manager: Steffen Hertling
Münchener Str. 13
85540 München-Haar
[ steffen.hertling@simplan.de](mailto:steffen.hertling@simplan.de)
Support: [ support@automod.de](mailto:support@automod.de)
[ +49 89 2189 7032 15](tel:+49892189703215)
[ +49 89 2189 7032 19](tel:+49892189703219)
Support: [ +49 89 2189 7032 25](tel:+49892189703225)
Italy and Italian-speaking Switzerland
#### Andrea Trere
Prolog S.r.l.
Via Mengolina 31
48018 Faenza RA
[ +39 0546 46073](tel:+39054646073)
[ +39 0546 607191](tel:+390546607191)
Info Line: [ +39 348 8706010](tel:+393488706010)
[ www.prolog.it](http://www.prolog.it), [ www.automod.it](http://www.automod.it/)
Spain
#### SIMCORE Spain
C/Génova, 7-3°-Izda
E-28004 MADRID
[ info@simcore.es](mailto:info@simcore.es)
[ +34 91 181 97 05](tel:+34911819705)
[ +34 91 102 28 93](tel:+34911022893)
Sweden
#### Pär Ström
ÅF Industry AB
Grafiska vägen 2
Box 1551
SE-401 51 Gothenburg
Sweden
[ par.strom@afconsult.com](mailto:par.strom@afconsult.com)
[ +46-10-505-3408](tel:+46105053408)
[ +46-10-505-3010](tel:+46105053010)
[ www.automod.se](http://www.automod.se/)
Turkey
#### SELCO Consulting
Haldun Çelik
Prof. Hıfzı Özcan Cad. TasarımKent, Blok D, No:4 34750 Ataşehir İSTANBULTurkey
[ info@selco.com.tr](mailto:info@selco.com.tr)
[ +90 216 5725001](tel:+902165725001), [ +90 533 360 0668](tel:+905333600668)
[ www.selco.com.tr](http://www.selco.com.tr)
United Kingdom
#### Graham Carter
Autologic Systems Ltd.
60 High Street
Tetsworth
Oxfordshire OX9 7AB
England
Support: [ support@autologic-systems.co.uk](mailto:support@autologic-systems.co.uk)
[ +44 (0) 1844 281380](tel:+4401844281380), [+44 (0) 7710 172577](tel:+4407710172577)
[ +44 (0) 1844 281874](tel:+4401844281874)
[ www.autologic-systems.co.uk](http://www.autologic-systems.co.uk/)
South America
### South America
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
Australia & New Zealand
### Australia & New Zealand
#### Applied Materials, Inc.
#### AutoMod Support, North America
5225 West Wiley Post Way
Suite 275
Salt Lake City, UT 84116
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
## Worldwide AutoMod Distributors
Not all simulation modeling tools are created equal. For 30 years, top material handling providers and systems integrators worldwide have relied on SmartFactory Simulation AutoMod to handle modeling, analyzing, and emulating complex manufacturing and handling systems to get the high quality level of detail required to reflect reality in their models. Ready to find a distributor for sales, integration or services near you? View our global resellers by region.
North America
### USA
All Regions
#### Matthew Hobson-Rohrer
#### Roar Simulation
Salt Lake City, Utah
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-829-7067](tel:8018297067)
Canada
#### Vincent Santiguida
#### MultiCIM
16 Westminster Ave. N suite 306C
Montreal-West, Quebec H4X 1Z1
Canada
[ admin@multicim.com](mailto:admin@multicim.com)
Support:
[ 514-633-6401](tel:5146336401)
[ 514-633-6495](tel:5146336495)
[ www.multicim.com](http://www.multicim.com/)
Asia
### Asia
China
#### Lixin Qu
#### Beijing Etech Technology Ltd., Com
Room 1001, Building E, Longqi Plaza
No. 19 of Huangpin Road
Changping District, Beijing, China
Post code: 100096
[ qulx@etech.com.cn](mailto:qulx@etech.com.cn)
[ 86-10-88878250](tel:861088878250), [8618601153747](tel:8618601153747)
[ www.etech.com.cn](http://www.etech.com.cn/)
Japan
#### Applied Materials Japan, Inc.
AGS/Manufacturing Automation Services
Yokoso Rainbow Tower,
3-20-20, Kaigan, Minato, Tokyo, 108-8444, Japan
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
Support: [ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-6812-6866](tel:+8168126866)
Support: [ +81-52-238-2801](tel:+81522382801)
[ www.brookssoftware.jp](https://www.brookssoftware.jp/)
India
#### Vikram Ramnath
#### Larvik Engineering Consultants Pvt. Ltd.
705, B Wing, Great Eastern Summit,
Plot 66, Sector 15,
CBD Belapur, Navi Mumbai 400 614
[ info@larvik.co.in](mailto:info@larvik.co.in)
Support: [ support@larvik.co.in](mailto:support@larvik.co.in)
[ 91-22-2758-1054](tel:912227581054)
[ larvik.co.in](https://larvik.co.in/)
Korea
#### SCA Inc.
\#805,E&C DreamTower-5,197-13
Guro3-Dong,Guro-Gu,Seoul
Korea(ZIP:152-050)
[ admin@scacompany.co.kr](mailto:admin@scacompany.co.kr)
Support: [ Support@scacompany.co.kr](mailto:Support@scacompany.co.kr)
[ +82-2-3281-5222](tel:82232815222)
[ www.scacompany.co.kr](http://www.scacompany.co.kr/)
Malaysia, Vietnam, Thailand, Indonesia, Philippines and Singapore
#### SCA Globals Co.,Ltd.
422 Nguyen Thi Thap, Tan Quy Ward, District 7,
Ho Chi Minh City, Vietnam
Support: [ support@scaglobals.com](mailto:support@scaglobals.com)
[ 8210-4743-5222](tel:821047435222)
[ www.scaglobals.com](https://www.scaglobals.com/)
Europe
### Europe
Belgium
#### SIMCORE Belgium
Bastion Tower, Floors 20&21
5 place du Champ de Mars
B-1050 BRUSSELS
[ info@simcore.be](mailto:info@simcore.be)
[ +32 2 550 37 69](tel:+3225503769)
[ +32 2 550 37 70](tel:+3225503770)
Denmark
#### Bent Aksel Jørgensen
Ivan Søndergaard Jensen
SIMCON A/S
Rugaardsvej 5
DK-8680 Ry
Denmark
[ info@simcon.dk](mailto:info@simcon.dk), [ automod@simcon.dk](mailto:automod@simcon.dk), [ simul8@simcon.dk](mailto:simul8@simcon.dk)
Support: [ automodsupport@simcon.dk](mailto:automodsupport@simcon.dk), [ simul8support@simcon.dk](mailto:simul8support@simcon.dk)
[ +45-86-89-03-22](tel:+4586890322)
[ +45-86-89-03-99](tel:+4586890399)
Support: [ 45-86-89-03-42](tel:4586890342)
France and French-speaking Switzerland
#### SIMCORE France
Parc Monier Immeuble Le Cassiopée
167 route de Lorient
F-35000 RENNES
[ info@simcore.fr](mailto:info@simcore.fr)
Support: [ support@simcore.fr](mailto:support@simcore.fr)
[ +33 2 99 14 88 50](tel:+33299148850)
[ +33 2 99 14 88 51](tel:+33299148851)
[ www.simcore.fr](https://www.simcore.fr/)
Germany, Holland, Austria and German-speaking Switzerland
#### Steffen Hertling
SimPlan AG
Niederlassung München
Manager: Steffen Hertling
Münchener Str. 13
85540 München-Haar
[ steffen.hertling@simplan.de](mailto:steffen.hertling@simplan.de)
Support: [ support@automod.de](mailto:support@automod.de)
[ +49 89 2189 7032 15](tel:+49892189703215)
[ +49 89 2189 7032 19](tel:+49892189703219)
Support: [ +49 89 2189 7032 25](tel:+49892189703225)
Italy and Italian-speaking Switzerland
#### Andrea Trere
Prolog S.r.l.
Via Mengolina 31
48018 Faenza RA
[ +39 0546 46073](tel:+39054646073)
[ +39 0546 607191](tel:+390546607191)
Info Line: [ +39 348 8706010](tel:+393488706010)
[ www.prolog.it](http://www.prolog.it/), [ www.automod.it](http://www.automod.it/)
Spain
#### SIMCORE Spain
C/Génova, 7-3°-Izda
E-28004 MADRID
[ info@simcore.es](mailto:info@simcore.es)
[ +34 91 181 97 05](tel:+34911819705)
[ +34 91 102 28 93](tel:+34911022893)
Sweden
#### Pär Ström
ÅF Industry AB
Grafiska vägen 2
Box 1551
SE-401 51 Gothenburg
Sweden
[ par.strom@afconsult.com](mailto:par.strom@afconsult.com)
[ +46-10-505-3408](tel:+46105053408)
[ +46-10-505-3010](tel:+46105053010)
[ www.automod.se](http://www.automod.se/)
Turkey
#### SELCO Consulting
Haldun Çelik
Prof. Hıfzı Özcan Cad. TasarımKent, Blok D, No:4 34750 Ataşehir İSTANBULTurkey
[ info@selco.com.tr](mailto:info@selco.com.tr)
[ +90 216 5725001](tel:+902165725001), [ +90 533 360 0668](tel:+905333600668)
[ www.selco.com.tr](http://www.selco.com.tr)
United Kingdom
#### Graham Carter
Autologic Systems Ltd.
60 High Street
Tetsworth
Oxfordshire OX9 7AB
England
Support: [ support@autologic-systems.co.uk](mailto:support@autologic-systems.co.uk)
[ +44 (0) 1844 281380](tel:+4401844281380), [+44 (0) 7710 172577](tel:+4407710172577)
[ +44 (0) 1844 281874](tel:+4401844281874)
[ www.autologic-systems.co.uk](http://www.autologic-systems.co.uk/)
South America
### South America
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
Australia & New Zealand
### Australia & New Zealand
#### Applied Materials, Inc.
#### AutoMod Support, North America
5225 West Wiley Post Way
Suite 275
Salt Lake City, UT 84116
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
---
### [PROMIS User Group](https://appliedsmartfactory.com/promis-user-group/)
**Published:** August 31, 2023
**Author:** Jill Oana
**Content:**
# SmartFactory MES
automation solutions
# Introducing…..
# PROMIS® on RedHat® Enterprise Linux®
- Proven operating system; mainstream hardware
- Extends the lifetime of your PROMIS assets
# For details about the new PROMIS on Linux
##### Watch the 2023 PROMIS User Group Video Replay
[ Watch webinar replay ](/blog/2023-promis-user-group/)
---
### [Innovation Forum 2024](https://appliedsmartfactory.com/innovationforum2024/)
**Published:** December 13, 2023
**Author:** Applied Smartfactory
**Content:**
# Optimizing existing assets
#### SmartFactory productivity solutions fully integrated
### 21st Innovation Forum for Automation
##### January 25 - 26, 2024 | Dresden, Germany
## Presentation | **Leveraging the Digital Twin to Boost Semiconductor Manufacturing Factory Productivity**
### Thursday, January 25 at 13:20 - 13:55
### Madhav Kidambi
##### Director, Technical Marketing
Applied Materials | Automation Products Group
[ Details ](https://www.innovation-forum-automation.com/speaker/madhav-kidambi-2/)
### Keynote topics:
### How digital twin is being used in semiconductor manufacturing facilities
### Enabling to improve quality and throughput while reducing overall costs
### Framework for digital twin that supports reusability, extensibility and interoperability
### For questions, contact
[Madhav\_Kidambi@amat.com](mailto:Madhav_Kidambi@amat.com)
### To view full conference agenda
[ Visit agenda ](https://www.innovation-forum-automation.com/conference/agenda/)
[ SmartFactory Productivity Solutions ](/semiconductor/productivity-solutions/)
Optimizing Existing Assets
- [ SmartFactory Insights Blog ](/blog/category/productivity/)
- [ SmartFactory Semiconductor Solutions ](https://www.linkedin.com/showcase/applied-smartfactory/)
- [ appliedsmartfactory.com ](/semiconductor)
## 21st Innovation Forum for Automation
January 25 – 26, 2024 | Dresden, Germany
---
### [Automation Solutions](https://appliedsmartfactory.com/semiconductor-automation-solutions/)
**Published:** December 18, 2023
**Author:** Applied Smartfactory
**Content:**
# Supercharge Your Productivity with Advanced Factory Automation
## Streamline deployment and achieve success with expert guidance.
Ready to revolutionize your semiconductor manufacturing? Our SmartFactory team of automation experts will work closely with you to overcome deployment hurdles and develop a tailored roadmap for achieving full automation. We have the expertise to optimize your processes and maximize efficiencies in factories of any size.
Download free article
#### [Pros and cons of various scheduling solutions for semiconductor factories](/semiconductor-blog/scheduling/scheduling-solutions-for-semiconductor-factories/)
Choose scheduling that will be the right fit for your factory needs - Heuristics
- Simulation
- Optimization
- Positive attributes
- Limitations
[ Learn More ](/semiconductor-blog/scheduling/scheduling-solutions-for-semiconductor-factories/)
#### [Synergizing Fault Detection and SPC: smarter manufacturing solution for cost reduction](/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
Integrating the functions of SPC and Fault Detection helps semiconductor manufacturers achieve higher quality, reliability, and efficiency.
- Understanding SPC-FD systems integration
- Correlating equipment data with inline measurements
- The Pearson Correlation Coefficient
- Implementing SPC with correlation analysis
[ Learn More ](/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
#### [Reduce cycle time with a powerful MES strategy](/semiconductor-blog/manufacturing-execution/mes-strategy/)
The MES is the operational backbone of many factories and can help monitor, control, and optimize production processes real-time. - Provide real-time visibility
- Automate data collection
- Use predictive analytics
- Improve communications and collaboration
- Optimize operational efficiencies
[ Learn More ](/semiconductor-blog/manufacturing-execution/mes-strategy/)
#### [Enhancing decision-making in real-time scheduling: leveraging data and AI technology](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/)
Find out the role of data in helping semiconductor manufacturers achieve greater benefits in productivity and quality.
- Data in scheduling and dispatching
- Push and pull interventions
- Event handling by rule-based systems
- Moving to predictive systems
- Impact of data
[ Learn More ](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/)
### Resources
[ 
#### SmartClips
These videos by our subject matter experts discuss how our customers are relying on SmartFactory…
](/smartclips/)
[ 
#### Semiconductor Events
Engage with our factory automation technology experts to gain a competitive advantage in semiconductor manufacturing.
](/semiconductor/events/)
[ 
#### SmartFactory MES solutions
Explore our videos to learn how to make your MES thrive vs survive in semiconductor factories of any size.
](/semiconductor-mes-video-channel/)
[ 
#### Semiconductor Blog
Learn how semiconductor factory automation experts are navigating technology, people…
](/semiconductor-blog/)
---
### [Schedule a Meeting](https://appliedsmartfactory.com/ai/schedule-a-meeting/)
**Published:** May 2, 2025
**Author:** Jill Oana
**Content:**
# Schedule a Meeting
Please complete the form and our AI solution manager will get back to you shortly.
All fields marked * are mandatory.
First Name: \*
Last Name: \*
Business Email: \*
Country: \*
Select your countryAfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Job Title: \*
Department:
Company Name: \*
No. of Employees: \*
Please select1-2021-200201-10,00010,000+
Meeting Topics (check all that apply) \*
Current Generative AI CapabilitiesGetting Started GuideGenerative AI RoadmapOther (Mention in Message)
Let us know how we can assist:
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
---
### [SmartClips](https://appliedsmartfactory.com/smartclips/)
**Published:** May 7, 2024
**Author:** Applied Smartfactory
**Content:**
# SmartClips
[ Interviews ](/smartclips/#interviews)
[ Panels ](/smartclips/#panel)
These videos by our subject matter experts discuss how our customers are relying on SmartFactory automation solutions to deliver what their customers need to improve quality and efficiency in the Fab.
### Panel Discussions
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
### [AI: Revolutionizing Factory Automation and Shaping Our Experiences](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
Join our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier as they explore how AI is accelerating the next generation of factory automation and transforming our daily lives.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
### [SmartFactory: Driving the Future of Manufacturing](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
Gain valuable insights as our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier explore how SmartFactory automation solutions are reshaping productivity and quality in factories of any size.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
### [Empowering Manufacturing Excellence with SmartFactory MES Automation Solutions](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
Learn from our technical leaders, David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier how SmartFactory MES automation solutions are at the forefront of advancing factory automation with fully integrated capabilities.
### Interviews
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
## [Efficiency Unleashed: Optimizing the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
Amnon Shenfeld shares his unique approach to maximizing efficiency in the fab. Discover the innovative methods that set SmartFactory apart.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
### [Innovation Integration: Seizing New Opportunities](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
Bing Wang discusses how SmartFactory's solutions empower customers to innovate and capture new opportunities through seamless integration. Explore the pathways to innovation with SmartFactory.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
### [Human-Centric Solutions: SmartFactory’s Approach](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
Selim Nahas discusses SmartFactory's commitment to making people an essential part of the solution. Embrace the human element in smart manufacturing solutions.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
### [MES Integration: Uniquely SmartFactory](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
Dan Meier dives into what makes SmartFactory's MES integration capabilities stand out. Learn about the unique solutions that can redefine your manufacturing operations.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
### [SPC Strategies: Realizing Excellence](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
Vishali Ragam unveils how SmartFactory's Statistical Process Control is driving quality improvements for customers. Learn the secrets to achieving excellence in quality management.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
### [Smart Manufacturing: The Evolutionary Edge](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
Phil Walker explores the integral role of SmartFactory in the evolution of smart manufacturing. Witness the cutting-edge advancements shaping the industry's future.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
### [Performance Pioneers: Factory Innovations](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
Chris Reeves shares transformative strategies for boosting quality and performance in factories. Gain valuable knowledge from the forefront of manufacturing innovation.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
### [Quality Quest: Insights from the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
Join David Hanny as he delves into what SmartFactory customers truly desire to enhance quality in their manufacturing processes. Discover the pivotal insights that can revolutionize the fab floor.
### Key Take-aways for Customers
### Enable innovation by integration
### Improve quality and performance
### Unique MES integration capabilities
### Seize new opportunities
### Major role in the evolution of smart manufacturing
### Prioritizes making people part of the solution
---
### [SmartClips](https://appliedsmartfactory.com/smartclips/)
**Published:** May 7, 2024
**Author:** Applied Smartfactory
**Content:**
# SmartClips
[ Interviews ](/smartclips/#interviews)
[ Panels ](/smartclips/#panel)
These videos by our subject matter experts discuss how our customers are relying on SmartFactory automation solutions to deliver what their customers need to improve quality and efficiency in the Fab.
### Panel Discussions
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
### [AI: Revolutionizing Factory Automation and Shaping Our Experiences](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
Join our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier as they explore how AI is accelerating the next generation of factory automation and transforming our daily lives.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
### [SmartFactory: Driving the Future of Manufacturing](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
Gain valuable insights as our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier explore how SmartFactory automation solutions are reshaping productivity and quality in factories of any size.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
### [Empowering Manufacturing Excellence with SmartFactory MES Automation Solutions](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
Learn from our technical leaders, David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier how SmartFactory MES automation solutions are at the forefront of advancing factory automation with fully integrated capabilities.
### Interviews
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
## [Efficiency Unleashed: Optimizing the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
Amnon Shenfeld shares his unique approach to maximizing efficiency in the fab. Discover the innovative methods that set SmartFactory apart.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
### [Innovation Integration: Seizing New Opportunities](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
Bing Wang discusses how SmartFactory's solutions empower customers to innovate and capture new opportunities through seamless integration. Explore the pathways to innovation with SmartFactory.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
### [Human-Centric Solutions: SmartFactory’s Approach](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
Selim Nahas discusses SmartFactory's commitment to making people an essential part of the solution. Embrace the human element in smart manufacturing solutions.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
### [MES Integration: Uniquely SmartFactory](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
Dan Meier dives into what makes SmartFactory's MES integration capabilities stand out. Learn about the unique solutions that can redefine your manufacturing operations.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
### [SPC Strategies: Realizing Excellence](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
Vishali Ragam unveils how SmartFactory's Statistical Process Control is driving quality improvements for customers. Learn the secrets to achieving excellence in quality management.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
### [Smart Manufacturing: The Evolutionary Edge](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
Phil Walker explores the integral role of SmartFactory in the evolution of smart manufacturing. Witness the cutting-edge advancements shaping the industry's future.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
### [Performance Pioneers: Factory Innovations](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
Chris Reeves shares transformative strategies for boosting quality and performance in factories. Gain valuable knowledge from the forefront of manufacturing innovation.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
### [Quality Quest: Insights from the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
Join David Hanny as he delves into what SmartFactory customers truly desire to enhance quality in their manufacturing processes. Discover the pivotal insights that can revolutionize the fab floor.
### Key Take-aways for Customers
### Enable innovation by integration
### Improve quality and performance
### Unique MES integration capabilities
### Seize new opportunities
### Major role in the evolution of smart manufacturing
### Prioritizes making people part of the solution
---
### [SmartClips](https://appliedsmartfactory.com/smartclips/)
**Published:** May 7, 2024
**Author:** Applied Smartfactory
**Content:**
# SmartClips
[ Interviews ](/smartclips/#interviews)
[ Panels ](/smartclips/#panel)
These videos by our subject matter experts discuss how our customers are relying on SmartFactory automation solutions to deliver what their customers need to improve quality and efficiency in the Fab.
### Panel Discussions
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
### [AI: Revolutionizing Factory Automation and Shaping Our Experiences](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
Join our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier as they explore how AI is accelerating the next generation of factory automation and transforming our daily lives.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
### [SmartFactory: Driving the Future of Manufacturing](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
Gain valuable insights as our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier explore how SmartFactory automation solutions are reshaping productivity and quality in factories of any size.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
### [Empowering Manufacturing Excellence with SmartFactory MES Automation Solutions](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
Learn from our technical leaders, David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier how SmartFactory MES automation solutions are at the forefront of advancing factory automation with fully integrated capabilities.
### Interviews
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
## [Efficiency Unleashed: Optimizing the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
Amnon Shenfeld shares his unique approach to maximizing efficiency in the fab. Discover the innovative methods that set SmartFactory apart.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
### [Innovation Integration: Seizing New Opportunities](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
Bing Wang discusses how SmartFactory's solutions empower customers to innovate and capture new opportunities through seamless integration. Explore the pathways to innovation with SmartFactory.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
### [Human-Centric Solutions: SmartFactory’s Approach](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
Selim Nahas discusses SmartFactory's commitment to making people an essential part of the solution. Embrace the human element in smart manufacturing solutions.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
### [MES Integration: Uniquely SmartFactory](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
Dan Meier dives into what makes SmartFactory's MES integration capabilities stand out. Learn about the unique solutions that can redefine your manufacturing operations.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
### [SPC Strategies: Realizing Excellence](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
Vishali Ragam unveils how SmartFactory's Statistical Process Control is driving quality improvements for customers. Learn the secrets to achieving excellence in quality management.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
### [Smart Manufacturing: The Evolutionary Edge](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
Phil Walker explores the integral role of SmartFactory in the evolution of smart manufacturing. Witness the cutting-edge advancements shaping the industry's future.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
### [Performance Pioneers: Factory Innovations](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
Chris Reeves shares transformative strategies for boosting quality and performance in factories. Gain valuable knowledge from the forefront of manufacturing innovation.
[  ](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
### [Quality Quest: Insights from the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
Join David Hanny as he delves into what SmartFactory customers truly desire to enhance quality in their manufacturing processes. Discover the pivotal insights that can revolutionize the fab floor.
### Key Take-aways for Customers
### Enable innovation by integration
### Improve quality and performance
### Unique MES integration capabilities
### Seize new opportunities
### Major role in the evolution of smart manufacturing
### Prioritizes making people part of the solution
---
### [MES Video Channel](https://appliedsmartfactory.com/semiconductor-mes-video-channel/)
**Published:** July 23, 2024
**Author:** Applied Smartfactory
**Content:**
Explore our videos to learn how to make your MES thrive vs survive in semiconductor factories of any size.
# Advancing Factory Automation with SmartFactory MES solutions
### Alarm Management (2-Part Series)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/avoid-alarm-overload-in-your-factory/)
### [Stop the noise! Avoid alarm overload to identify the most important issues in your factory](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/avoid-alarm-overload-in-your-factory/)
SmartFactory Alarm Management improves productivity by integrating and automating alarms
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/streamline-alarm-management/)
### [Streamline alarm management for a faster response and resolution](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/streamline-alarm-management/)
Simplify alarm management throughout the factory by integrating SmartFactory Alarm Management with key systems
### What Is An MES? (5-Part Series)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
### [What is an MES?
An aspirational view from the factory floor (Part 1/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
The MES is the operational backbone of the factory. But it should be so much more!
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
### [What is an MES?
All about process configurations (Part 2/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
Taking a deep dive into MES configurations.
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
### [What is an MES?
Lot tracking: the MES at run-time (Part 3/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
Keeping track of all the moving parts through lot tracking.
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
### [What is an MES?
Data and metrics that drive the factory (Part 4/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
Key MES data and metrics…and how manufacturers use them.
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
### [What is an MES?
Reporting and analytics for continuous improvement (Part 5/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
MES reporting and analysis | your tools to answer questions and solve problems.
### Beyond the MES (2-Part Series)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
### [Beyond the MES: Crawl. Walk. Run. (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
The MES provides a critical foundation for the semiconductor factory as needs change over time.
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
### [Beyond the MES: Fly. (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
Advanced capabilities and MES provide the intelligence that is key to the ‘lights out’ factory
---
### [Support](https://appliedsmartfactory.com/support/)
**Published:** December 3, 2021
**Author:** Applied Smartfactory
**Content:**
Global Support
# Software Portal
## Important Links:
[ ](https://amat.service-now.com/csm)
#### [ Portal Login ](https://amat.service-now.com/csm)
[ ](https://partner.amat.com/identityiq/external/amat/resetPassword/rstPwdBaseForm.jsf)
#### [ Reset your password ](https://partner.amat.com/identityiq/external/amat/resetPassword/rstPwdBaseForm.jsf)
[ ](/support-contacts)
#### [ View support center contact info by region ](/support-contacts)
[ ](mailto:customer_portal_support@amat.com)
#### [ Need Portal help? Contact Us ](mailto:customer_portal_support@amat.com)
**Impact from Apache log4j Vulnerability**
Applied Materials Automation Products Group (APG) continues to work on investigating and identifying mitigations for the Apache Log4J vulnerability (CVE-2021-44228), referred to as the “Log4Shell” vulnerability. APG continues to make the investigation and remediation of this vulnerability its top priority.
More information regarding CVE-2021-44228 is available from the Apache Announcement:
Please contact APG support team for information on products which may be impacted and also technical details on resolution.
#### The software portal enables users with current maintenance contracts to receive:
- Latest GA releases and patches
- Product related announcements
- Access to software support experts
#### While logged in, users can:
- Check the status of current cases
- Log new cases
- Access the Applied Box for FTP options
- Examine knowledge base materials
---
### [Battery](https://appliedsmartfactory.com/battery/)
**Published:** May 15, 2025
**Author:** Applied Smartfactory
**Content:**
# Maximize efficiency, quality, and safety with automation.
[ Read More ](#)
### Boost Yield and Performance
Improve uptime, reduce defects, and elevate quality with real-time insights and predictive analytics.
### Optimize Operations and Reduce Downtime
Data-driven control and predictive maintenance extend equipment availability and improve operational efficiency.
### Automate Material Movements
Orchestrate WIP across your battery production line using automated handling systems.
## Seamlessly integrate our solutions for immediate benefits in your operations
### Unified Process Control
Gain a holistic view of equipment and
process health.
### Sustainability
Implement eco-friendly practices for a
greener future.
### Data-Driven Decision Making
Leverage real-time monitoring and analytics
for informed decisions.
### Advanced Automation
Maximize efficiency, quality, and safety while
reducing costs.
## Battery Blog
Learn how automation experts are transforming manufacturing with SmartFactory battery solutions.
##### [Battery blog](/battery-blog/)
## Battery Events
Engage with our automation technology experts to gain a competitive advantage in battery manufacturing.
##### [Battery events](/battery-events/)
---
### [Battery](https://appliedsmartfactory.com/battery/)
**Published:** May 15, 2025
**Author:** Applied Smartfactory
**Content:**
# Maximize efficiency, quality, and safety with automation.
[ Read More ](#)
### Boost Yield and Performance
Improve uptime, reduce defects, and elevate quality with real-time insights and predictive analytics.
### Optimize Operations and Reduce Downtime
Data-driven control and predictive maintenance extend equipment availability and improve operational efficiency.
### Automate Material Movements
Orchestrate WIP across your battery production line using automated handling systems.
## Seamlessly integrate our solutions for immediate benefits in your operations
### Unified Process Control
Gain a holistic view of equipment and
process health.
### Sustainability
Implement eco-friendly practices for a
greener future.
### Data-Driven Decision Making
Leverage real-time monitoring and analytics
for informed decisions.
### Advanced Automation
Maximize efficiency, quality, and safety while
reducing costs.
## Battery Blog
Learn how automation experts are transforming manufacturing with SmartFactory battery solutions.
##### [Battery blog](/battery-blog/)
## Battery Events
Engage with our automation technology experts to gain a competitive advantage in battery manufacturing.
##### [Battery events](/battery-events/)
---
### [Advanced Scheduling](https://appliedsmartfactory.com/productivity-solutions/advanced-scheduling/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Advanced Scheduling
# Maximize capacity with optimized scheduling
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## Are you only using dispatching rules to maximize tool usage?
SmartFactory Advanced Scheduling is an optimization-based scheduling system for semiconductor manufacturers that addresses one of the industry’s biggest issues—managing lot movement to better maximize the use of tools. Both dispatching and scheduling are needed, but without optimized scheduling, even efficient fabs fail to maximize capacity.
## Why choose SmartFactory Advanced Scheduling?
### >1% litho utilization improvement
### 2.1% throughput improvement
## What can you gain from our approach?
## Fast schedule updates
- Uses real-time factory data to continually evaluate data from multiple upstream & downstream systems
- Uses sophisticated algorithms -- not possible with dispatching systems alone
- Produces up-to-the-minute schedule updates for lots and reticles
## Increased returns on equipment
- Enables customers to defer or eliminate investment in additional lithography equipment by increasing litho utilization
- Reduces capex spending on bottleneck tools
## Common framework
- Built on proven APF platform and common data model to execute planning, scheduling, and dispatching algorithms on factory events
- Provides out-of-box schedulers for fab and assembly and test areas
- No additional integration required
---
### [SmartFactory Knowledge Advisor](https://appliedsmartfactory.com/process-quality-solutions/knowledge-advisor/)
**Published:** June 5, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory Knowledge Advisor
# Bridge the gap between data, knowledge, and execution
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How can semiconductor manufacturers make process quality intelligent, scalable, and adaptive?
SmartFactory Knowledge Advisor is a next-generation Process Quality solution and factory-wide knowledge platform that leverages agentic AI to transform how semiconductor manufacturers investigate, diagnose, and resolve process and equipment issues.
## Why choose SmartFactory Knowledge Advisor?
**Proven production results include:**
### 60% faster resolution of SPC and FDC violations
### Reduced repeat violations and asset downtime
#### Improved yield through standardized corrective actions
## What can you gain from our approach?
## Connected data and reusable knowledge
- Unifies factory data with enterprise knowledge
- Captures and reuses troubleshooting insights across teams
- Transforms siloed information into a scalable knowledge platform
## Faster, more consistent decision-making
- Automates alarm and violation investigation across systems
- Applies AI-driven diagnosis with prescriptive next steps
- Reduces variability in how issues are analyzed and resolved
## More efficient engineering execution
- Eliminates manual, trial-and-error troubleshooting workflows
- Guides engineers through a structured, repeatable resolution path
- Shortens investigation cycles and improves response consistency
---
### [SmartFactory Knowledge Advisor](https://appliedsmartfactory.com/process-quality-solutions/knowledge-advisor/)
**Published:** June 5, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory Knowledge Advisor
# Bridge the gap between data, knowledge, and execution
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How can semiconductor manufacturers make process quality intelligent, scalable, and adaptive?
SmartFactory Knowledge Advisor is a next-generation Process Quality solution and factory-wide knowledge platform that leverages agentic AI to transform how semiconductor manufacturers investigate, diagnose, and resolve process and equipment issues.
## Why choose SmartFactory Knowledge Advisor?
**Proven production results include:**
### 60% faster resolution of SPC and FDC violations
### Reduced repeat violations and asset downtime
#### Improved yield through standardized corrective actions
## What can you gain from our approach?
## Connected data and reusable knowledge
- Unifies factory data with enterprise knowledge
- Captures and reuses troubleshooting insights across teams
- Transforms siloed information into a scalable knowledge platform
## Faster, more consistent decision-making
- Automates alarm and violation investigation across systems
- Applies AI-driven diagnosis with prescriptive next steps
- Reduces variability in how issues are analyzed and resolved
## More efficient engineering execution
- Eliminates manual, trial-and-error troubleshooting workflows
- Guides engineers through a structured, repeatable resolution path
- Shortens investigation cycles and improves response consistency
---
### [SmartFactory AI](https://appliedsmartfactory.com/ai/)
**Published:** April 3, 2025
**Author:** Applied Smartfactory
**Content:**
# AI for Smarter, Faster Fab Decisions
## Let’s explore how AI is transforming manufacturing
AI acts on large datasets, providing immediate insights for faster, more accurate decisions transforming your manufacturing landscape.
## Why?
Because your competition doesn’t rest.
### AI improves precision and accelerates decision-making
By integrating data from sensors, machines, and people it boosts yield, speeds up production, reduces costs, and enhances product quality.
AI predicts equipment failures, schedules equipment maintenance, and optimizes supply chains, leading to fewer disruptions and higher efficiency.
### Manage scalable AI solutions with your existing infrastructure using SmartFactory AI IQworksTM
### Edge & Cloud Integration
Scalable AI framework
### Quality Controls
Higher mix, low volume
### Latency Reduction
Rapid data & decisions
### Signal Management
Actionable insights
### Dynamic Scheduling
Factory adaptability
### Real-time Learning Environment
Continuous improvement capabilities
### Generative AI
Enhanced productivity
### Good Manufacturing Practices
Standards compliance & audit control
[ Explore SmartFactory AI IQworks ](/ai/smartfactory-iqworks/)
### Watch and Learn
#### Shape the future of seamless manufacturing with SmartFactory AI solutions
[ Watch Video ](#)
[](https://appliedsmartfactory.com/semiconductor-blog-category/ai-ml/)
#### [Learn how AI/ML automation experts are transforming manufacturing with SmartFactory AI solutions.](/semiconductor-blog-category/ai-ml/)
[ Read AI/ML Blog ](#)
[](https://appliedsmartfactory.com/ai/smartfactory-iqworks/)
#### [Manage scalable AI solutions with your existing infrastructure using SmartFactory AI IQworks](/semiconductor-blog/smart-manufacturing/leaping-ahead-factory-automation/)
[ Explore Now ](#)
# SmartFactory Podcast
## Semi‑Insightful
This podcast series features conversations on how manufacturers use AI, software, and data to run factory operations better and faster.
[ **Explore podcast** ](/podcast/semi-insightful/)
---
### [SmartFactory AI](https://appliedsmartfactory.com/ai/)
**Published:** April 3, 2025
**Author:** Applied Smartfactory
**Content:**
# AI for Smarter, Faster Fab Decisions
## Let’s explore how AI is transforming manufacturing
AI acts on large datasets, providing immediate insights for faster, more accurate decisions transforming your manufacturing landscape.
## Why?
Because your competition doesn’t rest.
### AI improves precision and accelerates decision-making
By integrating data from sensors, machines, and people it boosts yield, speeds up production, reduces costs, and enhances product quality.
AI predicts equipment failures, schedules equipment maintenance, and optimizes supply chains, leading to fewer disruptions and higher efficiency.
### Manage scalable AI solutions with your existing infrastructure using SmartFactory AI IQworksTM
### Edge & Cloud Integration
Scalable AI framework
### Quality Controls
Higher mix, low volume
### Latency Reduction
Rapid data & decisions
### Signal Management
Actionable insights
### Dynamic Scheduling
Factory adaptability
### Real-time Learning Environment
Continuous improvement capabilities
### Generative AI
Enhanced productivity
### Good Manufacturing Practices
Standards compliance & audit control
[ Explore SmartFactory AI IQworks ](/ai/smartfactory-iqworks/)
### Watch and Learn
#### Shape the future of seamless manufacturing with SmartFactory AI solutions
[ Watch Video ](#)
[](https://appliedsmartfactory.com/semiconductor-blog-category/ai-ml/)
#### [Learn how AI/ML automation experts are transforming manufacturing with SmartFactory AI solutions.](/semiconductor-blog-category/ai-ml/)
[ Read AI/ML Blog ](#)
[](https://appliedsmartfactory.com/ai/smartfactory-iqworks/)
#### [Manage scalable AI solutions with your existing infrastructure using SmartFactory AI IQworks](/semiconductor-blog/smart-manufacturing/leaping-ahead-factory-automation/)
[ Explore Now ](#)
# SmartFactory Podcast
## Semi‑Insightful
This podcast series features conversations on how manufacturers use AI, software, and data to run factory operations better and faster.
[ **Explore podcast** ](/podcast/semi-insightful/)
---
### [About us](https://appliedsmartfactory.com/about/)
**Published:** February 24, 2025
**Author:** Applied Smartfactory
**Content:**
We
# **Transform Manufacturing**
Global Automation Experts
0 +
Productivity and Quality Improvements
0 + years
Global Support Services
x7
Over the last 35+ years, our innovations have fundamentally changed how manufacturing works and how people interact through technology. Our SmartFactory portfolio offers integrated automation software solutions designed to maximize efficiency and empower manufacturing operations.
## Accelerate Innovation
We provide services like productivity enhancement, process quality improvement, MES integration, and supply chain management—from enterprise planning to production control.
With AI-powered automation and advanced scheduling technologies, manufacturers can elevate performance, optimize production flow, minimize downtime, and drive continuous improvement. Our holistic approach enables seamless monitoring and control of operations.
## Path to the Future
Our expertise in manufacturing automation drives breakthroughs in AI, big data, and cloud technologies, enabling manufacturers to gain a significant competitive advantage.
The world’s brightest minds—visionaries, engineers, scientists—bring their expertise in materials engineering and come together at Applied with a collection of diverse opinions, experiences and backgrounds to make possible better ideas and breakthrough innovations.
## Modernizing Automation
SmartFactory supports a practical, incremental approach to automation modernization. Manufacturers can improve performance in manageable steps—reducing risk while delivering measurable results along the way.
This approach enables modernization at a pace aligned to business priorities, operational readiness, and long-term objectives—without the disruption of large, all-at-once transformations.
## Industry insights from our experts
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)### Quality Quest: Insights from the Fab
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)### Performance Pioneers: Factory Innovations
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)### Smart Manufacturing: The Evolutionary Edge
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)### SPC Strategies: Realizing Excellence
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)### MES Integration: Uniquely SmartFactory
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)### Human-Centric Solutions: SmartFactory’s Approach
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)### Innovation Integration: Seizing New Opportunities
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)### Efficiency Unleashed: Optimizing the Fab
### SmartFactory Recognized for Contributions
#### Award of Excellence
RTD Private Cloud team recognized for most innovative solution at Applied Materials Engineering & Technology Conference
#### STMicroelectronics Award
SmartFactory wins best practices on increasing factory throughput through automation
#### Best Cooperative Supplier
SmartFactory played a crucial role in helping Gree establish Asia’s first fully automated 6-inch SiC factory, which ensuring the successful launch and stable operation of all systems.
#### Excellent Supplier
SmartFactory was honored for its exceptional support and premium service in enhancing factory productivity.
---
### [SmartFactory Advanced Recipe Tuning](https://appliedsmartfactory.com/process-quality-solutions/advanced-recipe-tuning/)
**Published:** July 20, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory AI™ Run-to-Run Advanced Recipe Tuning
# Improve process control for complex and low-volume products
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How do you improve yield and reduce variability when traditional R2R controllers struggle in high mix low volume environments?
SmartFactory AI Run-to-Run Advanced Recipe Tuning uses AI/ML to enhance existing R2R control systems, improving recipe adjustments for high-mix and low-volume semiconductor manufacturing while enabling tighter process control, faster optimization, and measurable yield gains without disrupting current infrastructure.
## Why choose SmartFactory AI Run-to-Run Advanced Recipe Tuning?
SmartFactory AI Run-to-Run Advanced Recipe Tuning helps teams improve process capability, deploy in months rather than years, and extend existing R2R investments without adding complexity.
### 10% improvement in Cpk
### 5-month deployment
### Seamless integration with existing infrastructure
## What can you gain from our approach?
## Improved process stability
- Augments traditional R2R control systems with AI-enhanced recipe tuning recommendations
- Delivers advanced control for nonlinear processes
- Creates more consistent process performance across products and operating conditions
## Improved yield and product quality
- Machine learning models improve recipe parameter adjustment accuracy
- Delivers more effective control for high-mix, low-volume manufacturing environments
- Creates measurable process capability improvements
## Faster deployment of AI for process control
- Provides a platform for rapid model training, deployment, and lifecycle management
- Delivers a web-based user experience that simplifies model implementation and adoption
- Creates visibility into model performance through integrated monitoring, reporting, and analytics
---
### [Factory Automation | Applied SmartFactory Solutions](https://appliedsmartfactory.com/)
**Published:** June 24, 2021
**Author:** Applied Smartfactory
**Content:**
# よりスマートな製造で、
見える成果を実現
Applied SmartFactoryは、AIを活用した自動化と統合型製造ソフトウェアにより、歩留まりの向上、オペレーショナルリスクの低減、生産性の最大化を支援します。
[SmartFactory半導体ソリューション](/ja/semiconductor/)
生産性と品質の向上によって 製造を変革する 詳細はこちら
1/3
[SmartFactory AIソリューション](/ja/ai/)
洞察とスピードで自律型製造を進化させる 詳細はこちら
2/3
[SmartFactoryバッテリーソリューション](/ja/battery/)
製造を、パワーと精度で導く 詳細はこちら
3/3
SmartFactory半導体ソリューションで
生産性と品質を向上させる
[生産性](/ja/semiconductor/productivity-solutions/)[ 品質](/ja/semiconductor/process-quality-solutions/)[製造実行システム（MES）](/ja/semiconductor/manufacturing-execution-solutions/)[サプライチェーン](/ja/semiconductor/supply-chain-solutions/)
1/2
SmartFactory AI ソリューションで
製造の自動化を加速する
[SmartFactory AIの詳細はこちら](/ja/ai/)
2/2
SmartFactory自動化ソリューションで
製造業を変革する
[SmartFactory](/ja/semiconductor/)
SmartFactory AI ソリューションで
製造の自動化を加速する
[SmartFactory AIの詳細はこちら](/ja/ai/)
SmartFactory半導体ソリューションで
生産性と品質を向上させる
[生産性](/ja/semiconductor/productivity-solutions/)[ 品質](/ja/semiconductor/process-quality-solutions/)[製造実行システム（MES）](/ja/semiconductor/manufacturing-execution-solutions/)[サプライチェーン](/ja/semiconductor/supply-chain-solutions/)
# 完全に統合されたソリューション
当社のSmartFactoryポートフォリオは、効率を最大化し、製造業務を強化する ために設計された統合自動化ソフトウェアソリューションを提供しております。
生産性の向上、プロセス品質の向上、MESの統合、サプライチェーンの管理など、企業計画から生産管理まですべてをカバする包括的なサービスを提供
します。
AIを活用した自動化と高度なスケジューリング技術により、メーカーはパフォーマンスを向上させ、生産フローを最適化し、ダウンタイムを最小限に抑え、継続的な改善を推進することができます。また、当社の総合的なアプローチにより、オペレーションのシームレスな監視と管理を可能にします。
当社のオートメーション専門チームが、工場の潜在能力を最大限に引き出し、ダイナミックな製造環境において、優れた成果を達成し、持続可能な成長を
促進します。
[ ソリューションを見る ](/ja/semiconductor/)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/06/applied-smartfactory-integrated-solutions-2.jpg)
[ View minds.ai ](https://minds.ai/)
Announcement
### Applied Materials
Acquires minds.ai
minds.ai specializes in reinforcement learning and deep learning AI for semiconductor manufacturing and is now part of the **Applied SmartFactory®** portfolio.
COMPETITIVE ADVANTAGE
SmartFactory customers gain advanced AI built for semiconductor fabs — optimizing yield, accelerating decisions, and advancing toward autonomous factory operations.
### Explore our blogs
Learn how factory automation experts are navigating technology, people, operations, and market dynamics to gain competitive advantage in manufacturing.
[  ](/semiconductor-blog/)
[Semi blog](/semiconductor-blog/)
[  ](/pharmaceutical-blog/)
[Pharma blog](/pharmaceutical-blog/)
### Competitive advantage with IQworks
Robust AI/ML models and fully integrated solutions increase quality and reliability across every stage of the manufacturing process, for any size factory. Gain an edge over the competition through better prediction, prevention and optimization.
[ More about IQworks ](#)
## SmartFactory関連ブログ
自動化のエキスパートから、SmartFactoryの自律型ソリューションで製造を変革する方法を学びましょう。
##### [半導体関連ブログ](/ja/semiconductor-blog/)
## SmartFactory関連イベント
当社の自動化のエキスパートと提携して、スマートな製造のアドバンテージを迅速に実現しましょう。
##### [半導体イベント](/ja/semiconductor-events/)
## 測定可能な改善点
自動化ソリューションを導入することで、みなさまの日常業務をより迅速に完了し、問題が発生する前に特定し、解決策を実装できるようになります。測定可能な改善には、下記の項目は含まれています。
### サイクルタイムの改善
### 歩留まりの向上
### スループットの向上
### 設備のダウンタイムの削減
### リスクの低減
### 市場投入までの時間の短縮
### 欠陥品の低減
### スケジューリングの効率化
## 自動化リーダー
当社のグローバルのエキスパートチームは、製造自動化ソリューションについて定期的に情報提供を行える業界のリーダーです。彼らは専門知識を活用して、自動化基盤を高めることができるスケーラブルなソリューションを開発しています。
自動化推進を始めた方、これから本格的に自動化を始める方、それぞれの方に、当社のエキスパートらは、自動化を実現するために必要なロードマップを提供します。
[ 独自のKPIを改善することを目指し、私たちとつながりを持ちましょう ](/ja/connect/)
### Upcoming events
[ All Events ](https://appliedsmartfactory.com/ja/semiconductor/events/)
### [SmartFactory Symposium India 2026](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
September 18, 2026
[ Register Now ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
### [A New Design Mindset to Enable AI-Driven Factory Automation](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
October 15, 2026
[ More Info ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
### [SEMICON Europa](https://www.semiconeuropa.org/)
November 10-13, 2026
| Munich, Germany
[ More Info ](https://www.semiconeuropa.org/)
### SmartFactory Symposium Japan 2026
December 8, 2026
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2026/)
December 6-9, 2026
| Glasgow, Scotland
[ More Info ](https://meetings.informs.org/wordpress/wsc2026/)
### [SmartFactory Webinar Replays](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
Available 24/7
[ More Info ](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
---
### [首页](https://appliedsmartfactory.com/)
**Published:** July 22, 2021
**Author:** Applied Smartfactory
**Content:**
# 更智能的制造
可量化的成果
应用材料公司 SmartFactory 解决方案通过 AI 驱动的自动化与集成化制造软件，帮助制造商提升良率、降低运营风险并提高生产效率。
[SmartFactory 半导体解决方案](/zh-hans/semiconductor/)
以质量与生产力驱动制造业变革 了解更多
1/2
[SmartFactory AI 解决方案](/zh-hans/ai/)
以智能洞察与高速响应，赋能自主制造升级了解更多
2/2
# 全面集成的解决方案
我们的 SmartFactory 产品组合提供高度集成的自动化软件解决方案，旨在最大化提升工厂效率，并强化生产运营能力。
我们提供全方位的服务，涵盖生产效率提升、工艺质量改进、制造执行系统 (MES) 系统集成和供应链管理，从企业规划到生产控制的每一个环节。
借助 AI 驱动的自动化和先进排程技术，制造商可以：提升运营绩效、优化生产流程、减少停机时间，并推动持续改进。我们的整体解决方案能够实现对运营的无缝监控与管控。
携手我们的专业自动化团队，释放您工厂的全部潜能，在快速变化的制造业环境中实现卓越运营与可持续增长。
[ 查看解决方案 ](/zh-hans/semiconductor/)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/06/applied-smartfactory-integrated-solutions-2.jpg)
[ View minds.ai ](https://minds.ai/)
Announcement
### Applied Materials
Acquires minds.ai
minds.ai specializes in reinforcement learning and deep learning AI for semiconductor manufacturing and is now part of the **Applied SmartFactory®** portfolio.
COMPETITIVE ADVANTAGE
SmartFactory customers gain advanced AI built for semiconductor fabs — optimizing yield, accelerating decisions, and advancing toward autonomous factory operations.
## SmartFactory 博客
了解自动化专家如何运用 SmartFactory 自主解决方案推动制造业转型升级。
##### [半导体行业博客](/zh-hans/semiconductor-blog/)
## SmartFactory 活动
与我们的自动化专家互动，加速获取智能制造优势。
##### [半导体行业活动](/zh-hans/semiconductor-events/)
## 可量化的效益提升
部署自动化解决方案，助力您的团队更快完成常规任务，提前预测并规避问题，高效实施解决方案，减少浪费。您将获得可量化的改进，包括但不限于：
### 缩短生产周期
### 提高良率
### 提升产能
### 降低设备停机率
### 减少风险
### 加快产品上市速度
### 减少缺陷率
### 优化生产排程
## 自动化行业领导者
我们的全球专家团队是制造业自动化领域的领军者，持续推动行业创新。他们凭借深厚的专业知识，为您量身打造可扩展的解决方案，帮助您根据自身需求和时间表逐步提升工厂自动化水平。
无论您是刚刚踏上自动化之旅，还是已准备好迈向“无人工厂”，我们的专家都能为您提供清晰的实施路线图，助您达成目标。
[ 联系我们，优化您的核心 KPI ](/zh-hans/connect/)
## 行业专家洞察
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)### Quality Quest: Insights from the Fab
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)### Performance Pioneers: Factory Innovations
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)### Smart Manufacturing: The Evolutionary Edge
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)### SPC Strategies: Realizing Excellence
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)### MES Integration: Uniquely SmartFactory
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)### Human-Centric Solutions: SmartFactory’s Approach
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)### Innovation Integration: Seizing New Opportunities
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)### Efficiency Unleashed: Optimizing the Fab
---
### [Let's Connect](https://appliedsmartfactory.com/connect/)
**Published:** June 27, 2021
**Author:** Applied Smartfactory
**Content:**
# Let's work together to make a positive impact on a global scale.
### Ready to connect with us?
Please fill out the form and we’ll get back to you shortly. All fields are mandatory.
# Let’s Connect
Connect with our SmartFactory team to explore how integrated automation can support your manufacturing goals.
#### Why Reach Out?
Whether you’re modernizing manufacturing operations, evaluating SmartFactory solutions, or have a specific question, our team is here to help.
First Name: \*
Last Name: \*
Company Name: \*
Business Email: \*
Country/Region: \*
Please select countryAfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
No. of Employees: \*
Please select1-2021-200201-10,00010,000+
Let us know how we can assist: \*
Tell us a bit about your role, goals, or questions so we can route your request appropriately.
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Thank you for contacting us; we will get back to you shortly. In the meantime, please visit our LinkedIn page dedicated to [semiconductor](https://www.linkedin.com/showcase/applied-smartfactory/) industry for the latest updates.
Δ
**Your message will be reviewed by the SmartFactory team and routed to the appropriate specialists. You’ll hear back as soon as possible.**
SmartFactory supports manufacturers seeking to improve efficiency, quality, and performance across modern factory operations. Our integrated automation software helps manufacturing teams optimize production, reduce risk, and drive continuous improvement.
---
### [Process Quality Solutions](https://appliedsmartfactory.com/process-quality-solutions/)
**Published:** September 8, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory Process Quality Solutions
Implement a zero-defect strategy to ensure superior process quality and consistency.
[](/semiconductor/process-quality-solutions/run-to-run-control/)### Run-to-Run Control
Improves yield by optimizing equipment and process performance
[](/semiconductor/process-quality-solutions/spc/)### SPC®
Combines the power of data transformation with analytics to deliver intelligent detection
[](/semiconductor/process-quality-solutions/fault-detection/)### Fault Detection
Minimizes yield loss and reduces unscheduled equipment downtime
[](/semiconductor/process-quality-solutions/recipe-management/)### Recipe Management System
Provides manufacturing consistency through automated recipe management
[](/semiconductor/process-quality-solutions/equipment-automation)### Equipment Automation
Increases productivity and reduces human error. Enables automation possibilities beyond manual basics
# Process quality for improved yield and reduced variability across the fab
### Engineering consistent yield and process control across semiconductor manufacturing
[](/semiconductor/process-quality-solutions/run-to-run-control/)#### Run-to-Run Control
Improves yield by optimizing equipment and process performance.
[](/semiconductor/process-quality-solutions/spc/)#### SPC
Combines the power of data transformation with analytics to deliver intelligent detection.
[](/semiconductor/process-quality-solutions/fault-detection/)#### Fault Detection
Minimizes yield loss and reduces unscheduled equipment downtime.
[](/semiconductor/process-quality-solutions/recipe-management/)#### Recipe Management System
Provides manufacturing consistency through automated recipe management.
[](/semiconductor/process-quality-solutions/equipment-automation/)#### Equipment Automation
Increases productivity and reduces human error. Enables automation possibilities beyond manual basics.
[](/semiconductor/process-quality-solutions/asset-trace/)#### Asset Trace
Improves asset utilization with asset trace throughout entire life cycle.
[](/semiconductor/process-quality-solutions/maintenance-management/)#### Maintenance Management
Improves power of equipment maintenance – scheduled and unscheduled activities.
[](https://appliedsmartfactory.com/process-quality-solutions/defect-classification/)#### Defect Classification
Improves classification accuracy, reduces cycle time, and enables consistent, scalable defect decisions.
[](https://appliedsmartfactory.com/process-quality-solutions/defect-source/)#### Defect Source
Accelerates root cause analysis by automatically identifying defect source layers and reducing manual troubleshooting effort for out-of-control events.
[](https://appliedsmartfactory.com/process-quality-solutions/knowledge-advisor/)#### Knowledge Advisor
Transforms how engineers investigate and resolve process issues by unifying factory data with AI-driven, reusable knowledge—enabling faster, more consistent decisions at scale.
[](https://appliedsmartfactory.com/process-quality-solutions/advanced-recipe-tuning/)#### Advanced Recipe Tuning
Enhances existing R2R control systems with AI-driven recipe tuning, improving process capability and yield for high-mix, low-volume manufacturing without disrupting current infrastructure.
[](https://appliedsmartfactory.com/process-quality-solutions/predictive-metrology/)#### Predictive Metrology
Predicts metrology values in real time using machine learning, reducing dependence on physical measurements and enabling earlier detection of process drift.
---
### [SmartFactory Predictive Metrology](https://appliedsmartfactory.com/process-quality-solutions/predictive-metrology/)
**Published:** July 20, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory AI™ Predictive Metrology
# Predict metrology
values in real time
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How do you increase metrology coverage and reduce cycle time without adding more physical measurements?
SmartFactory AI Predictive Metrology uses machine learning to predict metrology values in real time, helping manufacturers reduce dependence on physical measurements, improve sampling strategies, and detect process drift earlier. With confidence-scored predictions, automated model management, continuous retraining, and native quality system connectivity, teams can make faster, more reliable process control decisions.
## Why choose SmartFactory AI Predictive Metrology?
SmartFactory AI Predictive Metrology helps teams deploy faster, consolidate fragmented point solutions, and fine-tune measurement specifications with confidence.
### Deployment in just 5 months
### 1 unified platform, not fragmented solutions
#### Optimized UVA specifications
## What can you gain from our approach?
## Reduced cycle time
- Predict metrology results in real time instead of waiting for physical measurements
- Optimize sampling strategies to reduce metrology bottlenecks
- Accelerate decision-making across the production flow
## Improved yield and process control
- Detect process drift earlier before it impacts production
- Increase metrology coverage without adding measurement capacity
- Support tighter process control with confidence-scored predictions
## Simplify AI model management
- Automatically identify key features to accelerate model creation
- Continuously monitor data quality and model performance
- Auto-retrain models when drift or performance changes are detected
---
### [SPC](https://appliedsmartfactory.com/process-quality-solutions/spc/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory SPC
# 修复难以检测的过程变化
[ 阅读【质量博客】 ](/zh-hans/semiconductor-blog-category/quality-zh-hans/)
## 您是如何处理工厂的过程变化问题?
SmartFactory SPC 是一个先级过程控制（APC）引擎，通过运行统计数据来确定过程是否在规格范围内，以提高产品良率。 SPC 是在一个与其他过程控制元素共同的平台上设计的，是一个相互依赖的、智能的平台，可以解决集成数据和上下文的挑战，以更好地控制晶圆厂的过程质量。
## 为何选择 SmartFactory SPC？
### 通过 Cpk 提升与变异管控，每年降本超 65 万美元
### 信号检测率提升 5%，废品率降低 5%
### 自动化降低间接运营成本
## 采用我们的解决方案能为您带来什么？
## 数据集成
- 追溯统计分析和违规数据到工艺设备的原始数据
- 启用高级分析和自定义规则
- 提供人工智能（AI）/机器学习（ML）功能和Python模块支持
- 为快速分析和简单管理SPC图表提供单一UI
## 集成式的平台
- 提供通用平台，Run-to-Run系统、SPC系统、Recipe Management系统与FDC系统进行了无缝的整合，促进信息共享
- 使数据操作更容易
- 更少的配置依赖，提供更快的ROI
## 降低成本
- 提供对统计失败的根本原因分析的更快访问
- 消除设备连接和系统集成问题，降低整体拥有成本（CoO）
## Our Insights
[ View All ](https://appliedsmartfactory.com/blog/)
---
### [工艺质量解决方案](https://appliedsmartfactory.com/process-quality-solutions/)
**Published:** October 12, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory 工艺质量解决方案
实施零缺陷战略，确保卓越的工艺质量和一致性。
[](/zh-hans/semiconductor/process-quality-solutions/run-to-run-control/)### Run-to-Run Control
通过提升设备以及工艺的性能改善良率
[](/zh-hans/semiconductor/process-quality-solutions/spc/)### SPC™
结合数据信息的提取与分析，提供智能决策
[](/zh-hans/semiconductor/process-quality-solutions/fault-detection/)### Fault Detection
最大限度降低良率损失，减少计划外设备停机
[](/zh-hans/semiconductor/process-quality-solutions/recipe-management/)### Recipe Management System
通过自动化配方管理保持一致性
[](/zh-hans/semiconductor/process-quality-solutions/equipment-automation)### Equipment Automation
提高生产效率，减少人为错误，实现超越手动基础的全自动化可能性
[](/zh-hans/process-quality-solutions/asset-trace/)### SmartFactory Asset Trace
通过整个生命周期的资产追踪提高资产利用率
[](/zh-hans/process-quality-solutions/maintenance-management/)### Maintenance Management
提高设备维护能力——应对计划内和计划外事件
# 工艺质量解决方案：提升良率并降低整个晶圆厂的工艺波动
### 在半导体制造中实现一致的良率与工艺控制
[](/zh-hans/semiconductor/process-quality-solutions/run-to-run-control/)#### Run-to-Run Control
通过提升设备以及工艺的性能改善良率
[](/zh-hans/semiconductor/process-quality-solutions/spc/)#### SPC
结合数据信息的提取与分析，提供智能决策
[](/zh-hans/semiconductor/process-quality-solutions/fault-detection/)#### Fault Detection
最大限度降低良率损失，减少计划外设备停机
[](/zh-hans/semiconductor/process-quality-solutions/recipe-management/)#### Recipe Management System
通过自动化配方管理保持一致性
[](/zh-hans/semiconductor/process-quality-solutions/equipment-automation/)#### Equipment Automation
提高生产效率，减少人为错误，实现超越手动基础的全自动化可能性
[](/zh-hans/semiconductor/process-quality-solutions/asset-trace/)#### Asset Trace
通过整个生命周期的资产追踪提高资产利用率
[](/zh-hans/semiconductor/process-quality-solutions/maintenance-management/)#### Maintenance Management
提高设备维护能力——应对计划内和计划外事件
---
### [Process Quality Solutions](https://appliedsmartfactory.com/process-quality-solutions/)
**Published:** September 8, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactoryプロセス品質ソリューション
プロセスシステムの統合より、
優れたプロセス品質と
一貫性を確保
[](/ja/semiconductor/process-quality-solutions/run-to-run-control/)### Run-to-Run Control
装置とプロセスのパフォーマンスを最適化すること
で、歩留まりを向上
[](/ja/semiconductor/process-quality-solutions/spc/)### SPC®
データ組み合わせ仕組みでよる効率的に
分析施行して監視自動化機能を提供
[](/ja/semiconductor/process-quality-solutions/fault-detection/)### Fault Detection
歩留まり損失を最小限に抑え、予定外の装置ダウンタイムを減少
[](/ja/semiconductor/process-quality-solutions/recipe-management/)### Recipe Management System
レシピ管理システムを通じて製品処理製造の
品質一貫性を確保
[](/ja/process-quality-solutions/asset-trace/)### SmartFactory Asset Trace
生産設備や治具工具のライフサイクル全体を通じてトレースし、活用率を向上
[](/ja/semiconductor/process-quality-solutions/equipment-automation/)### Equipment Automation
生産性を向上させ、人為的なエラーを減少させ、
業界スタンダードの自動処理仕組みを実現
[](/ja/process-quality-solutions/maintenance-management/)### Maintenance Management
計画保全・計画外保全の両面で、装置
メンテナンスの効果を最大化
# 工場全体での歩留まり向上とばらつき低減を実現するプロセス品質ソリューション
### 半導体製造全体にわたって、一貫した歩留まりとプロセス制御を実現
[](/ja/semiconductor/process-quality-solutions/run-to-run-control/)#### Run-to-Run Control
装置とプロセスのパフォーマンスを最適化することで、歩留まりを向上
[](/ja/semiconductor/process-quality-solutions/spc/)#### SPC
データ組み合わせ仕組みでよる効率的に
分析施行して監視自動化機能を提供
[](/ja/semiconductor/process-quality-solutions/fault-detection/)#### Fault Detection
歩留まり損失を最小限に抑え、予定外の装置ダウンタイムを減少
[](/ja/semiconductor/process-quality-solutions/recipe-management/)#### Recipe Management System
レシピ管理システムを通じて製品処理製造の品質一貫性を確保
[](/ja/semiconductor/process-quality-solutions/equipment-automation/)#### Equipment Automation
生産性を向上させ、人為的なエラーを減少させ、業界スタンダードの自動処理仕組みを実現
[](/ja/semiconductor/process-quality-solutions/asset-trace/)#### Asset Trace
生産設備や治具工具のライフサイクル全体を通じてトレースし、活用率を向上
[](/ja/semiconductor/process-quality-solutions/maintenance-management/)#### Maintenance Management
計画保全・計画外保全の両面で、装置
メンテナンスの効果を最大化
[](https://appliedsmartfactory.com/process-quality-solutions/defect-classification/)#### Defect Classification
分類精度を向上させ、サイクルタイムを短縮し、一貫性のあるスケーラブルな欠陥判定を実現します。
[](https://appliedsmartfactory.com/process-quality-solutions/defect-source/)#### Defect Source
Out-of-Control(OOC)イベントにおける欠陥発生レイヤーを自動特定し、手作業によるトラブルシューティング負荷を低減することで、根本原因分析を加速します。
[](https://appliedsmartfactory.com/process-quality-solutions/knowledge-advisor/)#### Knowledge Advisor
AIと工場データを統合し、エンジニアの問題解析・解決を革新。再利用可能なナレッジを活用することで、大規模な製造現場でもより迅速かつ一貫性のある意思決定を実現します。
---
### [SPC](https://appliedsmartfactory.com/process-quality-solutions/spc/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory SPC
# 検出が困難なプロセス変動を 解決
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## 製造現場でのプロセス変動をどのように管理していますか？
SmartFactory SPCは、プロセスが仕様内にあるかどうかを統計的に判断し、製品の歩留まりを向上させる高度なプロセス制御（APC）エンジンです。他のプロセス制御要素と共通のプラットフォーム上に設計されており、データとコンテキストの統合という課題を解決し、ファブにおけるプロセス品質の制御を強化するインテリジェンス対応の相互依存型プラットフォームです。
## SmartFactory SPCを選ぶ理由
### Cpkと変動の改善で、年間65万ドル超のコスト削減が可能
### 信号検出とスクラップの改善率5%
### 自動化による間接コストの削減
## 私たちの取り組みから得られる効果
### データの完全性
- 統計解析結果や違反データを、プロセス装置の
生データまでトレース可能
- 高度な分析やカスタムルールの適用が可能
- Pythonブロック対応により、AI/ML機能を活用
- 単一のUIでSPCチャートの迅速な分析と簡易な管理を実現
### 統合プラットフォーム
- Run-to-Run、FDC、レシピ管理との統合が可能な共通プラットフォームを提供
- 複雑なデータ処理を簡素化
- 構成依存性が少なく、迅速なROIを実現
### コストの削減
- 統計的異常の根本原因分析に対して効率的に、すぐ 見つかる
- 装置のデータ活用とシステムとの連携で課題を解消し、総所有コスト（CoO）を削減
---
### [Production Control](https://appliedsmartfactory.com/supply-chain-solutions/production-control/)
**Published:** October 5, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Production Control
# Make better decisions by simulating operations
[ Read Semi Blog ](/semiconductor-blog/)
## How do you analyze, predict, and optimize operations in your fab?
SmartFactory Production Control is a capacity planning system for simulating manufacturing and planning operations. By replicating production dispatching in a simulation environment, the system identifies opportunities for improving WIP throughput and capacity utilization—all without disrupting factory operations.
## Why choose SmartFactory Production Control?
### 5–10% reduction in cycle time
### 5–10% throughput improvement
### 90–95% WIP prediction accuracy
## What can you gain from our approach?
## Simulation expertise
- Built on industry standards for modeling complex semi operations worldwide — RTD,
Activity Manager®, APF Fusion®, and AutoSched platforms
- Provides largest installed base in semi manufacturing
## Fast execution
- Offers object-oriented, data-driven modeling, providing the fastest execution of any commercially available products
- Offers the only advanced processing package that integrates with AutoMod® for better model accuracy
## Greater flexibility & detail
- Provides the most flexibility and detail in fab-level modeling
- Includes standard features and dispatching rules for quick model development
- Supports web-based interface for managing and analyzing simulation results
---
### [Production Control](https://appliedsmartfactory.com/supply-chain-solutions/production-control/)
**Published:** October 5, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Production Control
# Make better decisions by simulating operations
[ Read Semi Blog ](/semiconductor-blog/)
## How do you analyze, predict, and optimize operations in your fab?
SmartFactory Production Control is a capacity planning system for simulating manufacturing and planning operations. By replicating production dispatching in a simulation environment, the system identifies opportunities for improving WIP throughput and capacity utilization—all without disrupting factory operations.
## Why choose SmartFactory Production Control?
### 5–10% reduction in cycle time
### 5–10% throughput improvement
### 90–95% WIP prediction accuracy
## What can you gain from our approach?
## Simulation expertise
- Built on industry standards for modeling complex semi operations worldwide — RTD,
Activity Manager®, APF Fusion®, and AutoSched platforms
- Provides largest installed base in semi manufacturing
## Fast execution
- Offers object-oriented, data-driven modeling, providing the fastest execution of any commercially available products
- Offers the only advanced processing package that integrates with AutoMod® for better model accuracy
## Greater flexibility & detail
- Provides the most flexibility and detail in fab-level modeling
- Includes standard features and dispatching rules for quick model development
- Supports web-based interface for managing and analyzing simulation results
---
### [Productivity Solutions](https://appliedsmartfactory.com/productivity-solutions/)
**Published:** September 13, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory Productivity Solutions
Maximize output and enhance efficiency to achieve more with fewer resources.
[](/semiconductor/productivity-solutions/real-time-scheduling-reporting/)### Real Time Scheduling & Reporting
Reduces variability with advanced rule-based, real-time strategies
[](/semiconductor/productivity-solutions/fullauto/)### FullAuto
Eliminates white space with real-time, event-based workflows
[](/semiconductor/productivity-solutions/advanced-scheduling/)### Advanced Scheduling
Boosts productivity of key bottleneck areas with predictive scheduling
[](/semiconductor/productivity-solutions/production-control/)### Production Control
Improves WIP throughput and capacity utilization without disrupting manufacturing operations
[](/semiconductor/productivity-solutions/rtd/)### RTD
Identifies and implements process improvements without complex programming
[](/semiconductor/productivity-solutions/activity-manager/)### Activity Manager
Maximizes utilization and increases productivity with fully integrated automation workflow framework
[](/semiconductor/productivity-solutions/fusion/)### Fusion
Enhances accuracy of simulation models and quantifies impact of rule changes prior to implementation in production
[](/semiconductor/productivity-solutions/simulation-autosched/)### Simulation AutoSched
Enables better decision making and quick analysis
# Productivity for higher factory throughput and utilization
### Driving efficient, high-throughput factory operations across manufacturing
[](/semiconductor/productivity-solutions/real-time-scheduling-reporting/)#### Real Time Scheduling & Reporting
Reduces variability with advanced rule-based, real-time strategies.
[](/semiconductor/productivity-solutions/fullauto/)#### FullAuto
Eliminates white space with real-time, event-based workflows.
[](/semiconductor/productivity-solutions/advanced-scheduling/)#### Advanced Scheduling
Boosts productivity of key bottleneck areas with predictive scheduling.
[](/semiconductor/productivity-solutions/production-control/)#### Production Control
Improves WIP throughput and capacity utilization without disrupting manufacturing operations.
[](/semiconductor/productivity-solutions/activity-manager/)#### Activity Manager®
Maximizes utilization and increases productivity with fully integrated automation workflow framework.
[](/semiconductor/productivity-solutions/rtd/)#### RTD
Identifies and implements process improvements without complex programming.
[](/semiconductor/productivity-solutions/fusion/)#### Fusion
Enhances accuracy of simulation models and quantifies impact of rule changes prior to implementation in production.
[](/semiconductor/productivity-solutions/simulation-autosched/)#### Simulation AutoSched®
Enables better decision making and quick analysis.
[](/semiconductor/productivity-solutions/material-control/)#### Material Control
Automates WIP movement to increase throughput and decrease equipment idle time.
---
### [Production Control](https://appliedsmartfactory.com/productivity-solutions/production-control/)
**Published:** September 22, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Production Control
# Make better decisions by simulating operations
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## How do you analyze, predict, and optimize operations in your fab?
SmartFactory Production Control is a capacity planning system for simulating manufacturing and planning operations. By replicating production dispatching in a simulation environment, the system identifies opportunities for improving WIP throughput and capacity utilization—all without disrupting factory operations.
## Why choose SmartFactory Production Control?
### 5–10% reduction in cycle time
### 5–10% throughput improvement
### 90–95% WIP prediction accuracy
## What can you gain from our approach?
### Simulation expertise
- Built on industry standards for modeling complex semi operations worldwide — RTD,
Activity Manager®, APF Fusion®, and AutoSched platforms
- Provides largest installed base in semi manufacturing
### Fast execution
- Offers object-oriented, data-driven modeling, providing the fastest execution of any commercially available products
- Offers the only advanced processing package that integrates with AutoMod® for better model accuracy
### Greater flexibility & detail
- Provides the most flexibility and detail in fab-level modeling
- Includes standard features and dispatching rules for quick model development
- Supports web-based interface for managing and analyzing simulation results
---
### [300works Full-Auto](https://appliedsmartfactory.com/manufacturing-execution-solutions/300works-full-auto/)
**Published:** October 4, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES 300works® Full-Auto
# Achieve next generation manufacturing
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## Is your MES a full CIM offering and ready for 300mm?
Not all MES solutions have the depth necessary for full automation. SmartFactory MES 300works Full-Auto is an out-of-box factory automation solution that monitors and streamlines the flow of materials throughout a manufacturing facility. The solution allows manufacturers to focus on full automation in the CIM while accelerating new factory ramps, enabling products to arrive at market on time.
## Why choose SmartFactory MES 300works Full-Auto?
### 90 days to achieve first wafer start without delay
### 50% productivity improvement achieved by reducing equipment wait time
### >70% of new 300mm fabs choose 300works for their MES solution
## What can you gain from our approach?
### Quicker deployment
- Achieve on-time deployment goals and value-add improvements
- Save costs by minimizing time required for all phases of production ramp—first deployment in 90 days and all phases of production ramp in 1 year
- Deploy with pre-built, out-of-box functions
### Better integration
- Easily integrate with SmartFactory CIM applications and other enterprise systems
- Enable real-time, Run-to-Run tuning and fault detection to improve yield using direct link to Applied E3® equipment and process control platform
### Better extensibility
- Handle factory expansion to high volume manufacturing (e.g., 120K WSPM) or to multiple factories and lines
- Customize business operations to meet unique customer needs
- Use built-in business templates to support common manufacturing scenarios
---
### [Scheduling Faqs](https://appliedsmartfactory.com/scheduling-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Scheduling
#### How important is the manufacturing schedule in a semiconductor fab?
A semiconductor factory’s manufacturing schedule is vital; it has a direct impact on critical business objectives such as equipment productivity, product quality, and delivering products to customers on time.
#### How does a manufacturing scheduling system (or factory scheduling solution system), benefit a semiconductor manufacturer?
A manufacturing scheduling system helps semiconductor manufacturers make the best use of their equipment and personnel resources. A quality factory scheduling solution can improve equipment productivity, product quality, and on-time delivery of products.
#### How can manufacturing simulation software be used in semiconductor manufacturing?
Manufacturing simulation software can predict the impact of a particular change to the manufacturing process, such as scheduling rules, before it is made live in the production environment. This can identify potential problems to address prior to implementation, as well as help manufacturers find the most advantageous solutions.
#### How can SmartFactory Simulation AutoSched® help a fab model decision logic for its equipment?
SmartFactory Simulation AutoSched is a capacity planning system that enables simulation of complex workflows to identify hidden and wasted factory capacity. It allows users to create a virtual model of a fab to analyze, predict, and optimize operations, enabling experiments with scheduling rules, equipment, and operator cycles offline.
#### How does automated manufacturing work in the semiconductor industry?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automated manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
---
### [Scheduling Faqs](https://appliedsmartfactory.com/scheduling-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Scheduling
#### How important is the manufacturing schedule in a semiconductor fab?
A semiconductor factory’s manufacturing schedule is vital; it has a direct impact on critical business objectives such as equipment productivity, product quality, and delivering products to customers on time.
#### How does a manufacturing scheduling system (or factory scheduling solution system), benefit a semiconductor manufacturer?
A manufacturing scheduling system helps semiconductor manufacturers make the best use of their equipment and personnel resources. A quality factory scheduling solution can improve equipment productivity, product quality, and on-time delivery of products.
#### How can manufacturing simulation software be used in semiconductor manufacturing?
Manufacturing simulation software can predict the impact of a particular change to the manufacturing process, such as scheduling rules, before it is made live in the production environment. This can identify potential problems to address prior to implementation, as well as help manufacturers find the most advantageous solutions.
#### How can SmartFactory Simulation AutoSched® help a fab model decision logic for its equipment?
SmartFactory Simulation AutoSched is a capacity planning system that enables simulation of complex workflows to identify hidden and wasted factory capacity. It allows users to create a virtual model of a fab to analyze, predict, and optimize operations, enabling experiments with scheduling rules, equipment, and operator cycles offline.
#### How does automated manufacturing work in the semiconductor industry?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automated manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
---
### [Material Control](https://appliedsmartfactory.com/productivity-solutions/material-control/)
**Published:** October 7, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Material Control
# Expect superior uptime performance
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## What is the cost if your fab goes down for an hour—or even 10 minutes?
Interruptions in a fab caused by Manufacturing Control System (MCS) reliability concerns can cost millions of dollars in lost revenue. Known for its superior uptime, SmartFactory Material Control is a real-time material control system that coordinates the transportation and storage of wafers, reticles, and LCD panels. With over 250 deployments worldwide, Material Control (CLASS MCS 5®) is the market leading MCS solution in both semiconductor and display manufacturing, offering increased automation efficiency and improved inventory control.
## Why choose SmartFactory Material Control?
### Proven 99.99% production uptime
### AMHS and MES vendor independent
### Lower internal cost of ownership
## What can you gain from our approach?
### Tight integration
- Integrate with any AMHS solution or multiple AMHS providers without interruption
- Use external interfaces to communicate with standard and customer MES solutions on various platforms
- Extend the system’s rich feature set with your own factory customizations using the MCS Development Kit
### High availability
- Ensure that critical components are always operational through accelerated failover functionality
- Add or configure AMHS equipment without software changes or downtime
- Independently install, update, and remove components while the system is running
### Better productivity
- Ensure the best path is selected for a lot to reach its destination with advanced scheduling algorithms
- Reduce AMHS device transport times and overall AMHS footprint in the fab
- Quickly get to the root cause of delivery issues with a rich database of integrated logs
---
### [Semiconductor](https://appliedsmartfactory.com/semiconductor/)
**Published:** June 27, 2021
**Author:** Applied Smartfactory
**Content:**
# Improve Performance with SmartFactory Solutions for Semiconductor Manufacturing
Scroll to learn more about our capabilities, including MES, Process Quality, Productivity, and Supply Chain.
## SmartFactory MES Solutions
Streamline manufacturing execution by integrating and optimizing operations for better control and efficiency.
[](/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
Reduces production noise and boosts operation efficiency
[](/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
Improves asset utilization with asset trace throughout entire life cycle
[](/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works® Full-Auto
Improves high volume manufacturing by automating flow of materials
[](/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
Augments the FACTORYworks platform with additional out-of-box functionality to support semiconductor assembly and adjacent industries
[](/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
Accelerates high volume manufacturing improvements with special feature extensions
[](/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
Automates WIP movement to increase throughput and decrease equipment idle time
[](/semiconductor/manufacturing-execution-solutions/promis)### MES PROMIS®
Boosts efficiency with fab operation modeling capabilities
[](/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
Implements your proprietary business rules without programming
[](/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
Improves power of equipment maintenance – scheduled and unscheduled activities
[](/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
Detects and predicts system failures
[](/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
Optimizes MES intelligence for semiconductor backend manufacturing
# MES for predictable factory execution—at any scale or complexity
### Consistent factory execution across the entire semiconductor manufacturing lifecycle
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-substrate/)#### Wafer Substrate
Reliable, production‑grade MES for ingot and wafer environments—supporting crystal growth, wafering operations, and upstream production workflows with consistency and control.
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)#### Wafer Fab
Execute advanced wafer manufacturing with consistency and control–supporting complex operations across tools, processes, and production flows.
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)#### Test & Assembly
Maintain consistent execution across variable test and assembly environments–adapting to changing product mixes and volumes without disrupting factory performance.
[](/semiconductor/classic-mes/)#### Classic MES
Run established factory operations on proven MES foundations—supporting critical manufacturing environments with stability and depth at scale.
## SmartFactory Process Quality Solutions
Implement a zero-defect strategy to ensure superior process quality and consistency.
[](/semiconductor/process-quality-solutions/run-to-run-control/)### Run-to-Run Control
Improves yield by optimizing equipment and process performance
[](/semiconductor/process-quality-solutions/spc/)### SPC®
Combines the power of data transformation with analytics to deliver intelligent detection
[](/semiconductor/process-quality-solutions/fault-detection/)### Fault Detection
Minimizes yield loss and reduces unscheduled equipment downtime
[](/semiconductor/process-quality-solutions/recipe-management/)### Recipe Management System
Provides manufacturing consistency through automated recipe management
[](/semiconductor/process-quality-solutions/equipment-automation)### Equipment Automation
Increases productivity and reduces human error. Enables automation possibilities beyond manual basics
# Process quality for improved yield and reduced variability across the fab
### Engineering consistent yield and process control across semiconductor manufacturing
[](/semiconductor/process-quality-solutions/run-to-run-control/)#### Run-to-Run Control
Improves yield by optimizing equipment and process performance.
[](/semiconductor/process-quality-solutions/spc/)#### SPC
Combines the power of data transformation with analytics to deliver intelligent detection.
[](/semiconductor/process-quality-solutions/fault-detection/)#### Fault Detection
Minimizes yield loss and reduces unscheduled equipment downtime.
[](/semiconductor/process-quality-solutions/recipe-management/)#### Recipe Management System
Provides manufacturing consistency through automated recipe management.
[](/semiconductor/process-quality-solutions/equipment-automation/)#### Equipment Automation
Increases productivity and reduces human error. Enables automation possibilities beyond manual basics.
[](/semiconductor/process-quality-solutions/asset-trace/)#### Asset Trace
Improves asset utilization with asset trace throughout entire life cycle.
[](/semiconductor/process-quality-solutions/maintenance-management/)#### Maintenance Management
Improves power of equipment maintenance – scheduled and unscheduled activities.
[](https://appliedsmartfactory.com/process-quality-solutions/defect-classification/)#### Defect Classification
Improves classification accuracy, reduces cycle time, and enables consistent, scalable defect decisions.
[](https://appliedsmartfactory.com/process-quality-solutions/defect-source/)#### Defect Source
Accelerates root cause analysis by automatically identifying defect source layers and reducing manual troubleshooting effort for out-of-control events.
[](https://appliedsmartfactory.com/process-quality-solutions/knowledge-advisor/)#### Knowledge Advisor
Transforms how engineers investigate and resolve process issues by unifying factory data with AI-driven, reusable knowledge—enabling faster, more consistent decisions at scale.
[](https://appliedsmartfactory.com/process-quality-solutions/advanced-recipe-tuning/)#### Advanced Recipe Tuning
Enhances existing R2R control systems with AI-driven recipe tuning, improving process capability and yield for high-mix, low-volume manufacturing without disrupting current infrastructure.
[](https://appliedsmartfactory.com/process-quality-solutions/predictive-metrology/)#### Predictive Metrology
Predicts metrology values in real time using machine learning, reducing dependence on physical measurements and enabling earlier detection of process drift.
## SmartFactory Productivity Solutions
Maximize output and enhance efficiency to achieve more with fewer resources.
[](/semiconductor/productivity-solutions/real-time-scheduling-reporting/)### Real Time Scheduling & Reporting
Reduces variability with advanced rule-based, real-time strategies
[](/semiconductor/productivity-solutions/fullauto/)### FullAuto
Eliminates white space with real-time, event-based workflows
[](/semiconductor/productivity-solutions/advanced-scheduling/)### Advanced Scheduling
Boosts productivity of key bottleneck areas with predictive scheduling
[](/semiconductor/productivity-solutions/production-control/)### Production Control
Improves WIP throughput and capacity utilization without disrupting manufacturing operations
[](/semiconductor/productivity-solutions/rtd/)### RTD
Identifies and implements process improvements without complex programming
[](/semiconductor/productivity-solutions/activity-manager/)### Activity Manager
Maximizes utilization and increases productivity with fully integrated automation workflow framework
[](/semiconductor/productivity-solutions/fusion/)### Fusion
Enhances accuracy of simulation models and quantifies impact of rule changes prior to implementation in production
[](/semiconductor/productivity-solutions/simulation-autosched/)### Simulation AutoSched
Enables better decision making and quick analysis
# Productivity for higher factory throughput and utilization
### Driving efficient, high-throughput factory operations across manufacturing
[](/semiconductor/productivity-solutions/real-time-scheduling-reporting/)#### Real Time Scheduling & Reporting
Reduces variability with advanced rule-based, real-time strategies.
[](/semiconductor/productivity-solutions/fullauto/)#### FullAuto
Eliminates white space with real-time, event-based workflows.
[](/semiconductor/productivity-solutions/advanced-scheduling/)#### Advanced Scheduling
Boosts productivity of key bottleneck areas with predictive scheduling.
[](/semiconductor/productivity-solutions/production-control/)#### Production Control
Improves WIP throughput and capacity utilization without disrupting manufacturing operations.
[](/semiconductor/productivity-solutions/activity-manager/)#### Activity Manager®
Maximizes utilization and increases productivity with fully integrated automation workflow framework.
[](/semiconductor/productivity-solutions/rtd/)#### RTD
Identifies and implements process improvements without complex programming.
[](/semiconductor/productivity-solutions/fusion/)#### Fusion
Enhances accuracy of simulation models and quantifies impact of rule changes prior to implementation in production.
[](/semiconductor/productivity-solutions/simulation-autosched/)#### Simulation AutoSched®
Enables better decision making and quick analysis.
[](/semiconductor/productivity-solutions/material-control/)#### Material Control
Automates WIP movement to increase throughput and decrease equipment idle time.
## SmartFactory Supply Chain Solutions
Enhance supply chain management to improve planning, execution, and overall performance.
[](/semiconductor/supply-chain-solutions/enterprise-planning/)### Enterprise Planning
Increases capacity planning accuracy and responds faster to customer forecast changes
[](/semiconductor/productivity-solutions/production-control/)### Production Control
Runs high-speed what-if scenarios to improve WIP throughput and capacity utilization—without disrupting manufacturing operations
[](/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/)### Simulation AutoMod
Continuously improves productivity throughout the life of the facility with Powerful 3-D simulation modeling
# Improving planning and production control performance across manufacturing
### Plan, control, and simulate the impact of supply chain decisions across factories
[](/semiconductor/supply-chain-solutions/enterprise-planning/)#### Enterprise Planning
Increases capacity planning accuracy and responds faster to customer forecast changes.
[](/semiconductor/supply-chain-solutions/production-control/)#### Production Control
Runs high-speed what-if scenarios to improve WIP throughput and capacity utilization—without disrupting manufacturing operations.
[](/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/)#### Simulation AutoMod
Continuously improves productivity throughout the life of the facility with powerful 3-D simulation modeling.
## SmartFactory Blogs
Learn how automation experts are transforming manufacturing with SmartFactory autonomous solutions.
##### [Semi blog](/semiconductor-blog/) | [Battery blog](/battery-blog/)
## SmartFactory Events
Engage with our automation experts to fast-track advantages of smart manufacturing.
##### [Semi events](/semiconductor-events/) | [Battery events](/battery-events/)
[](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)#### Wafer Substrate
Reliable, production‑grade MES for ingot and wafer environments—supporting crystal growth, wafering operations, and upstream production workflows with consistency and control.
[](/semiconductor/manufacturing-execution-solutions/300works-full-auto/)#### Wafer Fab
Execute advanced wafer manufacturing with consistency and control–supporting complex operations across tools, processes, and production flows.
[](/semiconductor/manufacturing-execution-solutions/mesforatp/)#### Test & Assembly
Maintain consistent execution across variable test and assembly environments–adapting to changing product mixes and volumes without disrupting factory performance.
[](/semiconductor/classic-mes/)#### Classic MES
Run established factory operations on proven MES foundations—supporting critical manufacturing environments with stability and depth at scale.
---
### [SPC](https://appliedsmartfactory.com/process-quality-solutions/spc/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory SPC
# Fix hard-to-detect process variations
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How do you manage process variation issues in your facility?
SmartFactory SPC is an advanced process control (APC) engine that runs statistics to determine if processes are within spec to improve product yield. Designed on a common platform with other process control elements, SPC is an interdependent, intelligence-capable platform that solves the challenge of integrating data and context to better control process quality in fabs.
## Why choose SmartFactory SPC?
### $650K+ cost savings per year from improving Cpk and variability
### 5% improvements in signal detection and scrap
### Overhead cost savings due to automation
## What can you gain from our approach?
### Data integrity
- Traces statistical analysis and violation data back to the process equipment raw data
- Enables advanced analytics and custom rules
- Offers AI/ML capabilities with Python block support
- Provides single UI for rapid analysis and simple administration of SPC charts
### Integrated platform
- Offers common platform with integration to Run to Run, FDC, and Recipe Management to promote information sharing
- Makes data manipulation easier
- Requires fewer configuration dependencies, providing faster ROI
### Reduced costs
- Provides faster access to root cause analysis of statistical failures
- Eliminates issues with tool connectivity and system integration, lowering overall cost of ownership (CoO)
---
### [Quality Faqs](https://appliedsmartfactory.com/quality-faqs/)
**Published:** April 9, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Quality
#### What is manufacturing recipe management software?
A recipe in manufacturing refers to the set of instructions for how a particular piece of equipment is going to process material. Recipe management software helps manage the potentially thousands of recipes in any given semiconductor factory.
#### What are the benefits of a recipe management system for a semiconductor factory?
Recipe management systems can reduce errors, improve efficiency, increase wafer output and provide traceability. They do so by storing the recipes in a secure, central repository and providing a means to review recipe differences, duplicates, and consolidations. It also generates the data needed for certification and audit readiness.
#### What are key features to look for in a manufacturing recipe management software solution?
Managing thousands of recipes is a fundamental requirement of recipe management. Today’s recipe management systems must accommodate individual user organization preferences and provide flexible configuration options. They also should maintain recipes in a secure repository with redundancy and version control, reduce misprocessing by controlling equipment constants and recipe parameter values, and validate runtime recipes against recipe specifications to minimize rework and scrap.
#### How does statistical process control (SPC) software improve quality in manufacturing?
Statistical process control (SPC) tools can help manufacturers move from a detection-based quality control method to a prevention-based one. They can minimize problems with process or quality by identifying them early, recommending actions to prevent or correct issues and providing information necessary to develop process improvement strategies.
#### How does SmartFactory SPC work?
[SmartFactory SPC](/semiconductor/process-quality-solutions/spc/) processes parameters in real-time and analyzes production data to identify process nonconformities. It does so by validating whether specifications are within limits, identifying suspect processing trends, and warning the staff when a process nonconformity is identified. Additionally, SmartFactory SPC helps foster a culture of continuous improvement by providing vital feedback about production processes to the manufacturing staff in real-time.
---
### [Quality Faqs](https://appliedsmartfactory.com/quality-faqs/)
**Published:** April 9, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Quality
#### What is manufacturing recipe management software?
A recipe in manufacturing refers to the set of instructions for how a particular piece of equipment is going to process material. Recipe management software helps manage the potentially thousands of recipes in any given semiconductor factory.
#### What are the benefits of a recipe management system for a semiconductor factory?
Recipe management systems can reduce errors, improve efficiency, increase wafer output and provide traceability. They do so by storing the recipes in a secure, central repository and providing a means to review recipe differences, duplicates, and consolidations. It also generates the data needed for certification and audit readiness.
#### What are key features to look for in a manufacturing recipe management software solution?
Managing thousands of recipes is a fundamental requirement of recipe management. Today’s recipe management systems must accommodate individual user organization preferences and provide flexible configuration options. They also should maintain recipes in a secure repository with redundancy and version control, reduce misprocessing by controlling equipment constants and recipe parameter values, and validate runtime recipes against recipe specifications to minimize rework and scrap.
#### How does statistical process control (SPC) software improve quality in manufacturing?
Statistical process control (SPC) tools can help manufacturers move from a detection-based quality control method to a prevention-based one. They can minimize problems with process or quality by identifying them early, recommending actions to prevent or correct issues and providing information necessary to develop process improvement strategies.
#### How does SmartFactory SPC work?
[SmartFactory SPC](/semiconductor/process-quality-solutions/spc/) processes parameters in real-time and analyzes production data to identify process nonconformities. It does so by validating whether specifications are within limits, identifying suspect processing trends, and warning the staff when a process nonconformity is identified. Additionally, SmartFactory SPC helps foster a culture of continuous improvement by providing vital feedback about production processes to the manufacturing staff in real-time.
---
### [Quality Faqs](https://appliedsmartfactory.com/quality-faqs/)
**Published:** April 9, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Quality
#### What is manufacturing recipe management software?
A recipe in manufacturing refers to the set of instructions for how a particular piece of equipment is going to process material. Recipe management software helps manage the potentially thousands of recipes in any given semiconductor factory.
#### What are the benefits of a recipe management system for a semiconductor factory?
Recipe management systems can reduce errors, improve efficiency, increase wafer output and provide traceability. They do so by storing the recipes in a secure, central repository and providing a means to review recipe differences, duplicates, and consolidations. It also generates the data needed for certification and audit readiness.
#### What are key features to look for in a manufacturing recipe management software solution?
Managing thousands of recipes is a fundamental requirement of recipe management. Today’s recipe management systems must accommodate individual user organization preferences and provide flexible configuration options. They also should maintain recipes in a secure repository with redundancy and version control, reduce misprocessing by controlling equipment constants and recipe parameter values, and validate runtime recipes against recipe specifications to minimize rework and scrap.
#### How does statistical process control (SPC) software improve quality in manufacturing?
Statistical process control (SPC) tools can help manufacturers move from a detection-based quality control method to a prevention-based one. They can minimize problems with process or quality by identifying them early, recommending actions to prevent or correct issues and providing information necessary to develop process improvement strategies.
#### How does SmartFactory SPC work?
[SmartFactory SPC](/semiconductor/process-quality-solutions/spc/) processes parameters in real-time and analyzes production data to identify process nonconformities. It does so by validating whether specifications are within limits, identifying suspect processing trends, and warning the staff when a process nonconformity is identified. Additionally, SmartFactory SPC helps foster a culture of continuous improvement by providing vital feedback about production processes to the manufacturing staff in real-time.
---
### [Blog](https://appliedsmartfactory.com/blog/)
**Published:** October 18, 2021
**Author:** Applied Smartfactory
**Content:**
# SmartFactory Blog
Explore insights across semiconductor and battery manufacturing, including AI/ML, MES, quality, productivity, planning, scheduling, use cases, smart manufacturing, and battery. Find practical strategies to improve yield, reduce variability, and optimize factory performance through real-world use cases and Applied SmartFactory solutions.
## AI/ML
[ FAQs ](/ai-ml-faqs/)
[ View all ](/semiconductor-blog-category/ai-ml/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/retrieval-augmented-generation-in-semiconductor-manufacturing/)
### [Retrieval-Augmented Generation in semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/retrieval-augmented-generation-in-semiconductor-manufacturing/)
Understanding the importance and evolution of RAG
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/integrating-generative-ai-into-industrial-engineering-workflow/)
### [Integrating Generative AI into the industrial engineering workflow](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/integrating-generative-ai-into-industrial-engineering-workflow/)
The potential to turn complexity into clarity could be a game changer for industrial engineers tasked with managing complex data.
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
### [The potential to transform reporting with FactoryView and AI (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
Improve user experience and factory outcomes with AI
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
### [The potential to transform reporting with FactoryView and AI (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
Transform factory operations with an advanced decision support system
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-1/)
### [The integration of AI and cloud technologies (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-1/)
As AI deployment grows, cloud could pave the way forward
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-2/)
### [The integration of AI and cloud technologies (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-2/)
Deciding when and how to move AI to the cloud based on scalability and flexibility
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-transforming-manufacturing-kpis/)
### [AI integration is transforming manufacturing KPIs](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-transforming-manufacturing-kpis/)
Semi manufacturers are accelerating factory performance and uncovering new business opportunities
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/semiconductor-business-enhancement-with-ai/)
### [Enhance semiconductor business operations with AI-powered solutions](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/semiconductor-business-enhancement-with-ai/)
Benefits to quality and productivity help manufacturers stay ahead of demand
[  ](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/model-management-for-deploying-ai/)
### [The significance of data and model management for deploying AI](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/model-management-for-deploying-ai/)
Orchestrating scalable AI solutions
## MES
[ MES videos ](/semiconductor-mes-video-channel/)
[ FAQs ](/mes-faqs)
[ View all ](/semiconductor-blog-category/manufacturing-execution/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/how-advanced-packaging-mes-helps-atp-facilities-recover-capacity/)
### [How Advanced Packaging MES helps ATP facilities recover capacity](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/how-advanced-packaging-mes-helps-atp-facilities-recover-capacity/)
Legacy back-end MES systems are no longer enough
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/from-data-to-decisions-ai-enabled-digital-twins-transform-semiconductor-manufacturing/)
### [From data to decisions](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/from-data-to-decisions-ai-enabled-digital-twins-transform-semiconductor-manufacturing/)
How AI-enabled digital twins are transforming semiconductor manufacturing
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
### [Manufacturing discipline starts at the substrate: Why execution can’t wait for the fab](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
Front-end execution increasingly determines semiconductor outcomes
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
### [Predict, don’t react](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
Why predictive monitoring is essential for maximizing uptime in semiconductor manufacturing
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/spares-kitting-in-semiconductor-manufacturing/)
### [From downtime to uptime: the case for spares kitting in modern semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/spares-kitting-in-semiconductor-manufacturing/)
The right parts, at the right place, at the right spec and in the right time
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-execution-system-past-present-future-in-smart-factories/)
### [MES: Past, Present, Future](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-execution-system-past-present-future-in-smart-factories/)
The evolution of MES from a simple paper replacement to the backbone of the factory, and what’s next
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/how-to-solve-configuration-challenge-in-semiconductor-manufacturing-automation/)
### [From chaos to harmony: Solving the configuration challenge in semi manufacturing automation](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/how-to-solve-configuration-challenge-in-semiconductor-manufacturing-automation/)
Rethinking how configurations are used to improve productivity
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/smarter-alarm-management-and-hidden-cost-of-alarm-fatigue/)
### [Smarter alarm management: The hidden cost of alarm fatigue](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/smarter-alarm-management-and-hidden-cost-of-alarm-fatigue/)
The right alarms at the right time, to the right people
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/round-vs-square-differences-between-wafer-and-reticle-manufacturing/)
### [MES in the mask shop: Round versus square, wafer versus reticle (Part 1 of 4)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/round-vs-square-differences-between-wafer-and-reticle-manufacturing/)
Comparing operational efficiency and product quality across two familiar manufacturing paradigms
## Quality
[ FAQs ](/quality-faqs/)
[ View all ](/semiconductor-blog-category/quality/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/transform-dry-etch-process-control/)
### [How a leading memory manufacturer transformed dry etch process control](https://appliedsmartfactory.com/semiconductor-blog/quality/transform-dry-etch-process-control/)
Reducing false alarms and optimizing UVA specifications through data-driven intelligence
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/end-to-end-quality-intelligence-in-manufacturing/)
### [End-to-End Quality Intelligence in Manufacturing](https://appliedsmartfactory.com/semiconductor-blog/quality/end-to-end-quality-intelligence-in-manufacturing/)
The next frontier is connected, contextualized intelligence from supplier to customer
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/semiconductor-supplier-quality-management-best-practices/)
### [Supplier quality is a key contributor to enhancing Quality by Design practices](https://appliedsmartfactory.com/semiconductor-blog/quality/semiconductor-supplier-quality-management-best-practices/)
Improving quality systems for semiconductor manufacturing
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
### [Synergizing Fault Detection and SPC: smarter manufacturing solution for cost reduction](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
Integrating the functions of Statistical Process Control (SPC) and Fault Detection (FD) helps semiconductor manufacturers achieve higher quality, reliability, and efficiency
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/unifying-process-control/)
### [Benefits of unifying process control in semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/quality/unifying-process-control/)
Achieve better detection, decision making, and costs through unified process control
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/manufacturing-operations/)
### [Enhance manufacturing efficiency with SmartFactory Unified Process Control](https://appliedsmartfactory.com/semiconductor-blog/quality/manufacturing-operations/)
Explore AI-driven process quality improvement with SmartFactory’s UPC solution in this engaging article by Applied SmartFactory.
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/better-profitability-with-spc/)
### [Improve yield for better profitability, less waste with SmartFactory SPC](https://appliedsmartfactory.com/semiconductor-blog/quality/better-profitability-with-spc/)
Automating analytics reduces defects, optimizing continuous improvement
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/moving-toward-zero-defects/)
### [Moving toward zero-defects manufacturing with gusto to make your factories smarter](https://appliedsmartfactory.com/semiconductor-blog/quality/moving-toward-zero-defects/)
This blog series discusses strategies, priorities, and challenges manufacturers face to automate factories of any size to move the needle towards zero defects manufacturing
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/automotive-manufacturing/)
### [Zero-defect strategy: steering the automotive manufacturing electronic revolution](https://appliedsmartfactory.com/semiconductor-blog/quality/automotive-manufacturing/)
Increase yield and reduce costs of non-quality in automotive manufacturing
## Productivity
[ FAQs ](/productivity-faqs/)
[ View all ](/semiconductor-blog-category/productivity/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/removing-barriers-in-semiconductor-industry/)
### [Removing barriers to achieve higher levels of automation in the semiconductor industry](https://appliedsmartfactory.com/semiconductor-blog/productivity/removing-barriers-in-semiconductor-industry/)
Advancements are helping legacy fabs deploy automation solutions
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/advantages-of-reinforcement-learning/)
### [Unveiling the Advantages of Reinforcement Learning](https://appliedsmartfactory.com/semiconductor-blog/productivity/advantages-of-reinforcement-learning/)
Explore how reinforcement learning offers a revolutionary approach to using real world data to solve complex scheduling and dispatching challenges in semiconductor manufacturing.
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/factory-automation/)
### [Establishing a blueprint to optimize productivity with advanced factory automation](https://appliedsmartfactory.com/semiconductor-blog/productivity/factory-automation/)
Envisioning where you are and how to get there to ease deployment, ensuring smart manufacturing.
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/private-cloud/)
### [SmartFactory Private Cloud – Part 1: Roadmap to Deployment](https://appliedsmartfactory.com/semiconductor-blog/productivity/private-cloud/)
Framework makes it easier to plan and implement APF solutions in the cloud
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimization-of-dispatch-rule-parameters/)
### [Evolutionary optimization of dispatch rule parameters](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimization-of-dispatch-rule-parameters/)
Dynamically optimize a dispatch rule’s parameters for better lot scheduling.
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
### [Common Data Model enables RAPID deployment for productivity solutions – Challenges (Part 1/3)](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
Data challenges for rapid deployment of factory productivity and supply chain solutions
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
### [Common Data Model enables RAPID deployment for productivity solutions – Solutions (Part 2/3)](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
Common data framework for rapid deployment of factory productivity and supply chain solutions
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
### [Common Data Model enables RAPID deployment for productivity solutions – Dispatching and Reporting (Part 3/3)](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
Improve cycle time by 10% in less than 6 months using SmartFactory Dispatching Solution
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimize-factory-performance-2/)
### [Optimize factory performance](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimize-factory-performance-2/)
Madhav Kidambi describes how to improve factory performance from the enterprise down to the factory floor.
## Planning
[ FAQs ](/planning-faqs/)
[ View all ](/semiconductor-blog-category/planning)
[  ](https://appliedsmartfactory.com/semiconductor-blog/planning/boosting-productivity-with-advanced-planning-scheduling-solutions/)
### [Boosting productivity with advanced planning & scheduling solutions](https://appliedsmartfactory.com/semiconductor-blog/planning/boosting-productivity-with-advanced-planning-scheduling-solutions/)
New ways to streamline device production processes and wring higher productivity
## Scheduling
[ FAQs ](/scheduling-faqs/)
[ View all ](/semiconductor-blog-category/scheduling/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/scheduling/the-power-problem-semiconductor-energy-management/)
### [The power problem](https://appliedsmartfactory.com/semiconductor-blog/scheduling/the-power-problem-semiconductor-energy-management/)
Why energy management is the next frontier for fab competitiveness
[  ](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-1/)
### [Using a framework to validate factory scheduling solution systems (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-1/)
A quality factory scheduling solution can improve equipment productivity, product quality, and on-time delivery of products
[  ](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-2/)
### [Using a framework to validate factory scheduling solution systems (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-2/)
Make more advanced validations and fine tune the schedule generated by a factory schedule solution system to get the most from your semiconductor factory
[  ](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solutions-for-semiconductor-factories/)
### [Pros and cons of various scheduling solutions for semiconductor factories](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solutions-for-semiconductor-factories/)
Choose scheduling that will be the right fit for your factory needs
[  ](https://appliedsmartfactory.com/semiconductor-blog/scheduling/dispatching-scheduling-algorithms-impact/)
### [Analyze impact of dispatching and scheduling Algorithms on factory KPI’s](https://appliedsmartfactory.com/semiconductor-blog/scheduling/dispatching-scheduling-algorithms-impact/)
Use APF Fusion® to integrate dispatching and scheduling algorithms.
[  ](https://appliedsmartfactory.com/semiconductor-blog/scheduling/smartfactory-dispatching-solutions/)
### [Improve throughput by 5-10% using SmartFactory dispatching solutions](https://appliedsmartfactory.com/semiconductor-blog/scheduling/smartfactory-dispatching-solutions/)
Increase productivity by another 3-5% by integrating SmartFactory scheduling and dispatching solutions
## Use Cases
[ FAQs ](/use-cases-faqs/)
[ View all ](/semiconductor-blog-category/use-cases/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/avalign-technologies-case-study/)
### [Avalign Technologies improved planner productivity by approximately 75% using SmartFactory Production Control](https://appliedsmartfactory.com/semiconductor-blog/use-cases/avalign-technologies-case-study/)
Production Control simulation identifies roadblocks and overcomes challenges
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/maximize-roi-real-time/)
### [Infineon Technologies maximizes ROI real-time with SmartFactory Activity Manager®](https://appliedsmartfactory.com/semiconductor-blog/use-cases/maximize-roi-real-time/)
Activity Manager quickly tests models, puts data in easy-to-compare interface
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/infineon-technologies-describes-how-they-optimize-productivity/)
### [Infineon Technologies describes how they optimize productivity](https://appliedsmartfactory.com/semiconductor-blog/use-cases/infineon-technologies-describes-how-they-optimize-productivity/)
Enable dispatching, planning, and scheduling solutions integrated with real-time data to boost factory productivity.
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
### [UMC describes how they achieved manufacturing operations excellence](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
UMC integrates real-time dispatching, full automation workflow, MES 300works® and more.
## Smart Manufacturing
[ FAQs ](/smart-manufacturing-faqs/)
[ View all ](/semiconductor-blog-category/smart-manufacturing/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/incremental-automation-delivers-early-wins-and-long-term-gain/)
### [Incremental automation delivers early wins and long-term gain](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/incremental-automation-delivers-early-wins-and-long-term-gain/)
How SmartFactory enables a phased approach to fit specific manufacturers’ needs
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/how-semiconductor-industry-bridging-talent-gap/)
### [Bridging the talent gap](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/how-semiconductor-industry-bridging-talent-gap/)
How the semiconductor industry is responding to a design workforce crisis
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/semiconductor-chiplets-3d-stacking-sustainability-challenges/)
### [Navigating the challenges of chiplets, 3D stacking and sustainability](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/semiconductor-chiplets-3d-stacking-sustainability-challenges/)
Automation solutions need to keep up with increased complexity
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/origins-of-manufacturing/)
### [Smart Manufacturing Evolution](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/origins-of-manufacturing/)
Origins of manufacturing – what makes it smart?
(Part 1 of 3)
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/opportunity-to-leapfrog-manufacturing-automation/)
### [Smart Manufacturing Evolution](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/opportunity-to-leapfrog-manufacturing-automation/)
India’s opportunity to leapfrog manufacturing automation technology
(Part 2 of 3)
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/leaping-ahead-factory-automation/)
### [Smart Manufacturing Evolution](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/leaping-ahead-factory-automation/)
Key elements for leaping ahead in factory automation
(Part 3 of 3)
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/achieve-efficiency-and-sustainability-goals/)
### [Manufacturing automation software helps achieve efficiency and sustainability goals](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/achieve-efficiency-and-sustainability-goals/)
Advance factory automation to optimize manufacturing processes and reduce waste
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/advanced-automation-solutions/)
### [Next-Generation of Advanced Automation Solutions](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/advanced-automation-solutions/)
Increasing quality and productivity in factories of any size with Applied SmartFactory integrated automation solutions for semiconductor manufacturers
[  ](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/what-is-smart-manufacturing/)
### [What is Smart Manufacturing?](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/what-is-smart-manufacturing/)
We define smart manufacturing as striving for zero defects and optimal asset utilization of trying to get the most out of what you have. This allows you to drive the highest quality in your semiconductor factory and create the most profit from your operations.
## Battery
[ View all ](/battery-blog/)
[  ](https://appliedsmartfactory.com/battery-blog/automation/battery-gigafactory-anomaly-detection-ensemble-case-study/)
### [Cutting downtime with integrated quality and predictive maintenance](https://appliedsmartfactory.com/battery-blog/automation/battery-gigafactory-anomaly-detection-ensemble-case-study/)
Case study: How deploying Anomaly Detection Ensemble saved millions
[  ](https://appliedsmartfactory.com/battery-blog/automation/battery-gigafactory-cutting-downtime-with-integrated-quality-predictive-maintenance/)
### [Cutting downtime with integrated quality and predictive maintenance](https://appliedsmartfactory.com/battery-blog/automation/battery-gigafactory-cutting-downtime-with-integrated-quality-predictive-maintenance/)
How battery gigafactories can tie their quality story into their maintenance operation
[  ](https://appliedsmartfactory.com/battery-blog/automation/battery-manufacturing-process-quality-solutions/)
### [Powering the future: exploring process quality solutions in the battery sector](https://appliedsmartfactory.com/battery-blog/automation/battery-manufacturing-process-quality-solutions/)
How to achieve higher quality, reliability and efficiency with statistical process control and fault detection
[  ](https://appliedsmartfactory.com/battery-blog/automation/improve-decision-making-with-unified-process-control/)
### [Battery manufacturers can improve decision-making with Unified Process Control](https://appliedsmartfactory.com/battery-blog/automation/improve-decision-making-with-unified-process-control/)
Gain a holistic view of equipment and process health for increased performance and quality
[  ](https://appliedsmartfactory.com/battery-blog/automation/embracing-advanced-automation-solutions/)
### [The future of battery manufacturing: embracing advanced automation solutions](https://appliedsmartfactory.com/battery-blog/automation/embracing-advanced-automation-solutions/)
Maximize efficiency, quality, safety, and reduce costs
---
### [SmartFactory Defect Source](https://appliedsmartfactory.com/process-quality-solutions/defect-source/)
**Published:** June 4, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory Defect Source
# 根本原因分析を加速し、装置ダウンタイムを最小化
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## 半導体メーカーは、制御外イベントの原因をどのようにより迅速に特定できるのでしょうか？
SmartFactory Defect Source は、半導体製造における Out-Of-Contro (OOC) 欠陥エベントのトラブルシューティングに AI を活用します。欠陥が発生したレイヤーを自動で特定できるため、エンジニアの根本原因分析を加速し、手作業によるトラブルシューティングを削減します。
## SmartFactory Defect Sourceを選ぶ理由
SmartFactory Defect Sourceは、チームによる迅速な意思決定、エンジニアリング工数の削減、装置停止によるロスタイムの短縮を支援します。
**実際の生産現場で実証された成果：**
### 欠陥発生源特定までの意思決定時間を50%以上短縮
### OOCイベントをトリガーとした自動欠陥源特定および根本原因分析を、数時間から数秒へ短縮
#### 歩留まりエンジニアの手作業によるトラブルシューティング工数を90%削減
## 私たちの取り組みから得られる効果
## 根本原因分析の迅速化
- 検出から調査に至るまでの遅延時間を短縮
- 是正処置をどこに集中させるべきかを迅速に把握可能
## エンジニアリングリソースのより効率的な活用
- 手作業および特定の専門家に特化したトラブルシューティングへの依存度を低減
- 一部の経験豊富なエンジニアに依存しがちな知見の蓄積・活用を支援
- データサイエンスの専門知識を必要とせず、直観的な Web ベースのトラブルシューティング手順をベースにした作業が可能
## 既存の製造データとシステムのより効果的な活用
- 既存の DMS 投資を基盤とし、そのまま活かしながらの構築が可能
- Klarity、DiscoverなどのシステムおよびKLARFやTIFFなどのファイル形式や標準プロトコルを使用する御社ソリューションと統合可能
- API、SEM、TEM、ウェハマップから得られる検査・レビューデータを統合し、より包括的な欠陥分析を実現
---
### [SmartFactory Defect Classification](https://appliedsmartfactory.com/process-quality-solutions/defect-classification/)
**Published:** May 12, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory Defect Classification
# 手作業およびルールベースによる欠陥分類に取って代わる存在
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## 半導体メーカーは、どのようにリアルタイムかつ高精度に欠陥を検出・分類できるのでしょうか？
SmartFactory Defect Classificationは、半導体製造における検査画像を100種類以上の欠陥カテゴリとして自動的に検知・分類可能な実績のあるAIベースのソリューションです。手作業およびルールベースの欠陥レビューに取って代わり、本ソリューションは分類精度の向上、サイクルタイムの短縮、そして開発・立ち上げ・大量生産の各フェーズに渡って一貫性と拡張性のある欠陥判定を実現します。
## SmartFactory Defect Classificationを選ぶ理由
SmartFactory Defect Classification は、量産フェーズの規模感を想定して設計されており、手作業およびルールベースの欠陥分類システムの限界や制限事項を解決します。
**実際の生産現場で実証された成果：**
### 0.3～1%の歩留まり改善によりダイレクトに売上向上に貢献
### 人間による作業を最大90％削減（人対装置の比率）
### 検査から意思決定までのサイクルタイムを約26%短縮
これらの結果より、半導体メーカーは手作業によるレビューへの依存度を減らしつつ、業務の一貫性を向上させます。
## 私たちの取り組みから得られる効果
## 量産フェーズの規模感が想定された自動化の実現
SmartFactory Defect Classificationによる欠陥分類の自動化：
- SmartFactory Defect Classificationは検査欠陥の分類作業を90%以上の自動化率で実現し、手作業によるレビュー工数を大幅に削減します。
- SmartFactory Defect Classificationは不良流出率０％が報告されており、後工程以前に確実に欠陥を特定します。
- SmartFactory Defect Classificationは量産フェーズにおけるあらゆる欠陥対象項目に対して97.5%以上の分類精度を達成しており、製品の信頼性を向上させます。
## 歩留まりとサイクルタイムの改善
欠陥分類の自動化による歩留まりおよび検査スループットの向上
- より早くより一貫した欠陥検出および判定によって測定可能な歩留まりのリカバリを支援します。
- 欠陥レビューの待ち時間を短縮し、開発・立ち上げ・大量生産フェーズに渡って検査～意思決定のサイクルタイムを短縮します。
- 検査ツールの利用効率を向上させ、スキャンツールへの追加設備投資を延期または回避を可能にします。
## ファブ全体のインテリジェンス（統合による高度化）
欠陥分類データをファブ全体で活用：
- 欠陥分類の結果をダイレクトに歩留まり解析、判定、エンジニアリングのワークフローに反映させます。
- SPC、FDC、Run-to-Runといった複数の制御システムと統合することで、品質コントロール機能からプロセスコントロール機能全体に渡り、一貫した欠陥コンテキストを提供します。
- 検査結果と下流工程の是正処置を連携させることで、繰り返される処理へのフィードバック制御および迅速な根本原因分析を可能にします。
# 欠陥検出から実行可能なプロセス改善まで
AIを活用した欠陥分類と製造システム間の密な連携により、SmartFactory Defect Classification は欠陥検出から、より迅速かつ的確なプロセス意思決定までの一貫した取り組みを支援します。具体的には、分類精度の向上、手作業の削減、より効率的な欠陥データの活用を通じた歩留まり改善、プロセス制御、継続的な生産最適化を支援します。
---
### [Equipment Automation](https://appliedsmartfactory.com/process-quality-solutions/equipment-automation/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Equipment Automation
# 提高生产效率，降低人为失误
[ 阅读【质量博客】 ](/zh-hans/semiconductor-blog-category/quality-zh-hans/)
## 您的工厂是否计划将基础人工操作升级为自动化？
SmartFactory Equipment Automation是一个在运行时执行自动化服务的设备设计和控制框架。 该解决方案集成了设备数据（生产制造中最大的数据来源），以实现自动化流程设计、交易和序列测试、运行时故障诊断和集中用户维护。 这种集成的数据能力提高了生产效率，并减少了错误和物料损失。
## 为何选择 SmartFactory Equipment Automation？
### 通过自动化派工系统实现每日晶圆产量提升 10 - 15%
### 通过自动化派工系统实现设备利用率提升 10%
### 数据记录时间减少97%
## 采用我们的解决方案能为您带来什么？
## 优化资产
- 通过执行运行时自动化场景，保持设备资产的利用率
- 与SmartFactory FullAuto协调运输、装载、加工和卸载物料，无需操作员干预
## 减少错误
- 进行质量控制预检查，以保证正确的物料符合适当的顺序和配方
- 始终满足质量和工程数据要求
## 数据集成
- 编制数据收集记录并将其分发给适当的应用程序进行分析
- 分析设备性能，确定隐藏的周期时间损失
- 与应用材料公司的SmartFactory CIM解决方案和其他非应用材料公司的解决方案集成
---
### [Recipe Management](https://appliedsmartfactory.com/process-quality-solutions/recipe-management/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Recipe Management
# 保护您的配方管理
[ 阅读【质量博客】 ](/zh-hans/semiconductor-blog-category/quality-zh-hans/)
## 您是如何管理工厂的数千种配方?
制造设备的配方是一个公司的顶级知识产权。 为了管理这些配方，我们的SmartFactory Recipe Management系统（RMS）提供了一种简单的方法来检查配方的差异、副本和合并，同时通过安全的集中存储库保护配方的IP。 该解决方案验证运行时配方和参数，提高生产线良率并支持可追溯性。
## 为何选择 SmartFactory Recipe Management？
### 人为失误导致的物料损失预计降低 50%
### 成熟制程产线良率预计提升 4 - 10%
## 采用我们的解决方案能为您带来什么？
## 核心配方库
- 使用冗余和版本控制的方法在安全存储库中维护配方
- 通过防止设备配方意外丢失来保持业务连续性
- 提供认证和审核准备的历史配方可追溯性
## 有效的自动配方
- 控制设备常量和配方参数值，减少错误处理
- 与设备自动化一起自动化运行时验证, 增加晶圆产量
## 减少人为失误
- 根据配方规范验证运行时配方，最大限度地减少返工和损失
- 减少因变更不正确的步骤或修改错误的参数而产生的错误
---
### [Fault Detection](https://appliedsmartfactory.com/process-quality-solutions/fault-detection/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Fault Detection
# 减少因过程偏移造成的产量损失
[ 阅读【质量博客】 ](/zh-hans/semiconductor-blog-category/quality-zh-hans/)
## 您是通过什么方式来减少设备的偏移问题？
SmartFactory Fault Detection是一个过程控制解决方案，可以根据性能指标侦测传感器和事件，快速检测设备问题，从而提高设备的有效利用率和减少晶圆废料损失。 与许多依赖于反应性方法的独立系统不同，SmartFactory Fault Detection能够在设备问题影响产出之前提供主动和快速的反馈。
## 为何选择 SmartFactory Fault Detection？
### 减少高达90%的设备过程误警率
### 减少高达95%的原材料损失
### 设备异常停机时间减少25小时以上
## 采用我们的解决方案能为您带来什么？
## 改善晶圆厂关键绩效指标
- 通过从源头侦测设备故障来保护工厂
- 侦测以前无法检测到的问题
- 通过分析和报表监测设备性能
## 可采取的行动建议
- 在设备发生故障之前发出有效的预测并主动通知维护系统
- 提高了有效的预警度，减少设备停机时间
- 提供多种有效的方法减少误警率，方便系统维护
## 集成式的平台
- 提供通用平台，Run-to-Run系统、SPC系统、Recipe Management系统与FDC系统进行了无缝的整合，促进信息共享
- 整合过程设备和量测设备之间的数据，并且可以与其他的APC系统模块进行交互
---
### [Run To Run Control](https://appliedsmartfactory.com/process-quality-solutions/run-to-run-control/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Run-to-Run Control
# 优化设备配方参数
[ 阅读【质量博客】 ](/zh-hans/semiconductor-blog-category/quality-zh-hans/)
## 您是如何解决工厂的过程能力问题?
SmartFactory Run-to-Run Control是一个先进过程控制（APC）解决方案，可以提高过程能力（Cpk）和优化设备配方参数。 这个开箱即用的解决方案提供了专利的模型预测，经过验证部署成功，包括一个多变量、约束、基于优化的过程控制器。
## 为何选择 SmartFactory Run-to-Run Control？
### Cpk平均提高30%
### 晶片废料减少10-30%
### 成熟良率提升2-4%
## 采用我们的解决方案能为您带来什么？
## 提升良率
- 减少生产变异现象
- 能够在开发和生产阶段做出更好的决策
- 在大批次生产过程中减少良率的变化
## 提高品质
- 通过自动化优化设备配方参数来改进Cpk
- 通过对设备和过程加工产生的漂移现象进行补偿，减少OOS异常样品和材料损失
- 通过减少测试用的晶片来提高产出
## 降低拥有成本
- 通过统一的建模架构减少模型管理工作
- 提供通用平台，SPC系统、FDC系统与Run-to-Run系统进行了无缝的整合，促进信息共享
---
### [Productivity Solutions](https://appliedsmartfactory.com/productivity-solutions/)
**Published:** September 13, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory生産性ソリューション
より少ないリソースでより多く
の成果を得るために、生産性の
最大化と生産効率の向上を
実現
[](/ja/semiconductor/productivity-solutions/real-time-scheduling-reporting/)### Real Time Scheduling & Reporting
高度なルールベース/リアルタイム戦略により、
ばらつきを低減
[](/ja/semiconductor/productivity-solutions/fullauto/)### FullAuto
リアルタイムなイベントベースのワークフローを
使用し、設備の非稼働時間を排除
[](/ja/semiconductor/productivity-solutions/advanced-scheduling/)### Advanced Scheduling
スケジュール予測による、主要ボトルネック工程の生産性向上
[](/ja/semiconductor/productivity-solutions/production-control/)### Production Control
製造オペレーションに影響を与えることなく、WIP（仕掛品）のスループットと設備稼働率を改善
[](/ja/semiconductor/productivity-solutions/rtd/)### RTD
複雑なプログラミングを伴わない、プロセス
改善箇所の特定と実装
[](/ja/semiconductor/productivity-solutions/activity-manager/)### Activity Manager
統合自動化ワークフローフレームワークを使用した、リソース活用と生産性向上
[](/ja/semiconductor/productivity-solutions/fusion/)### Fusion
シミュレーションモデル精度の高度化による、
本番環境導入前のルール変更による影響を
定量化
[](/ja/semiconductor/productivity-solutions/simulation-autosched/)### Simulation AutoSched
迅速な分析と的確な意思決定の支援
[](/ja/productivity-solutions/material-control/)### Material Control
WIP（仕掛品）の移動を自動化し、スループットを向上、装置のアイドル時間を削減
# 工場スループットと設備稼働率を高める生産性
### 製造全体にわたって、高効率かつ高スループットなファクトリーオペレーションを推進
[](/ja/semiconductor/productivity-solutions/real-time-scheduling-reporting/)#### Real Time Scheduling & Reporting
高度なルールベース/リアルタイム戦略により、ばらつきを低減
[](/ja/semiconductor/productivity-solutions/fullauto/)#### FullAuto
リアルタイムなイベントベースのワークフローを使用し、設備の非稼働時間を排除
[](/ja/semiconductor/productivity-solutions/advanced-scheduling/)#### Advanced Scheduling
スケジュール予測による、主要ボトルネック工程の生産性向上
[](/ja/semiconductor/productivity-solutions/production-control/)#### Production Control
製造オペレーションに影響を与えることなく、WIP（仕掛品）のスループットと設備稼働率を改善
[](/ja/semiconductor/productivity-solutions/activity-manager/)#### Activity Manager
統合自動化ワークフローフレームワークを使用した、リソース活用と生産性向上
[](/ja/semiconductor/productivity-solutions/rtd/)#### RTD
複雑なプログラミングを伴わない、プロセス改善箇所の特定と実装
[](/ja/semiconductor/productivity-solutions/fusion/)#### Fusion
シミュレーションモデル精度の高度化による、本番環境導入前のルール変更による影響を定量化
[](/ja/semiconductor/productivity-solutions/simulation-autosched/)#### Simulation AutoSched
迅速な分析と的確な意思決定の支援
[](/ja/semiconductor/productivity-solutions/material-control/)#### Material Control
WIP（仕掛品）の移動を自動化し、スループットを向上、装置のアイドル時間を削減
---
### [Supply Chain Solutions](https://appliedsmartfactory.com/supply-chain-solutions/)
**Published:** September 14, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactoryサプライチェーンソリューション
サプライチェーン管理を最適化し、
計画精度・実行力・工場全体の
パフォーマンスを向上
[](/ja/semiconductor/supply-chain-solutions/enterprise-planning/)### Enterprise Planning
キャパシティプランニングの精度を高め、顧客の
需要変動にも迅速に対応
[](/ja/semiconductor/supply-chain-solutions/production-control)### Production Control
製造を止めることなく、WIPスループットと
設備稼働率を最大化する高速な「What-if」
シナリオを実行可能
[](#)### Simulation AutoMod
強力な3Dシミュレーションモデリングにより、工場のライフサイクル全体で生産性を継続的に改善
# 製造全体にわたる計画および生産制御パフォーマンスの向上
### 工場間にまたがるサプライチェーンの意思決定が与える影響を、計画・制御・シミュレーションを通じて最適化
[](/ja/semiconductor/supply-chain-solutions/enterprise-planning/)#### Enterprise Planning
キャパシティプランニングの精度を高め、顧客の需要変動にも迅速に対応
[](/ja/semiconductor/supply-chain-solutions/production-control)#### Production Control
製造を止めることなく、WIPスループットと設備稼働率を最大化する高速な「What-if」シナリオを実行可能
---
### [制造执行解决方案](https://appliedsmartfactory.com/manufacturing-execution-solutions/)
**Published:** October 12, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory 制造执行系统 (MES) 解决方案
优化整合生产运营，实现更高效管控，提升制造执行效率。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
降低生产干扰，提升运营效率
[](/zh-hans/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
通过整个生命周期的资产追踪提高资产利用率
[](/zh-hans/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works™ Full-Auto
借助自动化物料流程改进大批量生产
[](/zh-hans/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
借助开箱即用功能增强 FACTORYworks 平台，为半导体封装及相关行业提供有力支持
[](/zh-hans/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks™
借助特殊功能扩展加速大批量生产的改进
[](/zh-hans/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
实现在制品 (WIP) 生产运行自动化，提升整体产出及降低设备闲置时间
[](/zh-hans/semiconductor/manufacturing-execution-solutions/promis)### MES PROMIS™
利用晶圆厂运营建模功能提高生产效率
[](/zh-hans/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300™
无需编程即可部署您的工厂业务规则
[](/zh-hans/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
提高设备维护能力——应对计划内和计划外事件
[](/zh-hans/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
检测和预测系统故障
[](/zh-hans/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
优化半导体后段制造的 MES 系统智能
# 制造执行系统 (MES) 解决方案：支持任意规模或复杂度的可预测工厂执行
### 在整个半导体制造生命周期中，保持一致的工厂执行能力
#### 晶圆基板
适用于晶锭与晶圆制造环境的、可靠的、生产级制造执行系统 (MES) ——以一致性和可控性支持晶体生长、晶圆加工及上游生产流程。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)#### 晶圆制造
以一致性和可控性执行先进的晶圆制造——支持跨设备、跨工艺和跨生产流程的复杂操作。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)#### 测试与封装
在多变复杂的测试与封装环境中保持一致的执行力——灵活适应产品组合和产量的动态变化，同时确保工厂稳定运行。
[](/zh-hans/semiconductor/classic-mes/)#### 经典制造执行系统 (MES)
在经过验证的制造执行系统 (MES) 平台上运行成熟的工厂运营体系——以稳定性和深度支持关键制造环境，并实现规模化运作。
---
### [Alarm Management](https://appliedsmartfactory.com/manufacturing-execution-solutions/alarmmanagement/)
**Published:** September 21, 2023
**Author:** Applied Smartfactory
**Content:**
# 促进制造业效率提升
高集成度的 SmartFactory Alarm Management 解决方案
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ 降低生产杂讯，提高运营效率 ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
SmartFactory 团队推出全新警报处理解决方案
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
## 智能实时警报处理以实现更快速的响应
- 节省设备损失时间
- 降低产品质量风险
- 快速追踪整厂警报
[ 查看博客 ](/zh-hans/blog/boost-operation-efficiency/)
## 警报处理不当会导致重大问题。。。
## 。。。转向自动化应对警报处理挑战
## 使操作员能够更快地响应关键警报，从而提高良率、生产周期和制造效率。
## 我们的见解
## Our Insights
[ View All ](/blog)
## Our Insights
## Our Insights
[ View All ](/blog)
SmartFactory Alarm Management
# 高效管理警报系统，保障质量与生产效率
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## 如何在纷杂的工厂警报中准确识别关键警报？
通过高效的警报管理，SmartFactory Alarm Management 助您快速识别、优先处理警报，并及时采取有效措施。
## 为何选择 SmartFactory Alarm Management？
### 实现 100% 告警覆盖，有效减少“警报疲劳”现象
### 实时通知产线人员，设备正常运行时间 提升 1%
### 识别“关键警报”并实现自动决策，良率提升 0.5%
## 采用我们的解决方案能为您带来什么？
### 更快的故障解决
- 集中处理实时警报信息
- 去重算法减少生产噪音
- 更早发现影响质量的问题
### 更高的设备利用率
- 整合 CIM 系统报警数据，加快故障排查
- 加速根本原因分析
- 支持在制造执行系统、设备自动化等系统中预定义自动操作（如暂停批次、记录设备停机等）
### 更强的协同机制
- 设置警报接收人员和升级路径
- 实现全厂区实时可视化监控
---
### [经典制造执行系统 (MES)](https://appliedsmartfactory.com/manufacturing-execution-solutions/classic-mes/)
**Published:** April 10, 2026
**Author:** Sushmita Kumari
**Content:**
# **经典制造执行系统 (MES)**
经典制造执行系统 (MES) 解决方案是成熟的制造执行系统平台，数十年来深受半导体制造商信赖。这些系统提供久经考验的生产执行基础，适用于对稳定性、可靠性及深度管理要求极高的量产环境。众多客户仍将其作为制造环境的核心组件。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/promis/)### MES PROMIS™
稳定成熟的制造执行系统平台，支持关键任务型半导体制造。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks™
通过优化设备与工艺性能，提升产品良率。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
扩展 FACTORYworks 功能，满足高级运营需求。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300™
专为大规模制造设计的高量产制造执行系统平台。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### Alarm Management
集中化报警管理机制，保障运营稳定性。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
提供制造执行过程的可视化与监控能力。
---
### [ウェハー基板](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-substrate/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **ウェハー基板**
インゴットおよびウェハー製造環境に最適化された、信頼性の高い本番対応MES。結晶成長からウェハー加工、上流工程まで、製造プロセス全体を一貫して管理し、高い生産性と安定した品質を実現します。
[](/ja/semiconductor-blog/manufacturing-execution-ja/manufacturing-discipline-starts-at-the-substrate/)### MESブログ
ウェハー基板から始まる製造現場の規律: なぜファブに入ってからではもう遅いのか?
フロントエンドでの実行力が、半導体の成果を大きく左右する時代になっています。
---
### [Manufacturing Execution Solutions](https://appliedsmartfactory.com/manufacturing-execution-solutions/)
**Published:** September 13, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory MESソリューション
オペレーションを統合・最適化
し、より高い制御性と生産効率
を実現
[](/ja/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
アラートノイズを削減し、運用効率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
生産設備や治具工具のライフサイクル全体を通じてトレースし、活用率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works® Full-Auto
工場のモノの流れを自動化し、大量生産を効率化
[](/ja/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
FACTORYworksプラットフォームに、半導体組立や周辺業界向けの機能を追加
[](/ja/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
量産時における改善を加速するための拡張機能
を搭載
[](/ja/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
WIP（仕掛品）の移動を自動化し、スループットを向上、装置のアイドル時間を削減
[](/ja/semiconductor/manufacturing-execution-solutions/promis/)### MES PROMIS®
ファブ運用のモデリング機能により、効率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
プログラミング不要で、独自のビジネスルールを実装可能
[](/ja/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
計画保全・計画外保全の両面で、装置
メンテナンスの効果を最大化
[](/ja/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
システム障害の検知と予測を実現
[](/ja/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
半導体後工程向けに最適されたMES
## SmartFactory MES Solutions
Streamline manufacturing execution by integrating and optimizing operations for better control and efficiency.
[](/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
Reduces production noise and boosts operation efficiency
[](/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
Improves asset utilization with asset trace throughout entire life cycle
[](/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works® Full-Auto
Improves high volume manufacturing by automating flow of materials
[](/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
Augments the FACTORYworks platform with additional out-of-box functionality to support semiconductor assembly and adjacent industries
[](/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
Accelerates high volume manufacturing improvements with special feature extensions
[](/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
Automates WIP movement to increase throughput and decrease equipment idle time
[](/semiconductor/manufacturing-execution-solutions/promis)### MES PROMIS®
Boosts efficiency with fab operation modeling capabilities
[](/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
Implements your proprietary business rules without programming
[](/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
Improves power of equipment maintenance – scheduled and unscheduled activities
[](/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
Detects and predicts system failures
[](/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
Optimizes MES intelligence for semiconductor backend manufacturing
# あらゆるスケールや複雑性において、予測可能なファクトリー運用を実現するMES
### 半導体製造ライフサイクル全体にわたり、一貫したファクトリーオペレーションを実現
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-substrate/)#### ウェハー基板
インゴットおよびウェハー製造環境に最適化された、信頼性の高い本番対応MES。結晶成長からウェハー加工、上流工程まで、製造プロセス全体を一貫して管理し、高い生産性と安定した品質を実現します。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)#### ウェハーファブ
装置、プロセス、製造フローにまたがる高度で複雑なオペレーションを支えながら、一貫性と制御性の高い高度なウェハー製造を実現します。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)#### テスト & 組立
変動の大きいテストおよび組立環境においても一貫した実行を維持することで、製品ミックスや生産数量の変化に柔軟に対応しながら、工場パフォーマンスへの影響を最小限に抑えます。
[](/ja/semiconductor/classic-mes/)#### クラシックMES（Classic MES）
実績に裏付けられたMES基盤のもと、確立された工場オペレーションを安定的に実行し、クリティカルな製造環境を大規模かつ高い信頼性で支えます。
---
### [测试与封装](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **测试与封装**
在多变复杂的测试与封装环境中保持一致的执行力——灵活适应产品组合和产量的动态变化，同时确保工厂稳定运行。
[](/zh-hans/manufacturing-execution-solutions/mesforatp/)### MES解决方案
MES for ATP
优化半导体后段制造的 MES 系统智能
---
### [晶圆制造](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **晶圆制造**
以一致性和可控性执行先进的晶圆制造——支持跨设备、跨工艺和跨生产流程的复杂操作。
[](/zh-hans/manufacturing-execution-solutions/300works-full-auto/)### MES解决方案
MES 300works™ Full-Auto
借助自动化物料流程改进大批量生产
---
### [Semiconductor](https://appliedsmartfactory.com/semiconductor/)
**Published:** June 27, 2021
**Author:** Applied Smartfactory
**Content:**
# スマートファクトリーソリューションで半導体製造のパフォーマンスを向上
当社の提供するMES、プロセス品質、生産性、サプライチェーンなどの機能について、スクロールしてご覧ください。
## SmartFactory MESソリューション
オペレーションを統合・最適化
し、より高い制御性と生産効率
を実現
[](/ja/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
アラートノイズを削減し、運用効率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
生産設備や治具工具のライフサイクル全体を通じてトレースし、活用率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works® Full-Auto
工場のモノの流れを自動化し、大量生産を効率化
[](/ja/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
FACTORYworksプラットフォームに、半導体組立や周辺業界向けの機能を追加
[](/ja/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
量産時における改善を加速するための拡張機能
を搭載
[](/ja/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
WIP（仕掛品）の移動を自動化し、スループットを向上、装置のアイドル時間を削減
[](/ja/semiconductor/manufacturing-execution-solutions/promis/)### MES PROMIS®
ファブ運用のモデリング機能により、効率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
プログラミング不要で、独自のビジネスルールを実装可能
[](/ja/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
計画保全・計画外保全の両面で、装置
メンテナンスの効果を最大化
[](/ja/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
システム障害の検知と予測を実現
[](/ja/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
半導体後工程向けに最適されたMES
## SmartFactory MES Solutions
Streamline manufacturing execution by integrating and optimizing operations for better control and efficiency.
[](/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
Reduces production noise and boosts operation efficiency
[](/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
Improves asset utilization with asset trace throughout entire life cycle
[](/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works® Full-Auto
Improves high volume manufacturing by automating flow of materials
[](/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
Augments the FACTORYworks platform with additional out-of-box functionality to support semiconductor assembly and adjacent industries
[](/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
Accelerates high volume manufacturing improvements with special feature extensions
[](/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
Automates WIP movement to increase throughput and decrease equipment idle time
[](/semiconductor/manufacturing-execution-solutions/promis)### MES PROMIS®
Boosts efficiency with fab operation modeling capabilities
[](/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
Implements your proprietary business rules without programming
[](/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
Improves power of equipment maintenance – scheduled and unscheduled activities
[](/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
Detects and predicts system failures
[](/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
Optimizes MES intelligence for semiconductor backend manufacturing
# あらゆるスケールや複雑性において、予測可能なファクトリー運用を実現するMES
### 半導体製造ライフサイクル全体にわたり、一貫したファクトリーオペレーションを実現
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-substrate/)#### ウェハー基板
インゴットおよびウェハー製造環境に最適化された、信頼性の高い本番対応MES。結晶成長からウェハー加工、上流工程まで、製造プロセス全体を一貫して管理し、高い生産性と安定した品質を実現します。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)#### ウェハーファブ
装置、プロセス、製造フローにまたがる高度で複雑なオペレーションを支えながら、一貫性と制御性の高い高度なウェハー製造を実現します。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)#### テスト & 組立
変動の大きいテストおよび組立環境においても一貫した実行を維持することで、製品ミックスや生産数量の変化に柔軟に対応しながら、工場パフォーマンスへの影響を最小限に抑えます。
[](/ja/semiconductor/classic-mes/)#### クラシックMES（Classic MES）
実績に裏付けられたMES基盤のもと、確立された工場オペレーションを安定的に実行し、クリティカルな製造環境を大規模かつ高い信頼性で支えます。
## SmartFactoryプロセス品質ソリューション
プロセスシステムの統合より、
優れたプロセス品質と
一貫性を確保
[](/ja/semiconductor/process-quality-solutions/run-to-run-control/)### Run-to-Run Control
装置とプロセスのパフォーマンスを最適化すること
で、歩留まりを向上
[](/ja/semiconductor/process-quality-solutions/spc/)### SPC®
データ組み合わせ仕組みでよる効率的に
分析施行して監視自動化機能を提供
[](/ja/semiconductor/process-quality-solutions/fault-detection/)### Fault Detection
歩留まり損失を最小限に抑え、予定外の装置ダウンタイムを減少
[](/ja/semiconductor/process-quality-solutions/recipe-management/)### Recipe Management System
レシピ管理システムを通じて製品処理製造の
品質一貫性を確保
[](/ja/process-quality-solutions/asset-trace/)### SmartFactory Asset Trace
生産設備や治具工具のライフサイクル全体を通じてトレースし、活用率を向上
[](/ja/semiconductor/process-quality-solutions/equipment-automation/)### Equipment Automation
生産性を向上させ、人為的なエラーを減少させ、
業界スタンダードの自動処理仕組みを実現
[](/ja/process-quality-solutions/maintenance-management/)### Maintenance Management
計画保全・計画外保全の両面で、装置
メンテナンスの効果を最大化
# 工場全体での歩留まり向上とばらつき低減を実現するプロセス品質ソリューション
### 半導体製造全体にわたって、一貫した歩留まりとプロセス制御を実現
[](/ja/semiconductor/process-quality-solutions/run-to-run-control/)#### Run-to-Run Control
装置とプロセスのパフォーマンスを最適化することで、歩留まりを向上
[](/ja/semiconductor/process-quality-solutions/spc/)#### SPC
データ組み合わせ仕組みでよる効率的に
分析施行して監視自動化機能を提供
[](/ja/semiconductor/process-quality-solutions/fault-detection/)#### Fault Detection
歩留まり損失を最小限に抑え、予定外の装置ダウンタイムを減少
[](/ja/semiconductor/process-quality-solutions/recipe-management/)#### Recipe Management System
レシピ管理システムを通じて製品処理製造の品質一貫性を確保
[](/ja/semiconductor/process-quality-solutions/equipment-automation/)#### Equipment Automation
生産性を向上させ、人為的なエラーを減少させ、業界スタンダードの自動処理仕組みを実現
[](/ja/semiconductor/process-quality-solutions/asset-trace/)#### Asset Trace
生産設備や治具工具のライフサイクル全体を通じてトレースし、活用率を向上
[](/ja/semiconductor/process-quality-solutions/maintenance-management/)#### Maintenance Management
計画保全・計画外保全の両面で、装置
メンテナンスの効果を最大化
[](https://appliedsmartfactory.com/process-quality-solutions/defect-classification/)#### Defect Classification
分類精度を向上させ、サイクルタイムを短縮し、一貫性のあるスケーラブルな欠陥判定を実現します。
[](https://appliedsmartfactory.com/process-quality-solutions/defect-source/)#### Defect Source
Out-of-Control(OOC)イベントにおける欠陥発生レイヤーを自動特定し、手作業によるトラブルシューティング負荷を低減することで、根本原因分析を加速します。
[](https://appliedsmartfactory.com/process-quality-solutions/knowledge-advisor/)#### Knowledge Advisor
AIと工場データを統合し、エンジニアの問題解析・解決を革新。再利用可能なナレッジを活用することで、大規模な製造現場でもより迅速かつ一貫性のある意思決定を実現します。
## SmartFactory生産性ソリューション
より少ないリソースでより多く
の成果を得るために、生産性の
最大化と生産効率の向上を
実現
[](/ja/semiconductor/productivity-solutions/real-time-scheduling-reporting/)### Real Time Scheduling & Reporting
高度なルールベース/リアルタイム戦略により、
ばらつきを低減
[](/ja/semiconductor/productivity-solutions/fullauto/)### FullAuto
リアルタイムなイベントベースのワークフローを
使用し、設備の非稼働時間を排除
[](/ja/semiconductor/productivity-solutions/advanced-scheduling/)### Advanced Scheduling
スケジュール予測による、主要ボトルネック工程の生産性向上
[](/ja/semiconductor/productivity-solutions/production-control/)### Production Control
製造オペレーションに影響を与えることなく、WIP（仕掛品）のスループットと設備稼働率を改善
[](/ja/semiconductor/productivity-solutions/rtd/)### RTD
複雑なプログラミングを伴わない、プロセス
改善箇所の特定と実装
[](/ja/semiconductor/productivity-solutions/activity-manager/)### Activity Manager
統合自動化ワークフローフレームワークを使用した、リソース活用と生産性向上
[](/ja/semiconductor/productivity-solutions/fusion/)### Fusion
シミュレーションモデル精度の高度化による、
本番環境導入前のルール変更による影響を
定量化
[](/ja/semiconductor/productivity-solutions/simulation-autosched/)### Simulation AutoSched
迅速な分析と的確な意思決定の支援
[](/ja/productivity-solutions/material-control/)### Material Control
WIP（仕掛品）の移動を自動化し、スループットを向上、装置のアイドル時間を削減
# 工場スループットと設備稼働率を高める生産性
### 製造全体にわたって、高効率かつ高スループットなファクトリーオペレーションを推進
[](/ja/semiconductor/productivity-solutions/real-time-scheduling-reporting/)#### Real Time Scheduling & Reporting
高度なルールベース/リアルタイム戦略により、ばらつきを低減
[](/ja/semiconductor/productivity-solutions/fullauto/)#### FullAuto
リアルタイムなイベントベースのワークフローを使用し、設備の非稼働時間を排除
[](/ja/semiconductor/productivity-solutions/advanced-scheduling/)#### Advanced Scheduling
スケジュール予測による、主要ボトルネック工程の生産性向上
[](/ja/semiconductor/productivity-solutions/production-control/)#### Production Control
製造オペレーションに影響を与えることなく、WIP（仕掛品）のスループットと設備稼働率を改善
[](/ja/semiconductor/productivity-solutions/activity-manager/)#### Activity Manager
統合自動化ワークフローフレームワークを使用した、リソース活用と生産性向上
[](/ja/semiconductor/productivity-solutions/rtd/)#### RTD
複雑なプログラミングを伴わない、プロセス改善箇所の特定と実装
[](/ja/semiconductor/productivity-solutions/fusion/)#### Fusion
シミュレーションモデル精度の高度化による、本番環境導入前のルール変更による影響を定量化
[](/ja/semiconductor/productivity-solutions/simulation-autosched/)#### Simulation AutoSched
迅速な分析と的確な意思決定の支援
[](/ja/semiconductor/productivity-solutions/material-control/)#### Material Control
WIP（仕掛品）の移動を自動化し、スループットを向上、装置のアイドル時間を削減
## SmartFactoryサプライチェーンソリューション
サプライチェーン管理を最適化し、
計画精度・実行力・工場全体の
パフォーマンスを向上
[](/ja/semiconductor/supply-chain-solutions/enterprise-planning/)### Enterprise Planning
キャパシティプランニングの精度を高め、顧客の
需要変動にも迅速に対応
[](/ja/semiconductor/supply-chain-solutions/production-control)### Production Control
製造を止めることなく、WIPスループットと
設備稼働率を最大化する高速な「What-if」
シナリオを実行可能
[](#)### Simulation AutoMod
強力な3Dシミュレーションモデリングにより、工場のライフサイクル全体で生産性を継続的に改善
# 製造全体にわたる計画および生産制御パフォーマンスの向上
### 工場間にまたがるサプライチェーンの意思決定が与える影響を、計画・制御・シミュレーションを通じて最適化
[](/ja/semiconductor/supply-chain-solutions/enterprise-planning/)#### Enterprise Planning
キャパシティプランニングの精度を高め、顧客の需要変動にも迅速に対応
[](/ja/semiconductor/supply-chain-solutions/production-control)#### Production Control
製造を止めることなく、WIPスループットと設備稼働率を最大化する高速な「What-if」シナリオを実行可能
## SmartFactory関連ブログ
自動化のエキスパートから、SmartFactoryの自律型ソリューションで製造を変革する方法を学びましょう。
##### [半導体関連ブログ](/ja/semiconductor-blog/)
## SmartFactory関連イベント
当社の自動化のエキスパートと提携して、スマートな製造のアドバンテージを迅速に実現しましょう。
##### [半導体イベント](/ja/semiconductor-events/)
[](/semiconductor/process-quality-solutions/run-to-run-control/)#### Run-to-Run Control
Improves yield by optimizing equipment and process performance.
[](/semiconductor/process-quality-solutions/spc/)#### SPC®
Combines the power of data transformation with analytics to deliver intelligent detection.
[](/semiconductor/process-quality-solutions/fault-detection/)#### Fault Detection
Minimizes yield loss and reduces unscheduled equipment downtime.
[](/semiconductor/process-quality-solutions/recipe-management/)#### Recipe Management System
Provides manufacturing consistency through automated recipe management.
[](/semiconductor/process-quality-solutions/equipment-automation/)#### Equipment Automation
Increases productivity and reduces human error. Enables automation possibilities beyond manual basics.
[](/semiconductor/process-quality-solutions/asset-trace/)#### Asset Trace
Improves asset utilization with asset trace throughout entire life cycle.
[](/semiconductor/process-quality-solutions/maintenance-management/)#### Maintenance Management
Improves power of equipment maintenance – scheduled and unscheduled activities.
---
### [半导体行业](https://appliedsmartfactory.com/semiconductor/)
**Published:** July 22, 2021
**Author:** Applied Smartfactory
**Content:**
# 凭借 SmartFactory 半导体制造解决方案提升晶圆厂运营
向下滚动以了解更多关于我们核心能力的信息，包括制造执行系统 (MES)、工艺质量、生产效率和供应链。
## SmartFactory 制造执行系统 (MES) 解决方案
优化整合生产运营，实现更高效管控，提升制造执行效率。
[](/zh-hans/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
降低生产干扰，提升运营效率
[](/zh-hans/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
通过整个生命周期的资产追踪提高资产利用率
[](/zh-hans/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works™ Full-Auto
借助自动化物料流程改进大批量生产
[](/zh-hans/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
借助开箱即用功能增强 FACTORYworks 平台，为半导体封装及相关行业提供有力支持
[](/zh-hans/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks™
借助特殊功能扩展加速大批量生产的改进
[](/zh-hans/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
实现在制品 (WIP) 生产运行自动化，提升整体产出及降低设备闲置时间
[](/zh-hans/semiconductor/manufacturing-execution-solutions/promis)### MES PROMIS™
利用晶圆厂运营建模功能提高生产效率
[](/zh-hans/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300™
无需编程即可部署您的工厂业务规则
[](/zh-hans/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
提高设备维护能力——应对计划内和计划外事件
[](/zh-hans/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
检测和预测系统故障
[](/zh-hans/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
优化半导体后段制造的 MES 系统智能
# 制造执行系统 (MES) 解决方案：支持任意规模或复杂度的可预测工厂执行
### 在整个半导体制造生命周期中，保持一致的工厂执行能力
#### 晶圆基板
适用于晶锭与晶圆制造环境的、可靠的、生产级制造执行系统 (MES) ——以一致性和可控性支持晶体生长、晶圆加工及上游生产流程。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)#### 晶圆制造
以一致性和可控性执行先进的晶圆制造——支持跨设备、跨工艺和跨生产流程的复杂操作。
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)#### 测试与封装
在多变复杂的测试与封装环境中保持一致的执行力——灵活适应产品组合和产量的动态变化，同时确保工厂稳定运行。
[](/zh-hans/semiconductor/classic-mes/)#### 经典制造执行系统 (MES)
在经过验证的制造执行系统 (MES) 平台上运行成熟的工厂运营体系——以稳定性和深度支持关键制造环境，并实现规模化运作。
## SmartFactory 工艺质量解决方案
实施零缺陷战略，确保卓越的工艺质量和一致性。
[](/zh-hans/semiconductor/process-quality-solutions/run-to-run-control/)### Run-to-Run Control
通过提升设备以及工艺的性能改善良率
[](/zh-hans/semiconductor/process-quality-solutions/spc/)### SPC™
结合数据信息的提取与分析，提供智能决策
[](/zh-hans/semiconductor/process-quality-solutions/fault-detection/)### Fault Detection
最大限度降低良率损失，减少计划外设备停机
[](/zh-hans/semiconductor/process-quality-solutions/recipe-management/)### Recipe Management System
通过自动化配方管理保持一致性
[](/zh-hans/semiconductor/process-quality-solutions/equipment-automation)### Equipment Automation
提高生产效率，减少人为错误，实现超越手动基础的全自动化可能性
[](/zh-hans/process-quality-solutions/asset-trace/)### SmartFactory Asset Trace
通过整个生命周期的资产追踪提高资产利用率
[](/zh-hans/process-quality-solutions/maintenance-management/)### Maintenance Management
提高设备维护能力——应对计划内和计划外事件
# 工艺质量解决方案：提升良率并降低整个晶圆厂的工艺波动
### 在半导体制造中实现一致的良率与工艺控制
[](/zh-hans/semiconductor/process-quality-solutions/run-to-run-control/)#### Run-to-Run Control
通过提升设备以及工艺的性能改善良率
[](/zh-hans/semiconductor/process-quality-solutions/spc/)#### SPC
结合数据信息的提取与分析，提供智能决策
[](/zh-hans/semiconductor/process-quality-solutions/fault-detection/)#### Fault Detection
最大限度降低良率损失，减少计划外设备停机
[](/zh-hans/semiconductor/process-quality-solutions/recipe-management/)#### Recipe Management System
通过自动化配方管理保持一致性
[](/zh-hans/semiconductor/process-quality-solutions/equipment-automation/)#### Equipment Automation
提高生产效率，减少人为错误，实现超越手动基础的全自动化可能性
[](/zh-hans/semiconductor/process-quality-solutions/asset-trace/)#### Asset Trace
通过整个生命周期的资产追踪提高资产利用率
[](/zh-hans/semiconductor/process-quality-solutions/maintenance-management/)#### Maintenance Management
提高设备维护能力——应对计划内和计划外事件
## SmartFactory 生产效率解决方案
以最小资源投入，实现产能与效率最大化。
[](/zh-hans/semiconductor/productivity-solutions/real-time-scheduling-reporting/)### Real Time Scheduling & Reporting
使用先进规则的实时策略减少生产变异
[](/zh-hans/semiconductor/productivity-solutions/fullauto/)### FullAuto
通过实时的、基于事件的工作流消除生产空窗期
[](/zh-hans/semiconductor/productivity-solutions/advanced-scheduling/)### Advanced Scheduling
通过预测排程提高关键瓶颈区的生产效率
[](/zh-hans/semiconductor/productivity-solutions/production-control/)### Production Control
在不扰乱生产的前提下，提升在制品 (WIP) 的产出和产能利用率
[](/zh-hans/semiconductor/productivity-solutions/rtd/)### RTD
无需复杂编程即可识别并实施生产改进
[](/zh-hans/semiconductor/productivity-solutions/activity-manager/)### Activity Manager
采用完全集成的自动化工作流框架，提高资源利用率和生产效率
[](/zh-hans/semiconductor/productivity-solutions/fusion/)### Fusion
提高仿真模型的准确性，在部署到生产环境之前量化因生产规则变更而造成的影响
[](/zh-hans/semiconductor/productivity-solutions/simulation-autosched/)### Simulation AutoSched
实现更好的决策和快速分析
[](/zh-hans/productivity-solutions/material-control/)### Material Control
实现在制品 (WIP) 生产运行自动化，提升整体产出及降低设备闲置时间
# 生产效率解决方案：实现更高的工厂产出和利用率
### 在制造过程中驱动高效、高吞吐量的工厂运营
[](/zh-hans/semiconductor/productivity-solutions/real-time-scheduling-reporting/)#### Real Time Scheduling & Reporting
使用先进规则的实时策略减少生产变异
[](/zh-hans/semiconductor/productivity-solutions/fullauto/)#### FullAuto
通过实时的、基于事件的工作流消除生产空窗期
[](/zh-hans/semiconductor/productivity-solutions/advanced-scheduling/)#### Advanced Scheduling
通过预测排程提高关键瓶颈区的生产效率
[](/zh-hans/semiconductor/productivity-solutions/production-control/)#### Production Control
在不扰乱生产的前提下，提升在制品 (WIP) 的产出和产能利用率
[](/zh-hans/semiconductor/productivity-solutions/activity-manager/)#### Activity Manager
采用完全集成的自动化工作流框架，提高资源利用率和生产效率
[](/zh-hans/semiconductor/productivity-solutions/rtd/)#### RTD
无需复杂编程即可识别并实施生产改进
[](/zh-hans/semiconductor/productivity-solutions/fusion/)#### Fusion
提高仿真模型的准确性，在部署到生产环境之前量化因生产规则变更而造成的影响
[](/zh-hans/semiconductor/productivity-solutions/simulation-autosched/)#### Simulation AutoSched
实现更好的决策和快速分析
[](/zh-hans/semiconductor/productivity-solutions/material-control/)#### Material Control
实现在制品 (WIP) 生产运行自动化，提升整体产出及降低设备闲置时间
## SmartFactory 供应链解决方案
强化供应链管理，提升规划能力、执行效能与整体绩效。
[](/zh-hans/semiconductor/supply-chain-solutions/enterprise-planning/)### Enterprise Planning
提升产能规划的准确性，并更快速地响应客户的预测变化
[](/zh-hans/semiconductor/supply-chain-solutions/production-control/)### Production Control
不干扰生产运营的情况下，快速执行假设场景的逻辑判断以提高在制品 (WIP) 产量和产能利用率
[](/zh-hans/semiconductor/supply-chain-solutions/simulation-automod/)### Simulation AutoMod
通过强大的三维仿真建模，在设备的整个使用寿命中不断提高生产效率
# 提升制造全流程中的计划与生产管控绩效
### 跨工厂规划、控制并模拟供应链决策的影响
[](/zh-hans/semiconductor/supply-chain-solutions/enterprise-planning/)#### Enterprise Planning
提升产能规划的准确性，并更快速地响应客户的预测变化
[](/zh-hans/semiconductor/supply-chain-solutions/production-control/)#### Production Control
不干扰生产运营的情况下，快速执行假设场景的逻辑判断以提高在制品 (WIP) 产量和产能利用率
[](/zh-hans/semiconductor/supply-chain-solutions/simulation-automod/)#### Simulation AutoMod
通过强大的三维仿真建模，在设备的整个使用寿命中不断提高生产效率
## SmartFactory 博客
了解自动化专家如何运用 SmartFactory 自主解决方案实现制造转型
##### [半导体行业博客](/zh-hans/semiconductor-blog/)
## SmartFactory 活动
携手我们的自动化专家团队，快速实现智能制造优势
##### [半导体行业活动](/zh-hans/semiconductor-events/)
[](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)#### Wafer Substrate
Reliable, production‑grade MES for ingot and wafer environments—supporting crystal growth, wafering operations, and upstream production workflows with consistency and control.
[](/semiconductor/manufacturing-execution-solutions/300works-full-auto/)#### Wafer Fab
Execute advanced wafer manufacturing with consistency and control–supporting complex operations across tools, processes, and production flows.
[](/semiconductor/manufacturing-execution-solutions/mesforatp/)#### Test & Assembly
Maintain consistent execution across variable test and assembly environments–adapting to changing product mixes and volumes without disrupting factory performance.
[](/semiconductor/classic-mes/)#### Classic MES
Run established factory operations on proven MES foundations—supporting critical manufacturing environments with stability and depth at scale.
---
### [クラシックMES（Classic MES）](https://appliedsmartfactory.com/manufacturing-execution-solutions/classic-mes/)
**Published:** April 10, 2026
**Author:** Sushmita Kumari
**Content:**
# **クラシックMES（Classic MES）**
クラシックMESソリューションは、半導体メーカーから長年にわたり信頼されてきた、確立された製造実行システム（MES）プラットフォームを指します。これらのシステムは、実績に裏打ちされた実行基盤を提供し、安定性・信頼性・機能の深さが重視される大規模生産オペレーションを支えています。多くの顧客が、これらのプラットフォームを製造環境の中核コンポーネントとして現在も活用しています。
[](/ja/semiconductor/manufacturing-execution-solutions/promis/)### MES PROMIS®
ファブ運用のモデリング機能により、効率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
量産時における改善を加速するための拡張機能
を搭載
[](/ja/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
FACTORYworksプラットフォームに、半導体組立や周辺業界向けの機能を追加
[](/ja/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
プログラミング不要で、独自のビジネスルールを実装可能
[](/ja/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### Alarm Management
アラートノイズを削減し、運用効率を向上
[](/ja/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
システム障害の検知と予測を実現
---
### [テスト & 組立](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **テスト & 組立**
変動の大きいテストおよび組立環境においても一貫した実行を維持することで、製品ミックスや生産数量の変化に柔軟に対応しながら、工場パフォーマンスへの影響を最小限に抑えます。
[](/ja/manufacturing-execution-solutions/mesforatp/)### MES ソリューション
MES for ATP
半導体後工程向けに最適されたMES
---
### [ウェハーファブ](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **ウェハーファブ**
装置、プロセス、製造フローにまたがる高度で複雑なオペレーションを支えながら、一貫性と制御性の高い高度なウェハー製造を実現します。
[](/ja/manufacturing-execution-solutions/300works-full-auto/)### MES ソリューション
MES 300works® Full-Auto
工場のモノの流れを自動化し、大量生産を効率化
---
### [ウェハー基板](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-substrate/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **晶圆基板**
适用于晶锭与晶圆制造环境的、可靠的、生产级制造执行系统 (MES) ——以一致性和可控性支持晶体生长、晶圆加工及上游生产流程。
[](/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)### MES Blog
Manufacturing discipline starts at the substrate: Why execution can’t wait for the fab
Front-end execution increasingly determines semiconductor outcomes
---
### [生产效率解决方案](https://appliedsmartfactory.com/productivity-solutions/)
**Published:** October 12, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory 生产效率解决方案
以最小资源投入，实现产能与效率最大化。
[](/zh-hans/semiconductor/productivity-solutions/real-time-scheduling-reporting/)### Real Time Scheduling & Reporting
使用先进规则的实时策略减少生产变异
[](/zh-hans/semiconductor/productivity-solutions/fullauto/)### FullAuto
通过实时的、基于事件的工作流消除生产空窗期
[](/zh-hans/semiconductor/productivity-solutions/advanced-scheduling/)### Advanced Scheduling
通过预测排程提高关键瓶颈区的生产效率
[](/zh-hans/semiconductor/productivity-solutions/production-control/)### Production Control
在不扰乱生产的前提下，提升在制品 (WIP) 的产出和产能利用率
[](/zh-hans/semiconductor/productivity-solutions/rtd/)### RTD
无需复杂编程即可识别并实施生产改进
[](/zh-hans/semiconductor/productivity-solutions/activity-manager/)### Activity Manager
采用完全集成的自动化工作流框架，提高资源利用率和生产效率
[](/zh-hans/semiconductor/productivity-solutions/fusion/)### Fusion
提高仿真模型的准确性，在部署到生产环境之前量化因生产规则变更而造成的影响
[](/zh-hans/semiconductor/productivity-solutions/simulation-autosched/)### Simulation AutoSched
实现更好的决策和快速分析
[](/zh-hans/productivity-solutions/material-control/)### Material Control
实现在制品 (WIP) 生产运行自动化，提升整体产出及降低设备闲置时间
# 生产效率解决方案：实现更高的工厂产出和利用率
### 在制造过程中驱动高效、高吞吐量的工厂运营
[](/zh-hans/semiconductor/productivity-solutions/real-time-scheduling-reporting/)#### Real Time Scheduling & Reporting
使用先进规则的实时策略减少生产变异
[](/zh-hans/semiconductor/productivity-solutions/fullauto/)#### FullAuto
通过实时的、基于事件的工作流消除生产空窗期
[](/zh-hans/semiconductor/productivity-solutions/advanced-scheduling/)#### Advanced Scheduling
通过预测排程提高关键瓶颈区的生产效率
[](/zh-hans/semiconductor/productivity-solutions/production-control/)#### Production Control
在不扰乱生产的前提下，提升在制品 (WIP) 的产出和产能利用率
[](/zh-hans/semiconductor/productivity-solutions/activity-manager/)#### Activity Manager
采用完全集成的自动化工作流框架，提高资源利用率和生产效率
[](/zh-hans/semiconductor/productivity-solutions/rtd/)#### RTD
无需复杂编程即可识别并实施生产改进
[](/zh-hans/semiconductor/productivity-solutions/fusion/)#### Fusion
提高仿真模型的准确性，在部署到生产环境之前量化因生产规则变更而造成的影响
[](/zh-hans/semiconductor/productivity-solutions/simulation-autosched/)#### Simulation AutoSched
实现更好的决策和快速分析
[](/zh-hans/semiconductor/productivity-solutions/material-control/)#### Material Control
实现在制品 (WIP) 生产运行自动化，提升整体产出及降低设备闲置时间
---
### [关于 SmartFactory](https://appliedsmartfactory.com/about/)
**Published:** February 24, 2025
**Author:** Applied Smartfactory
**Content:**
我们
# **推动制造业
转型升级**
全球自动化专家
超过 0 名
以上生产效率与质量提升经验
0 年
全球支持服务
x7
过去 35 年多来，我们的创新技术彻底改变了制造业的运作模式和人机交互方式。SmartFactory 产品组合提供集成自动化软件解决方案，助力企业实现效能跃升与卓越运营。
### 创新加速引擎
我们提供生产力提升、工艺质量改进、制造执行系统 (MES) 集成及供应链管理等服务——从企业规划到生产控制全覆盖。
通过 AI 驱动的自动化与先进排程技术，制造商可提升运营绩效、优化生产排程、减少停机时间并实现持续改进。我们的整体解决方案实现全流程无缝监控与管控。
### 未来智造蓝图
我们在制造自动化领域的专业积累，正推动 AI、大数据和云计算技术的突破性应用，助力制造商赢得显著竞争优势。
全球顶尖智造智库——愿景者、工程师与科学家团队汇聚在应用材料公司，凭借材料工程领域的专业积淀，以多元观点、丰富经验和不同背景碰撞出更优创意，共同成就突破性创新。
### 自动化现代化改造
SmartFactory 支持一种实用、渐进式的自动化现代化改造方法。制造商可以通过可控的步骤逐步提升绩效——在此过程中降低风险，同时取得可衡量的成果。
这种方法使得现代化改造的进度能够与业务优先级、运营就绪状态和长期目标保持一致，避免了大规模、一次性全面转型所带来的混乱。
## 行业专家洞察
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)### Quality Quest: Insights from the Fab
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)### Performance Pioneers: Factory Innovations
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)### Smart Manufacturing: The Evolutionary Edge
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)### SPC Strategies: Realizing Excellence
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)### MES Integration: Uniquely SmartFactory
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)### Human-Centric Solutions: SmartFactory’s Approach
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)### Innovation Integration: Seizing New Opportunities
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)### Efficiency Unleashed: Optimizing the Fab
### SmartFactory 因卓越贡献荣获表彰
#### Award of Excellence
#### STMicroelectronics Award
#### Best Cooperative Supplier
#### Excellent Supplier
---
### [Fault Detection](https://appliedsmartfactory.com/process-quality-solutions/fault-detection/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Fault Detection
# エクスカーションによる歩留まり損失を最小限にする
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## 工場内のエクスカーションをどのように減らしますか？
SmartFactory Fault Detection は、センサーやイベントをパフォーマンス指標と照らし合わせて監視することで、装置の問題を迅速に検出するプロセス制御ソリューションです。これにより、装置の稼働率が向上し、スクラップが削減されます。多くのスタンドアロンシステムがリアクティブな手法に依存しているのに対し、SmartFactory Fault Detection は、プロセス出力に影響を与える前に装置の問題をプロアクティブかつ迅速にフィードバックします。
## SmartFactory Fault Detection を選ぶ理由
### 装置およびプロセスにおける誤警報を90%削減
### スクラップ材料を95%以上削減
### 突発的な装置停止時間を25時間以上削減
## 私たちの取り組みから得られる効果
### ファブのKPI向上
- 問題を根本から検出し、ファブを保護
- これまで検出できなかった問題も検出可能
- 分析とレポートによるファブの継続的な監視
### 実用的な情報提供
- 故障が発生する前に予測し、修理を事前にスケジューリング
- 操業や装置停止の予測性を向上
- 誤検出を排除し、保守イベントを容易に処理できる高度なデータフィルタリングを提供
### 統合プラットフォーム
- Run-to-Run、SPC、レシピ管理との共通プラットフォーム統合により情報共有を促進
- プロセス装置、計測装置、製造データのAPCコンポーネント間での統合を支援
---
### [供应链解决方案](https://appliedsmartfactory.com/supply-chain-solutions/)
**Published:** October 12, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory 供应链解决方案
强化供应链管理，提升规划能力、执行效能与整体绩效。
[](/zh-hans/semiconductor/supply-chain-solutions/enterprise-planning/)### Enterprise Planning
提升产能规划的准确性，并更快速地响应客户的预测变化
[](/zh-hans/semiconductor/supply-chain-solutions/production-control/)### Production Control
不干扰生产运营的情况下，快速执行假设场景的逻辑判断以提高在制品 (WIP) 产量和产能利用率
[](/zh-hans/semiconductor/supply-chain-solutions/simulation-automod/)### Simulation AutoMod
通过强大的三维仿真建模，在设备的整个使用寿命中不断提高生产效率
# 提升制造全流程中的计划与生产管控绩效
### 跨工厂规划、控制并模拟供应链决策的影响
[](/zh-hans/semiconductor/supply-chain-solutions/enterprise-planning/)#### Enterprise Planning
提升产能规划的准确性，并更快速地响应客户的预测变化
[](/zh-hans/semiconductor/supply-chain-solutions/production-control/)#### Production Control
不干扰生产运营的情况下，快速执行假设场景的逻辑判断以提高在制品 (WIP) 产量和产能利用率
[](/zh-hans/semiconductor/supply-chain-solutions/simulation-automod/)#### Simulation AutoMod
通过强大的三维仿真建模，在设备的整个使用寿命中不断提高生产效率
---
### [SmartFactory Defect Source](https://appliedsmartfactory.com/process-quality-solutions/defect-source/)
**Published:** June 4, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory Defect Source
# Accelerate root cause analysis and minimize equipment downtime
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How can semiconductor manufacturers identify the source of an out-of-control event faster?
SmartFactory Defect Source uses AI to troubleshoot Out-of-Control (OOC) defect events in semiconductor manufacturing. By automatically identifying defect source layers, it helps engineers accelerate root cause analysis and reduce manual troubleshooting.
## Why choose SmartFactory Defect Source?
SmartFactory Defect Source helps teams make faster decisions, reduce engineering effort, and shorten equipment stop-loss time during defect investigations.
**Proven production results include:**
### 50%+ reduction in time-to-decision for defect source identification.
### Hours-to-seconds improvement for automated defect source ID and root cause analysis triggered by OOC events.
#### 90% reduction in manual troubleshooting effort for yield engineers.
## What can you gain from our approach?
## Faster root cause analysis
- Reduces the delay between detection and investigation.
- Provides quick insight into where to focus corrective action.
## More efficient use of engineering resources
- Reduces reliance on manual troubleshooting and expert-only workflows.
- Helps preserve knowledge that is often held by a few experienced engineers.
- Enables engineers to work through an intuitive, web-based troubleshooting storyline without requiring data science expertise.
## Better use of existing manufacturing data and systems
- Builds on top of existing DMS investments rather than replacing them.
- Integrates with systems such as Klarity, Discover, and in-house solutions using standard protocols and file types including KLARF and TIFF.
- Combines inspection and review data from AOI, SEM, TEM, and wafer maps to provide more comprehensive defect analysis.
---
### [SmartFactory Defect Classification](https://appliedsmartfactory.com/process-quality-solutions/defect-classification/)
**Published:** May 12, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory Defect Classification
# Replace manual and rule-based defect classification
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How do semiconductor manufacturers detect and classify defects in real time with high accuracy?
SmartFactory Defect Classification is a production proven, AI based solution that automatically detects and classifies inspection images into 100+ defect categories in semiconductor manufacturing. By replacing manual and rule based defect review, the solution improves classification accuracy, reduces cycle time, and enables consistent, scalable defect decisions across development, ramp, and high volume production.
## Why choose SmartFactory Defect Classification?
SmartFactory Defect Classification is designed for production scale deployment and addresses the limitations of manual and rules based defect classification systems.
**Proven production results include:**
### 0.3–1% yield recovery directly contributing to top-line revenue
### Up to 90% reduction in person-to-machine ratios
### Approximately 26% faster inspection-to-decision cycle time
These results enable manufacturers to improve operational consistency while reducing reliance on manual review.
## What can you gain from our approach?
## Production-scale automation
How SmartFactory Defect Classification automates defect classification at production scale:
- SmartFactory Defect Classification automatically classifies inspection defects with greater than 90% automation, minimizing manual review effort.
- The solution maintains a reported 0% escape rate, ensuring defects are consistently identified before downstream processing.
- SmartFactory Defect Classification achieves greater than 97.5% accuracy across all defect classes in production environments, improving classification reliability.
## Improved yield and cycle time
Automated defect classification improves manufacturing yield and inspection throughput.
- SmartFactory Defect Classification helps recover measurable yield by enabling earlier, more consistent defect detection and disposition.
- The solution shortens defect review queues, reducing inspection to decision cycle time during development, ramp, and high volume manufacturing.
- SmartFactory Defect Classification improves inspection tool utilization, allowing manufacturers to defer or avoid additional scan tool capital expenditure.
## Fab-wide intelligence through integration
How defect classification data is operationalized across the factory:
- SmartFactory Defect Classification feeds defect results directly into yield analysis, disposition, and engineering workflows.
- The solution integrates with SPC, FDC, and Run-to-Run Control systems to provide consistent defect context across quality and process control functions.
- SmartFactory Defect Classification enables closed loop process control and faster root cause analysis by connecting inspection results to downstream corrective actions.
# From defect detection to actionable process improvement
By combining AI driven defect classification with tight integration across fab systems, SmartFactory Defect Classification helps manufacturers move from defect detection to faster, more informed process decisions. The result is higher classification accuracy, reduced manual effort, and more effective use of defect data to support yield improvement, process control, and continuous manufacturing optimization.
---
### [PROMIS](https://appliedsmartfactory.com/manufacturing-execution-solutions/promis/)
**Published:** October 5, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES PROMIS®
# 進化し続けるビジネスニーズに柔軟な対応を実現
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 最近、PROMISをご覧になりましたか？
SmartFactory MES PROMISは、製造品質と生産性を向上させる最新機能、新しい連携のためのオプション、ユーザーインターフェースの強化など、常に進化を続ける製造実行システム（MES）です。現在ご利用中のPROMISが最新バージョンでない場合でもアップグレードサービスをご提供し、豊富なMES基本機能、アウト・オブ・ボックスな新機能、効率的なファブ運用のための構成設定を活用できるようご支援いたします。
## SmartFactory MES PROMISを選ぶ理由
### 工程プロセスの更新作業に必要な工数を80%削減
### 工程プロセスの維持作業に必要な工数を85%削減
### 新機能と新ルールの活用により、PROMISのカスタマイズを90%以上削減
## 私たちの取り組みから得られる効果
### 定期的な機能強化
- 主要オペレーションの大幅な改善を実現
- キーユーザーの生産性を大幅に向上させる機会を逃さない
- 機能アップデートにより防止可能なミスを減らし、廃棄の発生を抑制
### ユーザーエラーの削減
- リワークやプロセス管理で発生する一般的なミスを削減
- よくある一般的なモデリングミスによる廃棄リスクの削減
- コードに手を加えることなく、PROMISの動作をその場で柔軟にカスタマイズ可能
### 実績ある信頼性
- 世界270以上の半導体・精密電子機器メーカーで導入されたMESの実績
- 高い稼働率を維持しながら、冗長性と定期的なアップグレードを実現する専門チームのノウハウを活用
---
### [PROMIS](https://appliedsmartfactory.com/manufacturing-execution-solutions/promis/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES PROMIS™
# 适用于不断变更的业务需求
## 您最近关注过PROMIS吗？
SmartFactory MES PROMIS是一套制造执行系统，为提高生产质量和生产效率持续提供更新功能、新集成选项并增强用户界面。 如果您不再使用当前版本的PROMIS，我们可以为您提供升级服务，以便您可以使用丰富的MES系统功能，开箱即用功能和高效的晶圆厂运行模块。
## 为什么选择SmartFactory MES PROMIS？
### 保持在制品（WIP）更新流程的工作量减少80%
### 维护更新流程的工作量减少85%以上
### 通过使用新功能和新规则来消除90%以上的PROMIS定制
## 您能从我们的解决方案中获得什么？
## 常规增强
- 改进主要的运营工作
- 为关键用户极大地提高生产效率
- 减少由于可以通过更新预防的失误造成的损耗
## 减少用户失误
- 消除返工和制程管理中常见错误的风险
- 通过最小化定制，消除由于某些类型的常见建模错误而产生的损耗
- 客制PROMIS行为无需修改代码——动态操作
## 经过验证的可靠性
- 这套MES系统在全球270多家半导体和精密电子制造商得到广泛验证
- 在保证冗余和定期升级的同时，在不损失生产时间的情况下，获得尽可能高的正常运行时间的团队经验
---
### [Monitor](https://appliedsmartfactory.com/manufacturing-execution-solutions/monitor/)
**Published:** October 8, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Monitor
# システム障害を検知・予測し、ダウンタイムの発生を防止
[ Watch Video ](/semiconductor-blog/manufacturing-execution/smartfactory-monitor/)
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 工場システムの動作が遅延したり、停止したりしていませんか？
中規模の半導体工場では、わずか1時間の突発的なダウンタイムで10万ドルもの損失が発生することもあります。こうした損失を未然に防ぐため、「SmartFactory Monitor」は、システム障害や予期せぬ停止を予測するための監視機能を提供します。
このソリューションは、リアルタイム監視と予測分析アルゴリズムを活用し、ソフトウェアシステム全体を常時見守ることで、将来の製造現場での異常・
トラブルの予測や、システムパフォーマンスの最適化のための知見を提供します。
## SmartFactory Monitorを選ぶ理由
### 予想せぬダウンタイムの削減
### システム障害や応答遅延の低減
### 平均修復時間（MTTR）の短縮
## 私たちの取り組みから得られる効果
### より深い洞察
- データベース、サーバー、製造アプリケーションから重要な指標を収集
- 最適化されたアラートを設定し、実用的な知見を提供
- イベントを重大度で分類・優先順位付けし、根本原因を即座に特定
### より高精度な予測
- 高度な分析で将来のイベントを予測し、ダウンタイムを削減
- 機械学習による生産データ分析で障害を予測し、パフォーマンスダッシュボードに結果を集約
- アラームに基づいて予防的な対応を行い、問題を事前に解決
### より広範なカバレッジ
- 経験豊富なグローバルチームによる24時間365日の監視体制で、生産の安定性・高可用性を維持
- 世界中のデータベース、アプリケーション、OS、ネットワークの監視サポートに対応
---
### [Monitor](https://appliedsmartfactory.com/manufacturing-execution-solutions/monitor/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Monitor
# 检测和预测系统故障
## 您的工厂系统是否存在减速或失灵的问题？
在一个中型晶圆厂中，仅仅一个小时的计划外停机就相当于10万美元的损失。 为了防止这种损失，具备生产监控功能的SmartFactory Monitor套件，可以巡视您的软件系统，预测系统故障和计划外停机。 通过在设备运行时进行监控和预测分析算法，该解决方案优化了系统性能，并为预测晶圆厂未来事件提供洞察。
## 为什么选择SmartFactory Monitor？
### 减少计划外停机
### 减少系统故障和缩短响应时间
### 缩短平均修复时间（MTTR）
## 您能从我们的解决方案中获得什么？
## 更好的洞察力
- 从数据库、服务器和生产应用程序中收集关键指标
- 设置优化的警报，获得可操作的洞察力
- 按严重程度对故障进行整理和优先级排序，以迅速识别根本原因
## 更好的预测
- 使用先进分析软件预测未来事件，以减少停机时间
- 使用机器学习获得的生产数据来预测故障，并在数字化面板上总结性能情况
- 根据警报采取预防措施，提前解决问题
## 更好的覆盖
- 经验丰富的全球团队为用户提供7x24小时支持服务，监控生产并保障设备性能、稳定性和高可用性
- 访问全球数据库、应用程序、操作系统和网络监控
---
### [FACTORYworks+](https://appliedsmartfactory.com/manufacturing-execution-solutions/factoryworks-plus/)
**Published:** October 5, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FACTORYworks+™
# 迅速な導入を実現するアウト・オブ・ボックス型MES
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 新工場で大量生産を開始するまで、どれくらいの時間がかかりますか？
SmartFactory MES FACTORYworks+は、半導体後工程および関連業界向けに開発された、アウト・オブ・ボックス型製造実行システム（MES）です。当社の実績あるFACTORYworksプラットフォームを基盤に、初期生産立ち上げを90日以内で実現するための機能を追加し、迅速な導入を可能にします。
## SmartFactory MES FACTORYworks+を選ぶ理由
### 大量生産の実現における生産効率の向上
### 品質向上と運用コストの削減を同時に実現
### 90日以内のスピード導入が可能
## 私たちの取り組みから得られる効果
### 柔軟なカスタマイズ性
- 最適化されたカスタマイズ
- お客様の製造シナリオに最適化されたモジュールの
カスタマイズ
- 各拠点固有のデータ要件に対応するFACTORYworksスキーマのカスタマイズ
### 高度な統合制御
- 保全管理、装置自動化、スケジューリングなど、他のSmartFactory CIMモジュールとの容易な統合
- ERPや倉庫管理システムなど、サードパーティ製
アプリケーションとの連携が簡単
### 優れたスケーラビリティ
- 既存の工場制御システムを拡張し、高度な製造レベルを実現
- 小規模なハードウェア構成からスタートし、ビジネスの成長に合わせて水平展開が可能
- 工場の拡張、複数工場・複数ラインの管理にも柔軟に対応
---
### [FACTORYworks+](https://appliedsmartfactory.com/manufacturing-execution-solutions/factoryworks-plus/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FACTORYworks+™
# 打破陈规思考如何实现更快地部署
## 您的新工厂多快能实现大批量生产？
SmartFactory MES FACTORYworks+是为半导体后道和半导体相关行业设计的即用型制造执行系统。 在领先的FACTORYworks平台的支持下，MES FACTORYworks+提供了快速实施和开箱即用功能，可在90天内实现首次投产。
## 为什么选择SmartFactory MES FACTORYworks+？
### 更高效地实现大批量生产
### 提高产品质量，降低运营成本
### 在90天内完成部署
## 您能从我们的解决方案中获得什么？
## 更好地定制化
- 定制模块以满足您的生产场景需求
- 自定义操作场景逻辑
- 为特定站点的数据需求定制FACTORYworks模式
## 集成控制
- 易于与其他SmartFactory CIM模块集成，包括维护管理、设备自动化和调度
- 与第三方应用程序轻松集成，包括EPR和仓库管理系统
## 更好的可伸缩性
- 扩展现有工厂控制系统以管理更高的生产水平
- 从小的硬件占用开始，然后随着业务的增长水平扩展
- 轻松处理跨工厂、多产线的工厂扩展
---
### [FACTORYworks](https://appliedsmartfactory.com/manufacturing-execution-solutions/factoryworks/)
**Published:** October 4, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FACTORYworks®
# オペレーションの自動化で、 さらなる効率化を実現
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 現在のMESは、大きく増大した生産規模に対応できるスケーラビリティを備えていますか？
SmartFactory MES FACTORYworksは、高度に自動化された製造オペレーションを実現する統合化された安定性の高い製造実行システム（MES）です。柔軟な構成設定と優れたスケーラビリティを特長とし、半導体前工程・後工程、ディスプレイ、ディスクリート製造など、さまざまな業界で実績を持つ信頼のソリューションです。
## SmartFactory MES FACTORYworks を選ぶ理由
### 高い信頼性と一貫した安定性
### 所有コストを削減するため様々なプラットフォームに対応
### 世界中のミッションクリティカルな現場での豊富な導入実績
## 私たちの取り組みから得られる効果
### 効率の向上
- オペレーターの誤操作の排除
- 材料不足や在庫過多を削減
- Applied製アプリケーションとの事前統合により、 統合工数を削減
- 市場や工場の状況変化への迅速な対応
### 拡張機能の開発
- 特別な機能やビジネスルール、外部システム連携のための拡張開発が可能
- ルール開発環境を活用して、固有の業務オぺーレーションの構築が可能
- 提供されるビジネスルールをコンパイル不要で置換・拡張可能
### マルチサイト対応
- 工場拡張や複数の工場、極端なスループットが要求されるラインの管理に対応
- 複数工場間での生産監視・制御を実現
- 拠点間での資材移動や重要リソースの共有が可能
---
### [FACTORYworks](https://appliedsmartfactory.com/manufacturing-execution-solutions/factoryworks/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FACTORYworks™
# 自动化操作以提高效率
## 您的MES系统是否可扩展以支持极端的生产需求？
SmartFactory MES FACTORYworks是一套完全集成的、稳定的制造执行系统，管理高度自动化的生产运营。 FACTORYworks以其可配置的建模和可扩展性而闻名，在半导体前道、后道、显示和分立制造方面均得到验证，拥有长期、成功的跟踪记录。
## 为什么选择SmartFactory MES FACTORYworks？
### 高可靠性和稳定性
### 多平台支持，降低拥有成本
### 在全球的重要应用任务中得到验证
## 您能从我们的解决方案中获得什么？
## 提高效率
- 消除运营错误流程
- 减少物料短缺和实际库存
- 通过使用应用材料公司的预集成应用程序减少集成工作
- 提高对变化的市场和工厂条件的响应时间
## 延伸部署
- 为特殊功能、业务规则和外部系统集成开发扩展
- 使用规则开发环境构建自定义操作
- 无需编译即可替换和扩展所提供的业务规则
## 多站点支持
- 处理工厂扩展，多工厂和多产线的极端产出需求
- 监控和控制多个工厂的生产
- 在站点之间移动材料和共享关键资源
---
### [FAB300](https://appliedsmartfactory.com/manufacturing-execution-solutions/fab300/)
**Published:** October 6, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FAB300®
# 需要に応じたスケールアップ＆スケールアウト
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 現在のMESは、大量生産と頻繁な更新に対応できていますか？
SmartFactory MES FAB300は、柔軟に構成・拡張可能なワークフローエンジンを備えたファブ管理システムです。ビジネスプロセスの変更を「数か月」ではなく「数日」で実現可能にします。月間30万枚の300mmウェーハ投入（WSPM）をサポートする実績を持ち、大量生産の立ち上げにおいて、短期間・低リスク・低コストでのスケーリングを可能にします。
## SmartFactory MES FAB300を選ぶ理由
### 他の工場システムとの容易な統合
### 月間30万枚のウェーハ投入をサポート
### ゼロダウンタイムでの運用を実現
## 私たちの取り組みから得られる効果
### 高い効率性
- プログラミング不要で、独自の運用ルールをワークフローとして実装
- ゼロダウンタイムでローリングアップグレード実施可能
- 単一ノード障害時も迅速に復旧し、稼働を継続
### 生産性の向上
- システム管理を簡素化し、安全かつ低コストな自動化を実現
- ファブプロセスの制御力を強化
- サイクルタイムを短縮し、スループットを向上
### 優れた適応性
- SmartFactoryモジュールやサードパーティ製アプリケーションと容易に統合し、トータルファクトリーソリューションを構築
- 標準コンポーネントに基づく単一環境で、工場のビジョンを実現
- 知的財産（IP）をデータとして保持し、ワークフローモデル内で管理。コードとは分離されているため、容易に保護することが可能
---
### [FAB300](https://appliedsmartfactory.com/manufacturing-execution-solutions/fab300/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FAB300™
# 扩大规模以满足需求
## 您的MES系统满足高产量良率和变更需求吗？
SmartFactory MES FAB300是一个Fab管理系统，提供可配置和可扩展的工作流引擎，简化业务流程的快速变更，只需几天而不是几个月即可完成部署。 经过验证，FAB300可支持300mm晶圆厂每月投片量（WSPM）达30万片，使制造商能够扩大规模，以满足大批量生产的要求，所有这些都可以在更短的时间内完成，风险更低，成本更低。
## 为什么选择SmartFactory MES FAB300？
### 易于与工厂的其他应用程序集成
### 支持每月晶圆投片量达30万片
### 近零停机
## 您能从我们的解决方案中获得什么？
## 更高效
- 无需编程即可通过工作流程实施专有操作
- 在几乎不停机的情况下滚动执行升级任务
- 如果单个站点发生故障，恢复所需的时间接近于零
## 更高的生产效率
- 实施简化的系统管理，从而实现安全性能更高、成本更低的自动化
- 增强对Fab流程的控制
- 缩短生产周期，提高产出
## 更好的适应性
- 与SmartFactory模块或第三方应用轻松集成，实现全面的工厂解决方案
- 使用基于标准组件的单一环境来实现您的工厂愿景
- 您的数据在工作流的模型中得到维护，与代码分开存储，多重防护构建数据安全，保障您的知识产权（IP）
---
### [300works Full-Auto](https://appliedsmartfactory.com/manufacturing-execution-solutions/300works-full-auto/)
**Published:** October 4, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES 300works® Full-Auto
# 次世代製造の実現
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 現在のMESは、完全なCIM対応で300mmに最適化されていますか？
既存のMESソリューションの多くが完全自動化を実現するまでの深みに到達できていません。しかし、SmartFactory MES 300works Full-Autoは、パッケージそのままで導入可能な工場自動化ソリューションで、工場設備全体でモノの流れを最適化します。お客様はCIM（Computer Integrated Manufacturing）における完全自動化に集中しながら、新工場の立ち上げを加速させることができ、製品を市場にタイムリーに投入することが可能になります。
## SmartFactory MES 300works Full-Auto を選ぶ理由
### 導入後、90日以内に初ウェーハ投入を実現
### 設備の待機時間を削減し、生産性を50%向上
### 新設300mmファブの70%以上が300worksをMESに採用
## 私たちの取り組みから得られる効果
### 迅速な導入
- 計画通りの導入と付加価値の向上を実現
- 全フェーズで必要な導入期間最小化しコスト抑えながら、初期導入は90日以内で実現し、製造工程全体の立ち上げは1年以内で完了します。
- そのまま利用可能な豊富なパッケージ機能で導入を迅速化
### 優れた統合性
- 充実したインテグレーション機能により各種SmartFactory CIMアプリケーションや他の周辺システムとの統合を容易に実現
- Applied E3® 装置・プロセス制御プラットフォームと直接連携し、リアルタイムのRun-to-Runチューニングや故障検出を実現し、歩留まりを向上
### 高い拡張性
- 生産規模の増大（例：120K WSPM）や複数工場・ラインへの工場拡張に柔軟に対応
- 顧客固有のニーズに合わせて業務運用をカスタマイズ可能
- 業界共通の製造シナリオをサポートするビジネステンプレートが利用可能
---
### [300works Full-Auto](https://appliedsmartfactory.com/manufacturing-execution-solutions/300works-full-auto/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES 300works™ Full-Auto
# 实现制造企业转型升级
## 您的MES系统是完整的CIM并已做好准备生产300mm晶圆吗？
并非所有MES解决方案都具备实现全自动化所需的深度。SmartFactory MES 300works Full-Auto是一种开箱即用的工厂自动化解决方案，可监控并简化整个生产制造的物料流动。该解决方案允许制造商专注于CIM系统全自动化，同时加速新工厂的坡道，使产品能够按时上市。
## 为什么选择SmartFactory MES 300works Full-Auto？
### 在90天内完成第一批晶圆投产
### 通过减少设备等待时间，提高50%的生产效率
### 70%以上的新300mm晶圆厂选择了300works作为MES解决方案
## 您能从我们的解决方案中获得什么？
## 更快地部署
- 实现按时部署目标及提高增值
- 通过将所有阶段的新产品第一次部署时间缩短至90天及所有阶段的新产品部署时间缩短至1年，从而节约成本
- 使用预构建的、开箱即用的功能进行部署
## 更好地集成
- 与SmartFactory CIM应用程序和其他企业系统轻松集成
- 通过与应用材料公司E3™设备和过程控制平台输出的直接连接，实现实时、批间控制的调谐和故障检测，以提高良率
## 更好地扩展
- 使工厂扩展到大批量生产（例如，120K WSPM）或多个工厂和产线
- 客制化业务操作以满足独特的客户需求
- 使用内置业务模板来支持常见的生产场景
---
### [Asset Trace](https://appliedsmartfactory.com/process-quality-solutions/asset-trace/)
**Published:** October 8, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Asset Trace
# ライフサイクル全体を通じてトレーサビリティを実現し、資産の有効活用を向上
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## 工場内の重要な生産資産、どのように管理していますか？
「耐久財」とは、レチクル、キャリア、プローブカード、ポンプ、バルブ、バーンインボード、ソケット、台車など、ツールのモバイル拡張として機能する資産です。一方、「消耗品」は、ガス、化学薬品、ターゲットなど、生産中に消費される資材です。SmartFactory Asset Traceは、これらの資産の使用状況、保守、ライフサイクルを自動で追跡・監視・最適化することで、スムーズな運用と生産性の最大化を実現する管理ソリューションです。
## SmartFactory Asset Traceを選ぶ理由
### 人的ミス、汚染、材料品質による廃棄を6〜8%削減
### 設備稼働率を3%向上
### 自動化による人件費の削減
## 私たちの取り組みから得られる効果
### トレーサビリティの向上
- 耐久財／消耗品の所在と状態を簡単に把握
- 設備稼働率の向上
- 適切な資産の使用と保守・保管により歩留まりを改善
- 耐久財／消耗品の手動管理の負担を軽減
### シームレスな統合
- MES、MCS、SPC、保守管理、ディスパッチなどの他システムと簡単に連携
- SmartFactory RTDを活用し、リアルタイムの意思決定とWIP（仕掛品）管理を強化し、設備の稼働時間を向上
- SmartFactory SPCを導入することで、プロセス品質を改善し、パフォーマンス統計に好影響を与えながらスクラップ時間を削減
### 状態モデリングの簡素化
- あらゆる耐久財／消耗品のライフサイクルを追跡・管理するための状態モデルを迅速に定義
- プログラミング不要で簡単にモデルを構成
- 自動トリガーによる効率的な運用
---
### [Maintenance Management](https://appliedsmartfactory.com/process-quality-solutions/maintenance-management/)
**Published:** October 6, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Maintenance Management
# 保全計画を最適化し、設備の稼働率を最大化
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 現在のファブでは、保全計画が自動化されていますか？
SmartFactory Maintenance Managementは、装置中心のコンピュータ化保全管理システム（CMMS）であり、計画保全・定期保全・計画保全・計画外保全を効果的に管理します。半導体業界向けに特化して開発されたこのソリューションは、在庫全体の最適化、装置の稼働率向上、そして人件費や部品コストの削減を実現します。
## SmartFactory Maintenance Managementを選ぶ理由
### 半導体装置の階層構造、柔軟な設定、状態モデリングへの対応
### 工場設備の稼働率と効率の向上
### 人件費および部品コストの削減
## 私たちの取り組みから得られる効果
### より良い計画立案
- 保全作業を自動化し、装置や技術者のスケジューリングを簡単に実施
- スプレッドシートや紙のスケジュール表は不要
- モバイルクライアントを使って「現場での」チェックリストを実行し、BKM（ベストナウンメソッド）と初回作業の正確性を確保
### 生産性の向上
- クラスターツール内の個別チャンバー単位で装置状態と作業履歴を追跡
- 稼働中でも性能が低下している装置の可用性を正確に評価
- ダウンタイム、段取り、調整による損失を削減し、資産の可用性を向上
### 高い統合性
- あらゆるMESと統合可能。特に、同一モデル上で動作するFACTORYworks®との親和性が高い
- Applied E3®やAPF RTD®との連携により、必要に応じてWIPの再割り当ても可能
- 予備部品在庫、技術者の追跡・スケジューリングなど、主要な工場システムとの統合も容易
---
### [Maintenance Management](https://appliedsmartfactory.com/process-quality-solutions/maintenance-management/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Maintenance Management
# 优化您的维护计划
## 您工厂的维护计划是自动化的吗？
SmartFactory Maintenance Management是一套以设备为中心的计算机化维护管理系统（CMMS），可以有效地管理计划、排程和计划外的维护。 这套专门为半导体行业开发的解决方案优化了整体库存水平的管理，提高了设备可用性，并降低了人力和零部件成本。
## 为什么选择SmartFactory Maintenance Management？
### 深度访问半导体设备层次结构、可配置性和状态建模
### 提高工厂设备的可用性和效率
### 降低人力和零部件成本
## 您能从我们的解决方案中获得什么？
## 更好的规划
- 维保自动化，可轻松安排您的设备和技术人员
- 消除对电子表格和纸质计划表的依赖
- 通过移动端执行“机台端”维保核检清单，确保BKMs和一次成功
## 更高的生产效率
- 对多腔体设备，可跟踪设备状态和事件到单个腔室
- 即使在降级的状态下也能准确评估设备的可用性
- 通过减少因停机、设置和调整造成的损失，提高资产可用性
## 更好的集成
- 可与任何MES系统集成，特别是在同一模型中工作的FACTORYworks™系统
- 与应用材料公司的E3™和APF RTD™解决方案集成，在需要时支持在制品（WIP）的重新分配
- 与关键工厂系统集成，包括备件库存和技术人员跟踪和调度
---
### [Asset Trace](https://appliedsmartfactory.com/process-quality-solutions/asset-trace/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Asset Trace
# 通过整个生命周期的资产追踪提高资产利用率
## 您是如何管理工厂的关键生产设备？
*耐用设备*本质上是设备的可移动延伸部分，包括光罩、载具、探针卡、泵、阀门、老化测试板、插座、推车等。 而气体、化学品和靶材等消耗品则会在生产过程中被消耗。SmartFactory Asset Trace 解决方案是一套自动化管理系统，可对这些资产的使用、维护及生命周期进行追踪、监控和优化，从而确保生产平稳运行并实现生产力最大化。
## 为何选择 SmartFactory Asset Trace?
### 减少 6-8% 因人为失误、污染和材料质量问题导致的的废品
### 提升 3% 设备利用率
### 通过自动化节省人力间接成本
## 采用我们的解决方案能为您带来什么？
## 更便捷的追溯能力
- 定位耐用品/消耗品及其当前状态
- 实现更高的设备利用率
- 通过正确使用、维护和存储耐用品/消耗品提高良率
- 减少人工追踪耐用品/消耗品的间接成本
## 无缝集成
- 轻松集成 MES、MCS 、SPC、Maintenance Management 和派工等其他工厂系统
- 利用 SmartFactory RTD 促进实时决策和在制品 (WIP) 管理，从而改善设备正常运行时间
- 部署 SmartFactory SPC 提升工艺质量，通过对性能统计数据的积极影响减少报废时间
## 更容易的状态建模
- 快速定义状态模型以追踪和管理任何耐用品/消耗品的生命周期
- 无需任何编程即可轻松配置模型
- 自动触发机制
---
### [Equipment Automation](https://appliedsmartfactory.com/process-quality-solutions/equipment-automation/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Equipment Automation
# 生産性を向上し、人為的ミスを削減
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## マニュアルオペレーションから自動化処理仕組みに切り替えることを検討していますか？
SmartFactory Equipment Automationは、自動化サービスを実行する装置設計および制御フレームワークです。このソリューションは、装置処理の自動化、上位管理システム（MES）との統合および装置データの処理をSEMIスタンダードやカスタマイズで対応より、生産性が向上し、エラーやスクラップの損失が削減されます。
## SmartFactory Equipment Automationを選ぶ理由
### 自動ディスパッチングにより、1日あたりのウェーハ出力が10〜15%向上
### 自動ディスパッチングにより、装置の稼働率が10%向上
### データ記録時間を97%削減
## 私たちの取り組みから得られる効果
### 資産の最適化
- 装置処理自動化シナリオを実行することで、装置資産の稼働を維持
- SmartFactory FullAuto と連携し、マテリアルズの搬送、ロード、処理、アンロードを自動化実現
### エラーの削減
- 品質管理の事前チェックにより、正しい材料が適切なシーケンスやレシピと一致していることを検証
- 品質およびエンジニアリングデータの要件を一貫して満たす
### データの統合
- データ収集記録を適切なアプリケーションに配信し、分析を支援
- 装置のパフォーマンスを分析し、隠れたサイクルタイム損失を特定
- Applied の SmartFactory CIM ソリューションや他社製ソリューションとの統合が可能
---
### [Recipe Management](https://appliedsmartfactory.com/process-quality-solutions/recipe-management/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Recipe Management
# レシピを安全に管理
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## 工場全体に分散する何千ものレシピを、どのように管理していますか？
製造装置のレシピは、企業にとって最も重要な知的財産のひとつです。SmartFactory Recipe Management System（RMS）は、レシピの差分、重複、統合を簡単に確認できる機能を提供し、安全に一元管理されたリポジトリによってレシピの知的財産を保護します。このソリューションは、実行時のレシピとパラメータを検証することで、ラインの歩留まりとトレーサビリティを向上させます。
## SmartFactory Recipe Managementを選ぶ理由
### 人為的ミスによる廃棄を最大50%削減
### 成熟ファブにおけるライン歩留まりを4〜10%向上
## 私たちの取り組みから得られる効果
### レシピ・リポジトリの一元管理
- 冗長性とバージョン管理を備えた安全なリポジトリでレシピを管理
- ツールレシピの誤削除を防ぎ、ビジネス継続性を確保
- 認証や監査に備えたレシピ履歴のトレーサビリティを提供
### レシピ効率の自動化
- 装置の定数やレシピパラメータ値を制御し、誤処理を削減
- 装置の自動化と連携して実行時の検証を自動化し、
ウェーハ出力を向上
### 人為的ミスの削減
- 実行時レシピを仕様と照合して検証し、手戻りや廃棄を最小化
- 誤った手順やパラメータの更新によるエラーを削減
---
### [Run To Run Control](https://appliedsmartfactory.com/process-quality-solutions/run-to-run-control/)
**Published:** September 27, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Run-to-Run Control
# ツールレシピパラメータの
最適化
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## 製造現場でのプロセス能力の課題をどのように解決していますか？
SmartFactory Run-to-Run Controlは、プロセス能力（Cpk）を向上させ、ツールレシピパラメータを最適化する高度なプロセス制御（APC）ソリューションです。この即時導入可能なソリューションは、特許取得済みのモデル予測機能を備えており、多変量・制約付きの最適化ベースのプロセスコントローラを搭載し、実績ある導入事例に裏打ちされた信頼性を誇ります。
## SmartFactory Run-to-Run Controlを選ぶ理由
### 平均30%のCpk向上
### スクラップ発生率を10〜30%削減
### 成熟工程での歩留まりを2〜4%向上
## 私たちの取り組みから得られる効果
### 歩留まりの向上
- プロセス変動を低減
- 開発・立ち上げフェーズでの意思決定を支援
- 量産時の歩留まり低下要因を抑制
### 品質の向上
- ツールレシピパラメータを自動最適化し、Cpkを改善
- 装置やプロセスのドリフトを補正し、規格外（OOS）やスクラップを削減
- パイロットウェーハの削減によりスループットを向上
### 所有コストの削減
- 統一されたモデリング構造によりモデル管理作業を軽減
- SPCやFDCとの統合が可能な共通プラットフォームで情報共有を促進
---
### [Material Control](https://appliedsmartfactory.com/productivity-solutions/material-control/)
**Published:** November 10, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Material Control
# 实现卓越的正常运行性能
## 如果您的工厂停工一小时或仅仅 10 分钟，会造成多大损失？
由物料控制系统（MCS）可靠性问题引起的晶圆厂停机可能会造成数百万美元的损失。 SmartFactory Material Control 以其卓越的正常运行时间而闻名，它是一种实时物料控制系统，可协调晶圆、光罩和 LCD 面板的搬运和存储。 Material Control （CLASS MCS 5）全球部署已超过250套，是半导体和显示器制造领域市场领先的 MCS 解决方案，可提高自动化效率并改善库存控制。
## 为什么选择 SmartFactory Material Control？
### 经验证，正常生产运行时间达 99.99%
### 独立于 AMHS 和 MES 供应商
### 降低内部拥有成本
## 您可以从我们的解决方案中获得什么？
## 紧密集成
- 无需停机即与任何 AMHS 解决方案或多个 AMHS 供应商设备无缝集成
- 使用对外接口与多种平台上标准的或客制化的MES解决方案进行数据通信
- 使用 MCS 开发套件为您自己的工厂扩展定制系统功能
## 高可用性
- 通过快速的失效备援自动切换功能，确保关键组件始终正常运行
- 无需更改软件或停机，即可添加或配置 AMHS 设备
- 独立安装、更新和删除组件，不影响系统的持续运作
## 更高的生产效率
- 基于先进的调度算法，确保选择最佳路径来进行在制品的搬送
- 减少 AMHS 设备搬送次数，降低 AMHS 设备控制复杂度
- 通过丰富的集成日志数据库快速找到搬送问题的根本原因
## Our Insights
[ View All ](https://appliedsmartfactory.com/zh-hans/blog/)
---
### [Material Control](https://appliedsmartfactory.com/productivity-solutions/material-control/)
**Published:** October 7, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Material Control
# 優れた稼働率で、止まらない製造を実現
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 現在のファブでは、1時間、あるいはたった10分でも停止した場合、その損失はどれほどになりますか？
ファブでは、製造制御システム（MCS）の信頼性による稼働中断で、数百万ドル規模の収益損失を引き起こす可能性があります。SmartFactory Material Controlは、ウェーハ、レチクル、LCDパネルの搬送・保管をリアルタイムで制御する、高信頼性のマテリアルコントロールシステムです。世界250件以上の導入実績を誇り、半導体およびディスプレイ製造分野における市場をリードするMaterial Control(CLASS MCS 5)ソリューションとして、優れた自動化効率と在庫管理の最適化を実現します。
## SmartFactory Material Controlを選ぶ理由
### 99.99%の実稼働率の実績
### AMHSおよびMESベンダーに依存しない柔軟な構成
### 内部保有コストの削減を実現
## 私たちの取り組みから得られる効果
### シームレスな統合
- どのAMHSソリューションともスムーズに統合可能
- 標準およびカスタマイズされたMESソリューションと、さまざまなプラットフォーム上で外部インターフェースを通じて通信可能
- MCS開発キットを活用し、工場独自のカスタマイズで機能を拡張可能
### 高可用性
- 重要なコンポーネントの常時稼働を支える高速フェイルオーバー機能
- ソフトウェアの変更やダウンタイムなしでAMHS装置の追加・構成が可能
- システム稼働中でも、コンポーネントのインストール、更新、削除を独立して実行可能
### 生産性の向上
- 高度なスケジューリング・アルゴリズムにより、ロットの目的地までの最適ルートを自動選択し、搬送効率を最大化
- AMHS装置の搬送時間とファブ内のAMHS設置面積を削減
- 統合ログデータベースにより、搬送トラブルの根本原因を迅速に特定
---
### [Simulation AutoSched](https://appliedsmartfactory.com/productivity-solutions/simulation-autosched/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoSched®
# 潜在価値を発見
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## ファブにおける設備の意思決定ロジックをどのようにモデル化していますか？
SmartFactory Simulation AutoSchedは、複雑なワークフローをシミュレーションし、工場内に潜在する未活用または無駄なキャパシティを特定できるキャパシティプランニングシステムです。ファブの仮想モデルを構築して、運用の分析・予測・最適化を行い、スケジューリングルールや装置、作業者のサイクルに関する実験をオフラインで実施することができます。
## SmartFactory Simulation AutoSchedを選ぶ理由
### サイクルタイムの改善
### WIP（仕掛品）およびバッファレベルの削減
### 意思決定ロジックの向上
## 私たちの取り組みから得られる効果
### より優れた実行性能
- オブジェクト指向かつデータ駆動型のモデリングツールを搭載し、商用製品の中で最速の実行性能を実現
- 迅速なモデル開発のための標準機能とディスパッチングルールを提供
### より高い統合性
- AutoMod®と統合可能な唯一の高度な処理パッケージで、詳細かつ正確なモデルを構築
- オープンアーキテクチャにより、あらゆるアプリケーションに対応したカスタマイズが可能
### より豊富な導入実績
- 半導体製造分野で20年以上のシミュレーション経験と425件以上の導入実績を誇る最大規模の導入ベース
- キャパシティプランニングとシミュレーションにおける業界のリーダーとして実証済み
---
### [Simulation AutoSched](https://appliedsmartfactory.com/productivity-solutions/simulation-autosched/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoSched™
# 发现隐藏的价值
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 在您的晶圆厂中，您是如何为设备的决策逻辑建模的？
SmartFactory Simulation AutoSched是一个产能规划系统，它通过仿真模拟复杂的工作流程来识别隐藏的和浪费的工厂产能。 它允许用户创建一个虚拟的晶圆厂模型来分析、预测和优化操作，可以在离线的情况下对调度规则、设备操作和操作周期进行检验。
## 为何选择 SmartFactory Simulation AutoSched？
### 改善生产周期
### 降低在制品（WIP）和缓冲（buffer）等级
### 增强决策逻辑
## 采用我们的解决方案能为您带来什么？
## 更好的执行
- 包括一个面向对象的、数据驱动的建模工具，提供市场在售产品中最快的执行速度
- 包括用于快速模型开发的表征特点和调度规则
## 更好的集成
- 针对构建详细、准确的模型，提供只与AutoMod™集成的高级处理包
- 为客制化的业务提供开放的体系结构，能模拟几乎任何的应用程序
## 更好的体验
- 为半导体行业提供最大的安装量——拥有超过20年的仿真模拟经验和425家以上实际用户的部署经验
- 为人所熟知的产能规划以及仿真模拟领域的领导企业
---
### [Fusion](https://appliedsmartfactory.com/productivity-solutions/fusion/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Fusion
# 量化因规则变更而产生的影响
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 在您的晶圆厂中，您是如何在不影响生产的情况下测试派工规则？
SmartFactory Fusion是针对派工和产能分析的解决方案，无需任何修改，即可在SmartFactory仿真模型中使用SmartFactory派工规则。 它允许用户在生产实施之前量化因规则变更而产生的影响，从而提高模型的准确性。
## 为何选择 SmartFactory Fusion？
### 减少由于不正确的派工规则而导致的停机
### 减少执行规则验证的劳动和工作
### 减少RTD规则开发时间
## 采用我们的解决方案能为您带来什么？
## 降低拥有成本
- 无需为模拟而执行维护单独的调度规则
- 减少重复规则
- 无需对C++进行扩展
## 更好的规则集成
- 将车间规则集成到模拟中
- 对产量和资本支出产生积极影响
## 改进模型的精确性
- 为RTD规则更改提供假设测试环境
- 提供使用本机模拟功能的能力，支持做出更好决策
---
### [Fusion](https://appliedsmartfactory.com/productivity-solutions/fusion/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Fusion
# ルール変更の影響を定量化
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## ファブにおいて、生産に影響を与えずにルールのテストはどうしていますか？
SmartFactory Fusionは、SmartFactoryシミュレーションモデル内でSmartFactoryディスパッチングルールをそのまま使用し、ディスパッチングおよびキャパシティの分析を行うソリューションです。本番稼動前にルール変更の影響を定量化し、モデルの精度を向上させます。
## SmartFactory Fusionを選ぶ理由
### 誤ったディスパッチルールによるダウンタイムの削減
### ルール検証にかかる労力と工数の削減
### RTD（リアルタイムディスパッチ）ルールの開発時間の短縮
## 私たちの取り組みから得られる効果
### 所有コストの削減
- シミュレーション用に別のディスパッチルールを維持する必要がなくなる
- 重複ルールの削減
- C++ 拡張の必要性を排除
### ルール統合の向上
- 現場のルールをシミュレーションに統合
- スループットと設備投資（CAPEX）への好影響を
提供
### モデル精度の向上
- RTDルール変更の what-if テスト環境を提供
- ネイティブなシミュレーション機能を活用し、より
良い意思決定を支援
---
### [RTD](https://appliedsmartfactory.com/productivity-solutions/rtd/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory RTD
# 装置の稼働能力を引出す
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## 工場で納期遵守のための対応について、どのように管理していますか？
SmartFactory RTDは、工場全体の生産性向上を支援する、リアルタイムのディスパッチングおよびレポートティングソリューションです。このソリューションにより、顧客納期を守りつつ、ボトルネック装置のパフォーマンスを最大化するためのディスパッチングポリシーを構築することができます。
## SmartFactory RTD
### 年間 300万〜1,200万ドル の利益向上
### 装置稼働率を10％向上
### 99%のオペレーター作業準拠率をサポート
## 私たちの取り組みから得られる効果
### 最適な意思決定
- 同じ設備・人員でより多くを生産可能にし、予測的かつ一貫性のある判断を実現
- 工場のリアルタイム状況に基づき、最適なロットを選択して処理可能
### ルールベースのディスパッチング
- 制約のある製造リソース領域での製品フローを最適化し、工場目標への整合性を確保
- アイコンベースの直感的なルール開発環境で、
ディスパッチングルールを簡単に導入可能
### データ統合とストレージ
- 生産、資材管理、品質アプリケーションとの連携
- 複数の情報源からデータを収集し、関連データを高速な時系列リポジトリにコピーする抽出技術を活用
---
### [RTD](https://appliedsmartfactory.com/productivity-solutions/rtd/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory RTD
# 释放隐藏的产能
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 在您的晶圆厂中，您是如何管理订单交付承诺？
SmartFactory RTD是一个实时的派工及报表解决方案，提供决策能力，以提高整个工厂的生产效率。 该解决方案使制造商能够制定派工策略，以满足客户交货时间，同时最大限度地提高瓶颈设备的生产能力。
## 为何选择 SmartFactory RTD？
### 每年增长300万-1200万美元的盈利
### 设备利用率提高10%
### 操作员一致性支持率高达99%
## 采用我们的解决方案能为您带来什么？
## 智能决策
- 使用同样的设备和人员生产更多的产品——使制定的决策具备预测性和一致性
- 根据工厂的实时状态选择最优批次进行加工
## 基于规则的派工
- 通过增强改善瓶颈区域的生产流程来确保实现工厂目标
- 使用易用的、基于图标的规则开发环境部署派工规则
## 数据集成和存储
- 集成生产系统、物料控制系统和质量控制系统
- 从多个数据源收集数据，使用提取技术对相关数据进行复制，并将这些数据存储到一个高速、瞬时数据库
---
### [Activity Manager](https://appliedsmartfactory.com/productivity-solutions/activity-manager/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Activity Manager®
# 完全自動化工場の実現へ
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## ファブにおいて、どのレベルの自動化を達成していますか？
SmartFactory Activity Managerは、工場内のイベントを処理するためのビジュアル開発環境です。このソリューションは、工場リソースの変化を検知し、プロセスを判断し、リソースに対応するという一連の流れをリアルタイムで実行することで、設備の稼働率と効率を向上させます。これにより、リソース・装置・ソフトウェアアプリケーション・人員の管理と制御が最適化され、ROI（投資対効果）の最大化が可能になります。
## SmartFactory Activity Managerを選ぶ理由
### ホワイトスペース(装置未稼働時間)を85%削減
### 完全自動搬送の95%を実現
### 熟練オペレーター作業の60〜70%削減
## 私たちの取り組みから得られる効果
### ワークフローと実行制御
- プロセスのワークフローを制御・監視
- 工場リソースの能力と生産容量に基づいて業務プロセスを最適化
- タスクの実行順序と所要時間を監視
### 自動化された例外処理
- 最小限の人手で生産を継続しながら、例外事象を一貫した方法で処理可能
### 統合フレームワーク
- 外部システムからイベントを発行したり、実行ジョブを開始したりすることが可能
- MCSやAPF RTD® リポジトリーを使用し、多様なMESアプリケーションと連携することで、状態変化やイベントに応じてジョブアプリケーションを起動
---
### [Activity Manager](https://appliedsmartfactory.com/productivity-solutions/activity-manager/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Activity Manager™
# 实现工厂自动化
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 在您的晶圆厂中，目前实现了何种等级的自动化？
SmartFactory Activity Manager 是一款用于处理工厂事件的可视化开发环境。该解决方案通过实时感知工厂资源的变化，决策工艺流程，并对设备资源做出响应，有效提升工厂利用率和运营效率，从而实现对资源、设备、软件应用及人员的优化管控，最大化投资回报率。
## 为何选择 SmartFactory Activity Manager？
### 生产空窗期减少85%
### 实现95%全自动移动
### 操作人员减少60%-70%
## 采用我们的解决方案能为您带来什么？
## 工作流和执行控制
- 控制并监控工艺流程
- 通过基于生产能力的资源分配优化工厂流程
- 监控任务执行的顺序和时间
## 自动化的异常管理
- 以一致的方式处理异常情况，以最少的人机交互保持生产运行
## 集成化的框架
- 实现外部系统发布事件或执行任务
- 集成MES、物料搬送系统及APF RTD™，根据状态变化或事件来启动作业应用程序
---
### [Production Control](https://appliedsmartfactory.com/productivity-solutions/production-control/)
**Published:** September 22, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Production Control
# シミュレーションによって、
より良い意思決定を実現
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## ファブにおいて、オペレーションをどのように分析・予測・最適化していますか？
SmartFactory Production Controlは、製造および計画業務をシミュレーションするためのキャパシティー計画システムです。実際の生産指示をシミュレーション環境で再現することで、工場のオペレーションを中断することなく、仕掛品（WIP）のスループットや設備稼働率の改善機会を特定します。
## SmartFactory Production Controlを選ぶ理由
### サイクルタイムを5％～10％削減
### スループットを5％～10％向上
### WIP予測精度 90〜95%の実現
## 私たちの取り組みから得られる効果
### シミュレーションの専門性
- RTD、Activity Manager、APF Fusion、AutoSched など、世界中の半導体製造に対応した業界標準に基づくモデリング
- 半導体製造業での最大の設備基盤を提供
### 高速な実行性能
- オブジェクト指向かつデータ駆動型のモデリングにより、市販製品中で最速の実行性能を実現
- AutoMod®と統合可能な唯一の高度処理パッケージにより、モデル精度を向上
### 高い柔軟性と詳細度
- ファブレベルのモデリングにおいて、最高レベルの柔軟性と詳細度を提供
- モデル開発を迅速化する標準機能と指示ルールを搭載
- シミュレーション結果の管理・分析を可能にするWebベースのインターフェースをサポート
---
### [Production Control](https://appliedsmartfactory.com/productivity-solutions/production-control/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Production Control
# 通过仿真模拟做出更好的决策
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 您是如何实现晶圆厂运营的分析、预测与优化？
SmartFactory Production Control是一个模拟生产和计划操作的产能规划系统。 通过在模拟环境中复制生产派工，该系统能识别出提高在制品（WIP）产出和产能利用率的机会——所有这些都不会影响工厂的运营。
## 为何选择 SmartFactory Production Control？
### 生产周期减少5%-10%
### 产出提高5%-10%
### 在制品（WIP）预测精度达到90%-95%
## 采用我们的解决方案能为您带来什么？
## 仿真技术
- 建立在RTD、Activity Manager、APF Fusion和AutoSched等用于建模复杂半导体操作的行业标准的平台之上
- 在半导体制造业提供了最大的安装量
## 快速执行
- 提供面向对象的、数据驱动的建模，提供市场在售产品中最快的执行速度
- 提供只与AutoMod™集成的高级处理包，以提高模型精度
## 更大的灵活性和细节
- 在晶圆厂级别的建模中提供最大的灵活性和细节
- 包括用于快速模型开发的标准特性和派工规则
- 支持基于web的界面来管理和分析仿真结果
---
### [Advanced Scheduling](https://appliedsmartfactory.com/productivity-solutions/advanced-scheduling/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Advanced Scheduling
# 最適化されたスケジュールで
生産能力を最大化
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## 装置の稼働率を最大化するために、ディスパッチングルール
だけに頼っていませんか？
SmartFactory Advanced Schedulingは、半導体製造における最大の課題のひとつである「ロットの移動管理」を解決する、最適化ベースのスケジューリングシステムです。装置の活用を最大化するには、ディスパッチングとスケジューリングの両方が必要ですが、最適化されたスケジューリングがなければ、効率的な工場であっても生産能力を最大限に活かすことはできません。
## SmartFactory Advanced Schedulingを選ぶ理由
### リソグラフィ装置の稼働率を1%以上向上
### スループットを2.1%向上
## 私たちの取り組みから得られる効果
## 迅速なスケジュール更新
- 工場のリアルタイムデータを活用し、複数の上流・下流システムからの情報を継続的に評価
- ディスパッチシステムだけでは実現できない高度なアルゴリズムを使用
- ロットやレチクルに対して、常に最新のスケジュールを提供
## 設備投資のリターンを最大化
- リソグラフィ装置の稼働率を向上させることで、新たな設備投資の延期または不要化を実現
- ボトルネック装置への設備投資（CapEx）を削減
## 共通のフレームワーク
- 実証済みのApplied APFプラットフォームと共通データモデル(common data model)をベースに構築され、工場イベントを基にプランニング、スケジューリング、ディスパッチ・アルゴリズムを実行
- 前工程および後工程(組立・テストエリア向け)に、すぐに使えるスケジューラーを提供
- 追加の統合作業（インテグレーション）は不要
---
### [Advanced Scheduling](https://appliedsmartfactory.com/productivity-solutions/advanced-scheduling/)
**Published:** October 12, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Advanced Scheduling
# 通过优化派工达到产能最大化
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 您是否仅靠派工规则来最大化设备利用率？
SmartFactory Advanced Scheduling 是一个优化的排程系统，解决了半导体行业最大的问题之一——管理批次调度，更好地最大化利用生产设备。 派工和排程都是必要的，但没有优化的排程，即使是高效的晶圆厂也不能最大限度地提高产能。
## 为何选择 SmartFactory Advanced Scheduling？
### 锂利用率提高1%以上
### 产量提高2.1%以上
## 采用我们的解决方案能为您带来什么？
## 快速排程更新
- 使用实时工厂数据，持续评估来自多个上下游系统的数据
- 使用复杂的算法——仅使用派工系统是无法达成的
- 为生产批次和光罩提供即时的时间表更新
## 增加设备收益
- 通过增加光刻利用率，使客户能够推迟或消除对额外光刻设备的投资
- 减少在瓶颈设备上的资本支出
## 通用框架
- 建立在经过验证的APF平台和通用数据模型上，用于在工厂事件上执行计划、调度和派工算法
- 为Fab、封装和测试区域提供开箱即用的调度程序
- 无需额外系统集成
---
### [FullAuto](https://appliedsmartfactory.com/productivity-solutions/fullauto/)
**Published:** October 12, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory FullAuto
# 消除生产空窗期
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 在您的晶圆厂中，如何实现设备空窗期最小化？
SmartFactory FullAuto是一个自动化的工作流引擎系统，通过“下一步做什么”、“下一步在哪里”的规则来执行在制品（WIP）预分级、释放批次，并调整生产设备的负载平衡，以改进产品和资源的使用。 这减少了生产空窗期，提高了运营效率。
## 为何选择 SmartFactory FullAuto？
### 交付时间减少17%——提高瓶颈设备的产出
### 200mm晶圆厂操作员减少65%
### 在300mm晶圆厂，8个月内的批次，自动化执行率达到95%以上
## 采用我们的解决方案能为您带来什么？
## 减少生产空窗期
- 提供减少设备空窗期的能力
- 降低对专业操作人员管理工厂运行的需要
## 更快速部署
- 可以快速部署以迅速提升工厂运营的开箱即用解决方案——不同于许多本地解决方案，它们是硬编码，部署和维护成本很高
## 通用框架
- 建立在应用材料公司的APF平台和公共数据模型上，对工厂事件执行计划、调度和派工算法
- 执行和控制任何级别的工厂自动化
- 无需额外系统集成
---
### [FullAuto](https://appliedsmartfactory.com/productivity-solutions/fullauto/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory FullAuto
# 装置稼働率の向上へ
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## 貴社工場における、装置空き時間の最小化をどの様に実現しますか？
SmartFactory FullAuto は自動化されたワークフローエンジンです。製品製造のスループットおよび装置などのリソース稼働率を改善するために”what next”、”where next”ルールを使用し、WIPの事前計画、lotのリリースおよび製造装置使用のバランシング調整を実施します。これにより装置の空き時間削減と
オペレータの作業効率の向上が期待できます。
## SmartFactory FullAuto を選ぶ理由
### 納期を17%短縮 — ボトルネック装置のスループット向上
### 200mm工場の熟練オペレータ作業を65%削減
### 8か月以内に300mm工場でのLotの95%以上を自動実行
## 私たちの取り組みから得られる効果
## 装置空き時間の削減
- 装置の空き時間を削減
- 工場オペレーションを管理するための熟練オペレータの依存度を削減
## 迅速な導入が可能
- すぐに導入可能なパッケージソリューション ー 多くの自社開発ソリューションとは異なり、ハードコーディング不要で、導入・保守コストを大幅に削減
## 共通のフレームワーク
- Applied APF プラットフォームと共通データ モデル（common data model）に基づいて構築されており、貴社工場での計画、スケジュール、およびディスパッチングアルゴリズムを実行
- あらゆるレベルでの工場自動化を実行/制御
- 追加の統合作業(インテグレーション)は不要
---
### [Real Time Scheduling & Reporting](https://appliedsmartfactory.com/productivity-solutions/real-time-scheduling-reporting/)
**Published:** October 12, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Real Time Scheduling & Reporting
# 实时提高工厂生产效率
[ 阅读【生产效率博客】 ](/zh-hans/semiconductor-blog-category/productivity-zh-hans/)
## 您是否在寻找可以有效管理工厂生产周期的方法？
SmartFactory Real Time Scheduling & Reporting是一个自动化决策解决方案，通过在应用材料公司成熟的APF平台上执行先进的基于规则的实时派工和报表策略，提高工厂效率。
## 为何选择 SmartFactory Real Time Scheduling & Reporting？
### 时间和变化周期减少50%
### 晶圆日产量提高10%-15%
### 操作员一致性达99%
## 采用我们的解决方案能为您带来什么？
## 提高瓶颈区域的产出
- 使用派工规则，通过更好地对相同特性的批次进行分组来提高瓶颈区域的产出，同时满足按时交货的承诺
- 提高年盈利水平——一份客户报告显示，通过基于规则的派工提高了工厂产出，每个工厂增加了60万至100万美元
## 缩短部署时间
- 与自定义部署相比，部署时间减少50%以上
- 快速部署，以迅速提高工厂运行
- 具有集成功能的开箱即用解决方案
## 无需复杂编程
- 无需复杂编程，识别和实施工艺改进
- 使用易用的规则开发环境部署简单的派工规则
- 所有规则和报表都是使用基于图标方式开发的
---
### [Real Time Scheduling & Reporting](https://appliedsmartfactory.com/productivity-solutions/real-time-scheduling-reporting/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Real Time Scheduling & Reporting
# リアルタイムで工場の生産性を向上
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## ファブ全体のサイクルタイムの課題を管理する方法を探していますか？
SmartFactory Real Time Scheduling & Reportingは、自動化された意思決定ソリューションであり、実績あるAppliedのAPFプラットフォーム上で、高度なルールベースのリアルタイムディスパッチおよびレポート戦略を実行することで、工場の生産性を向上させます。
## SmartFactory Real Time Scheduling & Reportingを選ぶ理由
### サイクルタイムとばらつきを50%削減
### 1日あたりのウェーハ生産量を10〜15%向上
### オペレーターの手順遵守率99%
## 私たちの取り組みから得られる効果
### ボトルネックの解消による
処理能力の向上
- 同じ特性を持つロットをより効果的にグループ化し、納期を守りながらディスパッチルールを活用することで、ボトルネックを解消し、工程全体のスループットを向上
- 工場の出力向上により年間利益を増加 — あるお客様 は、ルールベースのディスパッチング導入で、年間 60万〜100万ドルの利益向上を実現
### 導入時間の短縮
- カスタム導入と比較して、導入期間を50%以上短縮
- 工場運用を迅速に強化するためにスピーディーに導入可能
- 高い統合性を備えた即時利用可能なソリューション
### 複雑なプログラミングは不要
- 複雑なプログラミングなしでプロセス改善を特定・実装可能
- 使いやすいルール開発環境でシンプルなルールシナリオを展開
- すべてのルールとレポートはアイコンベースで直感的に操作可能
---
### [Enterprise Planning](https://appliedsmartfactory.com/supply-chain-solutions/enterprise-planning/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Enterprise Planning
# お客様の変化に対する迅速な 対応を実現
[ Read Semi Blog ](/semiconductor-blog/)
## 製造現場では、お客様の需要予測の変更にどのように対応していますか？
SmartFactory Enterprise Planningは、製造業向けのサプライチェーン計画プランニングソリューションであり、高速なプランニングエンジンを備え、納期遵守と柔軟な対応力を向上させます。多くのプランニングソリューションとは異なり、複雑な導入やカスタマイズを必要とせず、計画から実行まで一本化されています。オープンボックス型のアプローチにより、高精度かつ迅速な需要予測変更対応を実現します。
## SmartFactory Enterprise Planning を選ぶ理由
### プランニングに関するダウンタイムを最大95%削減
### プランナーの生産性を10〜30%向上
### 設備稼働率を3〜5%改善
## 私たちの取り組みから得られる効果
### 自動データ入力
- AppliedのAPFテクノロジーを活用し、必要な計画データを自動で収集・読み込み
- 実績のある高速データ抽出・処理により、迅速に供給計画を生成
### 迅速な対応力
- 高速な数理ソルバーを搭載した計画エンジンで、納期遵守などの目標を最適化
- 顧客の要求に迅速に対応できるよう、「what if」シナリオ・プランニングや再プランニングを迅速に実行
### データ連携
- SmartFactoryソリューションと共通フレームワークでシームレスに統合
- エンタープライズ計画と現場の作業指示を連携し、迅速な警告発報の機能を提供
---
### [Simulation AutoSched](https://appliedsmartfactory.com/zh-hans/supply-chain-solutions/simulation-autosched/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoSched®
# 发现隐藏的价值
## 您是如何为您的生产设备建立决策逻辑模型的?
SmartFactory Simulation AutoSched是一个产能规划系统，它通过仿真模拟复杂的工作流程来识别隐藏的和浪费的工厂产能。 它允许用户创建一个虚拟的晶圆厂模型来分析、预测和优化操作，可以在离线的情况下对调度规则、设备操作和操作周期进行检验。
## 为什么选择SmartFactory Simulation AutoSched？
### 改善生产周期
### 降低在制品（WIP）和缓冲（buffer）等级
### 增强决策逻辑
## 您能从我们的解决方案中获得什么？
## 更好的执行
- 包括一个面向对象的、数据驱动的建模工具，提供市场在售产品中最快的执行速度
- 包括用于快速模型开发的表征特点和调度规则
## 更好的集成
- 针对构建详细、准确的模型，提供只与AutoMod®集成的高级处理包
- 为客制化的业务提供开放的体系结构，能模拟几乎任何的应用程序
## 更好的体验
- 为半导体行业提供最大的安装量——拥有超过20年的仿真模拟经验和425家以上实际用户的部署经验
- 为人所熟知的产能规划以及仿真模拟领域的领导企业
---
### [Production Control](https://appliedsmartfactory.com/supply-chain-solutions/production-control/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Production Control
# 通过仿真模拟做出更好的决策
## 您是如何分析、预测和优化工厂的运营？
SmartFactory Production Control是一个模拟生产和计划操作的产能规划系统。 通过在模拟环境中复制生产派工，该系统能识别出提高在制品（WIP）产出和产能利用率的机会——所有这些都不会影响工厂的运营。
## 为什么选择SmartFactory Production Control？
### 生产周期减少5%-10%
### 产出提高5%-10%
### 在制品（WIP）预测精度达到90%-95%
## 您能从我们的解决方案中获得什么？
## 仿真技术
- 建立在RTD、Activity Manager、APF Fusion和AutoSched等用于建模复杂半导体操作的行业标准的平台之上
- 在半导体制造业提供了最大的安装量
## 快速执行
- 提供面向对象的、数据驱动的建模，提供市场在售产品中最快的执行速度
- 提供只与AutoMod™集成的高级处理包，以提高模型精度
## 更大的灵活性和细节
- 在晶圆厂级别的建模中提供最大的灵活性和细节
- 包括用于快速模型开发的标准特性和派工规则
- 支持基于web的界面来管理和分析仿真结果
---
### [Enterprise Planning](https://appliedsmartfactory.com/supply-chain-solutions/enterprise-planning/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Enterprise Planning
# 对客户的变更需求做出更快的响应
## 您的工厂是如何应对客户的变更需求？
SmartFactory Enterprise Planning是一个供应链规划解决方案，包括一个快速规划引擎，以提高制造商按时交货和及时响应的能力。与许多需要复杂部署和定制的规划解决方案不同，SmartFactory Enterprise Planning集成了从规划到执行的全过程，提供了一种开箱式的方法，提高了准确性，并能更快地响应客户预测变化的需求。
## 为什么选择SmartFactory Enterprise Planning？
### 减少95%的计划外停机
### 计划员的效率提高10-30%
### 产能利用率提高3-5%
## 您能从我们的解决方案中获得什么？
## 数据输入自动化
- 使用应用材料公司的APF技术自动收集和加载所有必要的规划数据
- 使用成熟的、高速数据提取和处理的系统快速生成供应计划
## 快速响应时间
- 使用计划引擎和快速数学求解器优化按时交货和其他目标
- 执行快速的“假设”场景规划或重新规划，以快速响应客户要求
## 数据连接
- 通过从派工到自动化的通用框架，与SmartFactory解决方案无缝集成
- 将企业生产规划与车间调度联系起来，提供预警能力
---
### [Enterprise Planning](https://appliedsmartfactory.com/supply-chain-solutions/enterprise-planning/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Enterprise Planning
# React faster to customer changes
[ Read Semi Blog ](/semiconductor-blog/)
## In your fab, how do you respond to customer forecast changes?
SmartFactory Enterprise Planning is a supply chain planning solution that includes a fast planning engine to improve on-time delivery and responsiveness for manufacturers. Unlike many planning solutions, which require complex deployments and customizations, SmartFactory Enterprise Planning is integrated from planning through execution, offering an open-box approach with increased accuracy and faster response to customer forecast changes.
## Why choose SmartFactory Enterprise Planning?
### 95% reduction in planning downtime
### 10–30% improved planner productivity
### 3–5% capacity utilization improvement
## What can you gain from our approach?
### Automated data input
- Use Applied’s APF technology to automatically gather and load all necessary planning data
- Quickly generate supply plans using proven, high speed data extraction and processing
### Fast response times
- Optimize on-time delivery and other objectives using planning engine with fast mathematical solver
- Execute fast “what if” scenario planning or re-planning to enable quick response times to customer requests
### Data linking
- Integrate seamlessly with SmartFactory solutions through common framework from dispatching to automation
- Link enterprise planning to shop floor dispatching to provide early warning capability
---
### [Simulation AutoSched](https://appliedsmartfactory.com/productivity-solutions/simulation-autosched/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoSched®
# Discover hidden value
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## In your fab, how do you model decision logic for your equipment?
SmartFactory Simulation AutoSched is a capacity planning system that enables simulation of complex workflows to identify hidden and wasted factory capacity. It allows users to create a virtual model of a fab to analyze, predict, and optimize operations, enabling experiments with scheduling rules, equipment, and operator cycles offline.
## Why choose SmartFactory Simulation AutoSched?
### Improved cycle time
### Reduced WIP and buffer levels
### Improved decision logic
## What can you gain from our approach?
### Better execution
- Includes an object-oriented, data driven modeling tool, providing the fastest execution of any of the commercially available products
- Includes standard features and dispatching rules for quick model development
### Better integration
- Offers the only advanced processing package that integrates with AutoMod® for detailed, accurate models
- Provides open architecture for customizations to model virtually any application
### Better experience
- Offers the largest installed based in semiconductor manufacturing—over 20 years of simulation experience and over 425 deployments
- Proven to be the industry leader in capacity planning and simulation
---
### [Fusion](https://appliedsmartfactory.com/productivity-solutions/fusion/)
**Published:** September 24, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Fusion
# Quantify the impact of rule changes
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## In your fab, how do you test rules without impacting production?
SmartFactory Fusion is a dispatching and capacity analysis solution that uses SmartFactory dispatching rules within SmartFactory simulation models without any modifications. It enables users to quantify the impact of rule changes prior to implementing them in production, improving model accuracy.
## Why choose SmartFactory Fusion?
### Reduced downtime due to incorrect dispatching rules
### Reduced labor and effort to execute rule validations
### Reduced RTD rule development time
## What can you gain from our approach?
### Lower cost of ownership
- Eliminates need to maintain separate dispatching rules for simulation
- Reduces duplicate rules
- Eliminates need for C++ extensions
### Better rule integration
- Integrates shop floor rules into simulation
- Provides positive impact on throughput and CAPEX spending
### Improved model accuracy
- Provides what-if test environment for RTD rule changes
- Offers ability to use native simulation capability, enabling better decisions
---
### [RTD](https://appliedsmartfactory.com/productivity-solutions/rtd/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory RTD
# Reclaim hidden capacity
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## In your fab, how do you manage delivery-to-promise commitments?
SmartFactory RTD is a real-time dispatching and reporting solution that provides decision making ability to improve productivity across the entire factory. The solution enables manufacturers to develop dispatching policies to meet customer due dates while maximizing performance of bottleneck tools.
## Why choose SmartFactory RTD?
### $3M - $12M annual increase in profitability
### 10% increase in tool utilization
### 99% operator conformance support
## What can you gain from our approach?
### Intelligent decision making
- Produce more with the same equipment and personnel — enabling predictive and consistent decisions
- Select optimal lots to process based on real-time state of the factory
### Rules-based dispatching
- Enhance product workflow in areas with constrained manufacturing resources while ensuring adherence to factory objectives
- Deploy dispatching rules with easy-to-use icon-based rule-development environment
### Data integration & storage
- Integrates with production, material control, and quality applications
- Collects data from multiple sources using extraction technology that copies relevant data to a high-speed, temporal repository
---
### [Activity Manager](https://appliedsmartfactory.com/productivity-solutions/activity-manager/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Activity Manager®
# Enabling lights out factory automation
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## In your fab, what level of automation have you achieved?
SmartFactory Activity Manager is a visual development environment for handling factory events. The solution increases plant utilization and efficiency by sensing changes in factory resources, deciding on processes, and responding to factory resources—all in real‐time. This results in better management and control of resources, equipment, software applications and personnel, maximizing ROI.
## Why choose SmartFactory Activity Manager?
### 85% white space reduction
### 95% enablement of full automation moves
### 60%–70% reduction in expert operators
## What can you gain from our approach?
### Workflow & execution control
- Control and monitor process workflow
- Optimize business processes by assigning plant resources based on capabilities and capacity
- Monitor the sequence and time in which tasks are performed
### Automated exception management
- Handle exceptions in a consistent manner by keeping production running with minimum human interaction
### Integration framework
- Enable external systems to publish events or start execution jobs
- Integrate with a wide variety of MES applications, with material control systems, and with the APF RTD® repository to start job applications based on state changes or events
---
### [FullAuto](https://appliedsmartfactory.com/productivity-solutions/fullauto/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory FullAuto
# Eliminate white space
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## In your fab, how do you minimize white space on tools?
SmartFactory FullAuto is an automated workflow engine system that executes pre-staging of WIP, releases lots, and adjusts load balancing of production equipment through “what next” and “where next” rules to improve the use of products and resources. This results in reduced white space and improves operator efficiency.
## Why choose SmartFactory FullAuto?
### 17% Reduction in Delivery Time — Improved Throughput for Bottleneck Tools
### 65% Reduction in Super Operators in 200mm Fabs
### >95% Automatic Execution of Lots Achieved within 8 Months in 300mm Fabs
## What can you gain from our approach?
## Reduced white space
- Offers ability to reduce white space on tools
- Reduces need for expert operators to manage factory operations
## Faster deployment
- Out-of-box solution that can be quickly deployed to rapidly enhance factory operations—unlike many homegrown solutions, which are hardcoded and costly to deploy and maintain
## Common framework
- Built on the Applied APF platform and common data model to execute planning, scheduling, and dispatching algorithms on factory events
- Executes and controls any level of fab automation
- No additional integration required
---
### [Real Time Scheduling & Reporting](https://appliedsmartfactory.com/productivity-solutions/real-time-scheduling-reporting/)
**Published:** September 23, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Real Time Scheduling & Reporting
# Improve factory productivity in real-time
[ Read Productivity blog ](/semiconductor-blog-category/productivity/)
## Are you looking for ways to manage cycle time issues across your fab?
SmartFactory Real Time Scheduling & Reporting is an automated decision-making solution that improves factory productivity by executing advanced rule-based, real-time dispatching and reporting strategies on Applied’s proven APF platform.
## Why choose SmartFactory Real Time Scheduling & Reporting?
### 50% Reduction in Time & Variability Cycles
### 10% -15% Increase in Wafer Output Per Day
### 99% Operator Conformance
## What can you gain from our approach?
### Increased bottleneck throughput
- Use dispatching rules to increase bottleneck throughput by better grouping lots of the same characteristics while meeting due date commitments
- Increase annual profitability—one customer reported an increase of $600K to $1M per factory due to higher factory output through rules-based dispatching
### Shorter deployment times
- Cut deployment times by more than 50% compared to custom deployments
- Deploy quickly to rapidly enhance factory operations
- Out-of-the-box solution with tight integration capabilities
### No complex programming
- Identify and implement process improvements without complex programming
- Deploy simple rule scenarios with easy-to-use rule-development environment
- All rules and reports are icon-based
---
### [Maintenance Management](https://appliedsmartfactory.com/process-quality-solutions/maintenance-management/)
**Published:** October 6, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Maintenance Management
# Optimize your maintenance schedules
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## In your fab, is maintenance planning automated?
SmartFactory Maintenance Management is an equipment‐centric computerized maintenance management system (CMMS) that effectively manages planned, scheduled, and unscheduled maintenance activities. Developed specifically for the semiconductor industry, the solution optimizes the management of overall inventory levels, improves equipment availability, and decreases labor and parts costs.
## Why choose SmartFactory Maintenance Management?
### Access to in-depth semi equipment hierarchy, configurability, and state modeling
### Increased factory equipment availability and efficiency
### Reduction in labor and parts costs
## What can you gain from our approach?
### Better planning
- Automate maintenance activities and easily schedule your tools and technicians
- Eliminate need for spreadsheets and paper schedules
- Implement “at-the-tool” checklists using mobile client to ensure BKMs and first time rights
### Better productivity
- Track equipment states and activities down to individual chamber in cluster tools
- Accurately assess tool availability even in downgraded yet operational states
- Improve asset availability by reducing loss due to downtime, setup, and adjustments
### Better integration
- Integrate with any MES, and specifically with FACTORYworks®, which works on the same model
- Integrate with Applied E3® and APF RTD® solutions to support WIP reallocation when necessary
- Integrate with key factory systems, including spare parts inventory and technician tracking and scheduling
---
### [Asset Trace](https://appliedsmartfactory.com/process-quality-solutions/asset-trace/)
**Published:** October 8, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Asset Trace
# Improves asset utilization with asset trace throughout entire life cycle
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## How do you manage critical production assets in your factory?
A *durable* is essentially a mobile extension of a tool—a reticle, carrier, probe card, pump, valve, burn-in-board, socket, trolley etc. *Consumables* such as gases, chemicals and targets, are used up during production. SmartFactory Asset Trace solution is an automated management system that involves tracking, monitoring and optimizing the usage, maintenance, and lifecycle of these assets to ensure smooth operations and maximize productivity.
## Why choose SmartFactory Asset Trace?
### 6-8% of scrap reduction due to human error, contamination and material quality
### 3% improvement on equipment utilization
### Labor overhead cost savings due to automation
## What can you gain from our approach?
### Easier traceability
- Locating the durable/consumable and what state it is in
- Achieve higher equipment utilization
- Gain higher yield by using the proper durable/consumable and properly maintaining and storing them
- Reduce overhead from manually tracking durables/consumables
### Seamless integration
- Easily connect with other factory systems such as MES, MCS, SPC, Maintenance Management and dispatching
- Utilize SmartFactory RTD to boost real-time decision-making and WIP management, resulting in improved equipment uptime
- Deploy SmartFactory SPC to improve process quality and reduce scrap time by having a positive impact on performance statistics
### Easier state modeling
- Rapid ability to define state model to track and manage the lifecycle of any durable/consumable
- Easily configure models without any programming
- Automatic triggers
---
### [Equipment Automation](https://appliedsmartfactory.com/process-quality-solutions/equipment-automation/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Equipment Automation
# Increase productivity and reduce human error
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## In your facility, are you looking to move beyond manual basics?
SmartFactory Equipment Automation is an equipment design and control framework that executes automation services in run-time. The solution integrates equipment data—the largest source of data in manufacturing—to enable automation flow design, transaction and sequence testing, run-time troubleshooting and diagnostics, and centralized user maintenance. This integrated data capability results in increased productivity, as well as reduced errors and scrap losses.
## Why choose SmartFactory Equipment Automation?
### 10–15% increased wafer output per day with automated dispatching
### 10% increased tool utilization with automated dispatching
### 97% reduction in data recording time
## What can you gain from our approach?
### Optimized assets
- Keep equipment assets utilized by executing run-time automation scenarios
- Coordinate with SmartFactory FullAuto to transport, load, process, and unload material without operator intervention
### Reduced errors
- Enable quality control pre-checks to validate that the correct material matches the appropriate sequences and recipes
- Consistently meet quality and engineering data requirements
### Integrated data
- Compile and distribute data collection records to the appropriate applications for analysis
- Analyze equipment performance to identify hidden cycle time losses
- Integrate with Applied’s SmartFactory CIM solution and other non-Applied solutions
---
### [Recipe Management](https://appliedsmartfactory.com/process-quality-solutions/recipe-management/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Recipe Management
# Safeguard your recipes
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How do you manage thousands of recipes spread across your facility?
Manufacturing equipment recipes are a company’s top intellectual property. To manage these recipes, our SmartFactory Recipe Management System (RMS) provides an easy way to review recipe differences, duplicates, and consolidations, while protecting recipe IP through a secure centralized repository. The solution validates runtime recipes and parameters, improving line yield and traceability.
## Why choose SmartFactory Recipe Management?
### 50% estimated scrap reduction due to human error
### 4–10% estimated line yield improvement in mature fabs
## What can you gain from our approach?
### Central recipe repository
- Maintains recipes in secure repository with redundancy and version control
- Protects business continuity by preventing accidental loss of tool recipes
- Provides historical recipe traceability for certification and audit readiness
### Automated recipe efficiency
- Controls equipment constants and recipe parameter values, reducing misprocessing
- Automates run-time validation in conjunction with equipment automation, increasing wafer output
### Reduced human errors
- Validates runtime recipes against recipe specifications, minimizing rework and scrap
- Reduces errors from updating incorrect steps or modifying wrong parameters
---
### [Fault Detection](https://appliedsmartfactory.com/process-quality-solutions/fault-detection/)
**Published:** September 28, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Fault Detection
# Minimize yield loss due to excursions
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How do you reduce excursions in your facility?
SmartFactory Fault Detection is a process control solution that quickly detects equipment issues by monitoring sensors and events against performance metrics, resulting in improved tool availability and reduced scrap. Unlike many standalone systems, which rely on reactive methods, SmartFactory Fault Detection offers proactive and rapid feedback on equipment issues before they affect process output.
## Why choose SmartFactory Fault Detection?
### 90% reduction in equipment & process false alarms
### >95% reduction in scrapped material
### 25+ hour reduction in unscheduled equipment downtime
## What can you gain from our approach?
### Improved fab KPIs
- Safeguards your fab by detecting problems at the source
- Detects previously undetectable issues
- Monitors your fab through analytics and reporting
### Actionable information
- Predicts and proactively schedules systems for repair before failures can occur
- Increases predictability of operations and tool downtime
- Offers extensive data filtering to eliminate false positives and easily handle maintenance events
### Integrated platform
- Offers common platform with integration to Run-to-Run, SPC, and Recipe Management to promote information sharing
- Facilitates integration of process tool, metrology tool, and manufacturing data between APC components
---
### [Run To Run Control](https://appliedsmartfactory.com/process-quality-solutions/run-to-run-control/)
**Published:** September 27, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Run-to-Run Control
# Optimize tool recipe parameters
[ Read Quality blog ](/semiconductor-blog-category/quality/)
## How do you solve process capability issues in your facility?
SmartFactory Run-to-Run Control is an advanced process control (APC) solution that improves process capability (Cpk) and optimizes tool recipe parameters. The out-of-box solution offers patented model prediction that includes a multivariant, constrained, optimization-based process controller with proven deployment success.
## Why choose SmartFactory Run-to-Run Control?
### 30% average Cpk improvement
### 10–30% reduction in scrap events
### 2–4% increase in mature yield
## What can you gain from our approach?
### Improved yield
- Reduces process variation
- Enables better decision-making during development and ramp phases of production
- Reduces yield killing process variation during high volume manufacturing
### Improved quality
- Improves Cpk by automatically optimizing tool recipe parameters
- Reduces out of spec (OOS) and scrap events by compensating for drifts from equipment and processes
- Improves throughput by reducing pilot wafers
### Lower cost of ownership
- Reduces model management activities through a unified modeling structure
- Offers common platform with integration to SPC and FDC to promote information sharing
---
### [Monitor](https://appliedsmartfactory.com/manufacturing-execution-solutions/monitor/)
**Published:** October 8, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Monitor
# Detect & predict system failures
[ Watch Video ](/semiconductor-blog/manufacturing-execution/smartfactory-monitor/)
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## Are your factory systems slowing down or failing?
In a medium-volume fab, just one hour of unscheduled downtime equates to a $100,000 loss. To prevent such losses, SmartFactory Monitor is a suite of production monitoring capabilities that patrols your software system to predict system failures and unscheduled downtime. Using run-time monitoring and predictive analytics algorithms, the solution optimizes system performance and provides insights for predicting future fab events.
## Why choose SmartFactory Monitor?
### Reduce unscheduled downtime
### Reduce system failures and slow response times
### Reduce mean-time-to-resolve (MTTR)
## What can you gain from our approach?
### Better insight
- Collect critical indicators from databases, servers, and manufacturing applications
- Set up optimized alerts, leading to actionable insights
- Sort and prioritize events by severity to instantly identify root cause
### Better prediction
- Predict future events with advanced analytics, which reduces downtime
- Use production data from machine learning to predict failures, and summarize results on performance dashboard
- Take preventive action based on alarms, and fix problems in advance
### Better coverage
- Access 24/7 dedicated coverage through experienced global team to monitor production and maintain performance, stability, and high-availability
- Access worldwide database, apps, OS, and network monitoring support
---
### [Alarm Management](https://appliedsmartfactory.com/manufacturing-execution-solutions/alarmmanagement/)
**Published:** November 4, 2022
**Author:** Applied Smartfactory
**Content:**
SmartFactory Alarm Management
# Efficiently manage alarms to safeguard quality and productivity
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## How do you cut through the noise to identify the critical alarms in your factory?
By efficiently managing alarms, SmartFactory Alarm Management helps you more quickly identify, prioritize and respond to alerts and take appropriate action.
## Why choose SmartFactory Alarm Management?
### 100% coverage of alarms with significantly minimized “alarms fatigue"
### 1% uptime increase due to immediate issue notification to fab personnel
### 0.5% improved yield by identifying “critical alarms” and automating decision making
## What can you gain from our approach?
### Faster resolution
- Centralize real-time alarm handling
- Reduce production noise with a de-duplication algorithm
- Catch quality-impacting issues sooner
### Increased tool utilization
- Consolidate alarm data from your CIM stack for fast troubleshooting
- Accelerate root cause analysis
- Create predefined, automated actions like putting a lot on hold or logging a tool down across MES, equipment automation, and other systems
### Improved communication
- Set alert recipients and escalation paths
- Real-time, factory-wide view
---
### [FAB300](https://appliedsmartfactory.com/manufacturing-execution-solutions/fab300/)
**Published:** October 6, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FAB300®
# Scale up and out to meet demand
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## Does your MES support high-volume yields and updates?
SmartFactory MES FAB300 is a fab management system that offers a configurable and extensible workflow engine that simplifies quick changes in business processes in days—not months. Proven to support 300K 300mm wafer starts per month (WSPM), FAB300 enables manufacturers to scale up and out to meet high volume production ramps—and all this can be done in less time, with less risk, and at a lower cost.
## Why choose SmartFactory MES FAB300?
### Easy integration with other factory applications
### Support for 300,000 wafer starts per month
### Near-zero downtime
## What can you gain from our approach?
### Greater efficiency
- Implement proprietary operating practices through workflows, without the need for programming
- Perform rolling upgrades with near-zero downtime
- Recover with near-zero downtime if failure of a single node occurs
### Better productivity
- Implement simplified system management capabilities for safer and lower cost automation
- Increase control over fab processes
- Reduce cycle time and increase throughput
### Better adaptability
- Easily integrate with SmartFactory modules or third-party applications to achieve a total factory solution
- Implement your factory vision using a single environment based on standard components
- Ensure your intellectual property (IP) is in the data—maintained in workflow models—separated from the code and easily protected
---
### [FACTORYworks+](https://appliedsmartfactory.com/manufacturing-execution-solutions/factoryworks-plus/)
**Published:** October 5, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FACTORYworks+™
# Think out-of-box for faster deployment
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## How quickly can you achieve high volume production in your new factory?
SmartFactory MES FACTORYworks+ is an out-of-the-box manufacturing execution system developed for semiconductor back-end and semiconductor-adjacent industries. Powered by our leading FACTORYworks platform, MES FACTORYworks+ offers rapid implementation with additional out-of-box functionality tailored for achieving first production starts in 90 days.
## Why choose SmartFactory MES FACTORYworks+?
### Greater efficiency in achieving high volume production
### Improved product quality while reducing operational costs
### Less than 90-day deployment times
## What can you gain from our approach?
### Better customization
- Customize modules to meet needs of your manufacturing scenarios
- Customize logic for operation scenarios
- Customize FACTORYworks schema for site-specific data requirements
### Integration control
- Easily integrate with other SmartFactory CIM modules, including maintenance management, equipment automation, and dispatching
- Easily integrate with third-party applications, including ERP and warehouse management systems
### Greater scalability
- Scale existing factory control systems to manage higher production levels
- Start with small hardware footprint, then scale horizontally as your business grows
- Easily handle factory expansion, multiple factories, and multiple lines
---
### [FACTORYworks](https://appliedsmartfactory.com/manufacturing-execution-solutions/factoryworks/)
**Published:** October 4, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES FACTORYworks®
# Automate operations for greater efficiency
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## Is your MES scalable to support extreme levels of production?
SmartFactory MES FACTORYworks is a fully integrated, stable manufacturing execution system that manages highly automated manufacturing operations. Known for its configurable modeling and scalability, FACTORYworks is proven in semiconductor frontend, backend, display, and discrete manufacturing and has a long, successful track record.
## Why choose SmartFactory MES FACTORYworks?
### High reliability and consistent stability
### Multiple platform support to reduce cost of ownership
### Proven in mission critical applications around the world
## What can you gain from our approach?
### Efficiency improvements
- Eliminate operator misprocessing
- Reduce material shortage and physical inventory
- Reduce integration effort by using pre-integrated Applied applications
- Improve response time to changing market and plant conditions
### Extension development
- Develop extensions for special features, business rules, and external system integrations
- Build custom business operations using rule development environment
- Replace and extend supplied business rules without compilations
### Multisite support
- Handle factory expansion, multiple factories, and lines with extreme throughput requirements
- Monitor and control production across multiple factories
- Move material and share critical resources between sites
---
### [SmartFactory MES for ATP](https://appliedsmartfactory.com/manufacturing-execution-solutions/mesforatp/)
**Published:** January 6, 2025
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES for ATP
# Advanced MES for semiconductor backend manufacturing
[ Read MES Blog ](/semiconductor-blog-category/manufacturing-execution/)
## Do you want to streamline the flow of materials throughout your manufacturing facility?
SmartFactory MES for ATP is a comprehensive system to streamline and monitor the flow of materials throughout the semiconductor backend manufacturing facility. MES for ATP is designed to support lights-out manufacturing with automation scenarios for advanced assembly, test and packaging; it optimizes factory control and handles manufacturing anomalies automatically. With the SmartFactory MES for ATP, you can accelerate new facility ramp-up and speed time-to-market.
## Why choose SmartFactory MES for ATP?
### Achieve first wafer out within 90 days
### Reduce misprocessing by up to 70%
### Proven 99.99% production uptime
## What can you gain from our approach?
### Increase manufacturing efficiency
- Flexible modeling for die attachment, including substrate location and placement sequence
- Accurate traceability of die, substrates, and lots through the manufacturing process
- Unified MES platform handles everything from traditional test and assembly to fully automated advanced packaging
### Rapid deployment
- Pre-built “best practice” manufacturing scenarios enable first wafer out within 90 days
- Integrated functionality minimizes production ramp time and speeds yield improvement
### Enable lights-out manufacturing
- Flexible deployment from manual operation all the way to fully automated manufacturing
- Pre-defined error-handling scenarios automate recovery from unexpected manufacturing events
- Field-proven to accelerate production ramp all the way through lights-out manufacturing within one year
---
### [SmartFactoryについて](https://appliedsmartfactory.com/about/)
**Published:** February 24, 2025
**Author:** Applied Smartfactory
**Content:**
私たちは
# **製造業を
変革します**
自動化のエキスパート
0 名以上の
生産性と品質の向上の実績
0 年以上
グローバルサポートサービス
時間365日対応
過去35年以上にわたり、私たちのイノベーションは、テクノロジーを通じて、製造業の仕組みと、人々の関わり方を根本的に変えてきました。当社のSmartFactoryポートフォリオは、効率を最大化し、製造オペレーションを強化するように設計された総合自動化ソフトウェアソリューションを提供します。
## イノベーションを加速する
生産性向上、工程品質改善、MES統合、サプライチェーン管理など、企業計画から生産管理までのサービスを提供します。
AIを活用した自動化と高度なスケジューリング技術により、製造業はパフォーマンスを向上させ、生産フローを最適化し、ダウンタイムを最小限に抑え、継続的な改善を推進することができます。当社の総合的なアプローチは、オペレーションのシームレスな監視と制御を可能にします。
## 未来への道
工場の自動化における当社の専門知識は、AI、ビッグデータ、クラウド技術におけるブレークスルーを促進し、製造業者が大きな競争優位性を獲得することを可能にします。
先見の明を持つエンジニアや科学者といった世界屈指の頭脳が、材料工学の専門知識と多様な意見、経験、経歴をアプライド マテリアルズに結集することで、より優れたアイデアと画期的なイノベーションを実現します。
## オートメーションのモダナイズ
SmartFactoryは、オートメーションのモダナイゼーションを実現するために、実用的かつ段階的なアプローチを提供します。製造現場は、無理のないステップで着実にパフォーマンスを向上させながら、リスクを抑えつつ、継続的に成果を可視化できます。
このアプローチにより、ビジネスの優先度や現場の準備状況、長期的な目標に合わせたペースでモダナイゼーションを推進可能。大規模な一括変革による混乱を招くことなく、スムーズな移行を実現します。
## 当社のエキスパートによる業界の洞察
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)### Quality Quest: Insights from the Fab
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)### Performance Pioneers: Factory Innovations
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)### Smart Manufacturing: The Evolutionary Edge
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)### SPC Strategies: Realizing Excellence
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)### MES Integration: Uniquely SmartFactory
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)### Human-Centric Solutions: SmartFactory’s Approach
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)### Innovation Integration: Seizing New Opportunities
[](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)### Efficiency Unleashed: Optimizing the Fab
### SmartFactory、数々の貢献が評価され各賞を受賞
#### Award of Excellence
#### STMicroelectronics Award
#### Best Cooperative Supplier
#### Excellent Supplier
---
### [Support Contacts](https://appliedsmartfactory.com/support-contacts/)
**Published:** December 3, 2021
**Author:** Applied Smartfactory
**Content:**
グローバルサポート
# 地域別連絡先一覧
## 包括的なグローバルソフトウェアサポート
サービス
### 有資格エンジニアによる グローバルサポート
- ソフトウェアの問題のトラブル
シューティング
- 機能や機能性に関する質問への
対応
- 既知のベストナレッジメソッド（BKM）の支援
### カスタマートレーニング
- 機能/機能性のデモ
- 実践的な指導とトレーニング
セッション
- オプションで提供可能な
トレーニング内容：
- 教室形式（顧客またはアプライドのサイトで）
- オンライン/バーチャルライブ教室
- 自習用トレーニング資料
### ソフトウェアポータルで保守契約中のお客様が以下のサービスを受けられる：
- 最新のGAリリースとパッチ
- 製品関連のお知らせ
- ソフトウェアサポートのエキスパートへのアクセス
## 追加のサポートが必要な場合は、お住まいの地域のサポートセンターまで連絡してください：
日本
北アメリカ
ヨーロッパ
中国
韓国
東南アジア
台湾
日本
### 日本
営業時間 午前9:00～午後5:30 (GMT+9、夏時間なし)
#### Yoshio Oikawa, AMJ Regional Manager
[ Yoshio\_oikawa@amat.com]()
[ +81-3-6812-6293](tel:+81368126293)
[ +81-90-5197-0014](tel:+819051970014)
#### AutoMod/AutoSched
[ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support\_jp@amat.com](mailto:apf_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### E3 Platform / FDC / R2R
[ e3\_support\_jp@amat.com](mailto:e3_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### CLASS MCS 5
[ mcs\_support\_jp@amat.com](mailto:mcs_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### MES製品
[ mes\_support\_jp@amat.com]()
[ +81-52-238-2801](tel:+81522382801)
#### 全製品
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
[ +81-52-238-2801](tel:+81522382801)
北アメリカ
### 北アメリカ
営業時間 午前7:00～午後6:00（米国山岳部時間）
#### Satish Baskaran, AMNA Regional Manager
[ satish\_baskaran@amat.com]()
[ +1-408-584-0022](tel:+14085840022)
[ +1-408-757-6851](tel:+14087576851)
#### 300works
[ 300works\_support@amat.com](mailto:300works_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoMod
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoSched AP
[ autoschedap\_support@amat.com](mailto:autoschedap_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### CELLworks
[ cellworks\_support@amat.com](mailto:cellworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### CLASS MCS 5
[ classmcs5\_support@amat.com](mailto:classmcs5_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### E3 Platform / FDC / R2R
[ e3\_support@amat.com](mailto:e3_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### FAB300
9:00 AM – 6:00 PM PT
[ crc\_fab300@amat.com](mailto:crc_fab300@amat.com)
*For FAB-down situations, Platinum customers should use the contact number given by Support*
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### iDurables
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Maintenance Management (Xsite)
[ xsite\_support@amat.com](mailto:xsite_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Productivity Solutions
[ productivity\_support@amat.com](mailto:productivity_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### PROMIS
8:00 AM – 8:00 PM ET
[ promis\_support@amat.com](mailto:promis_support@amat.com)
[ 800-784-6778](tel:8007846778)
#### Sentinel
[ sentinel\_support@amat.com](mailto:sentinel_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SF Rx Support
[ SF\_Rx\_Support@amat.com](mailto:SF_Rx_Support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SPACE
[ space\_support@amat.com](mailto:space_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### STATIONworks
[ stationworks\_support@amat.com](mailto:stationworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
ヨーロッパ
### ヨーロッパ
営業時間 午前7:00～午後6:00（GMT）
#### Antoine Carlier, AME Regional Manager
[ antoine\_carlier@amat.com]()
[ +33-476-04-29-19](tel:tel:+33476042919)
[ +33-607-87-77-76](tel:+33607877776)
#### 全製品
[ eur\_customersupport@amat.com](mailto:eur_customersupport@amat.com)
[ +44-118-931-5678](tel:+441189315678)
中国
### 中国
営業時間 午前7:00～午後6:00（GMT+8）
#### Michael Gao, AMC Regional Manager
[ michael\_gao@amat.com]()
[ +86-29-68917000](tel:+862968917000)
[ +86-29-68917138](tel:+862968917138)
[ +86-18101883550](tel:+8618101883550)
#### 全製品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +86-21-58958985 x 1190](tel:+862158958985x1190)
韓国
### 韓国
営業時間 午前8:30～午後5:30（GMT+9、夏時間なし）
#### William Kang, AMK Regional Manager
[ William\_Kang@amat.com]()
[ +82-31-724-5000](tel:+82317245000)
[ +82-10-6340-2706](tel:+821063402706)
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ +82-31-724-5000](tel:+82317245000)
#### 全製品
[ MAS\_JKR\_SWsupport@amat.com](mailto:MAS_JKR_SWsupport@amat.com)
[ +82-31-724-5000](tel:+82317245000)
東南アジア
### 東南アジア
営業時間 午前9:00～午後5:00
#### Kwee Thiam Lim, AMSEA Regional Manager
[ kwee-thiam\_lim@amat.com](mailto:kwee-thiam_lim@amat.com)
[ +65-63117306](tel:+6563117306)
[ +65-97843991](tel:+6597843991)
#### 全製品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +65-63117311](tel:+6563117311)
台湾
### 台湾
営業時間 午前8:30～午後5:30 (GTM+8)
#### James Chang, AMT Regional Manager
[ James\_SC\_Chang@amat.com ]()
[ +886 35793185](tel:+88635793185)
[ +886 936259648](tel:+886936259648)
#### 全製品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +886-3-5793111](tel:+88635793111)
## 追加のサポートが必要な場合は、お住まいの地域のサポートセンターまで連絡してください：
日本
### 日本
営業時間 午前9:00～午後5:30（GMT+9、夏時間なし）
#### Yoshio Oikawa, AMJ Regional Manager
[ Yoshio\_oikawa@amat.com](mailto:Yoshio_oikawa@amat.com)
[ +81-3-6812-6293](tel:+81368126293)
[ +81-90-5197-0014](tel:+819051970014)
#### AutoMod/AutoSched
[ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support\_jp@amat.com](mailto:apf_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### E3 Platform / FDC / R2R
[ e3\_support\_jp@amat.com](mailto:e3_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### CLASS MCS 5
[ mcs\_support\_jp@amat.com](mailto:mcs_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### MES製品
[ mes\_support\_jp@amat.com](mailto:mes_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### 全製品
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
[ +81-52-238-2801](tel:+81522382801)
北アメリカ
### 北アメリカ
営業時間 午前7:00～午後6:00（米国山岳部時間）
#### Satish Baskaran, AMNA Regional Manager
[ satish\_baskaran@amat.com](mailto:satish_baskaran@amat.com)
[ +1-408-584-0022](tel:+14085840022)
[ +1-408-757-6851](tel:+14087576851)
#### 300works
[ 300works\_support@amat.com](mailto:300works_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Activity Manager / APF Reporter / RTD / SmartFactory Productivity Solutions
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoMod
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoSched AP
[ autoschedap\_support@amat.com](mailto:autoschedap_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### CELLworks
[ cellworks\_support@amat.com](mailto:cellworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### CLASS MCS 5
[ classmcs5\_support@amat.com](mailto:classmcs5_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### E3 Platform / FDC / R2R
[ e3\_support@amat.com](mailto:e3_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### FAB300
9:00 AM – 6:00 PM PT
[ crc\_fab300@amat.com](mailto:crc_fab300@amat.com)
*For FAB-down situations, Platinum customers should use the contact number given by Support*
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### iDurables
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Maintenance Management (Xsite)
[ xsite\_support@amat.com](mailto:xsite_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Productivity Solutions
[ productivity\_support@amat.com](mailto:productivity_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### PROMIS
8:00 AM – 8:00 PM ET
[ promis\_support@amat.com](mailto:promis_support@amat.com)
[ 800-784-6778](tel:8007846778)
#### Sentinel
[ sentinel\_support@amat.com](mailto:sentinel_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SF Rx Support
[ SF\_Rx\_Support@amat.com](mailto:SF_Rx_Support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SPACE
[ space\_support@amat.com](mailto:space_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### STATIONworks
[ stationworks\_support@amat.com](mailto:stationworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
ヨーロッパ
### ヨーロッパ
営業時間 午前7:00～午後6:00（GMT）
#### Antoine Carlier, AME Regional Manager
[ antoine\_carlier@amat.com](mailto:antoine_carlier@amat.com)
[ +33-476-04-29-19](tel:tel:+33476042919)
[ +33-607-87-77-76](tel:+33607877776)
#### 全製品
[ eur\_customersupport@amat.com](mailto:eur_customersupport@amat.com)
[ +44-118-931-5678](tel:+441189315678)
中国
### 中国
営業時間 午前7:00～午後6:00（GMT+8）
#### Michael Gao, AMC Regional Manager
[ michael\_gao@amat.com](mailto:michael_gao@amat.com)
[ +86-29-68917000](tel:+862968917000)
[ +86-29-68917138](tel:+862968917138)
[ +86-18101883550](tel:+8618101883550)
#### 全製品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +86-21-58958985 x 1190](tel:+862158958985x1190)
韓国
### 韓国
営業時間 午前8:30～午後5:30 （GMT+9、夏時間なし）
#### William Kang, AMK Regional Manager
[ William\_Kang@amat.com](mailto:William_Kang@amat.com)
[ +82-31-724-5000](tel:+82317245000)
[ +82-10-6340-2706](tel:+821063402706)
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ +82-31-724-5000](tel:+82317245000)
#### 全製品
[ MAS\_JKR\_SWsupport@amat.com](mailto:MAS_JKR_SWsupport@amat.com)
[ +82-31-724-5000](tel:+82317245000)
東南アジア
### 東南アジア
営業時間 午前9:00～午後5:00
#### Kwee Thiam Lim, AMSEA Regional Manager
[ kwee-thiam\_lim@amat.com](mailto:kwee-thiam_lim@amat.com)
[ +65-63117306](tel:+6563117306)
[ +65-97843991](tel:+6597843991)
#### 全製品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +65-63117311](tel:+6563117311)
台湾
### 台湾
営業時間 午前8:30～午後5:30 (GTM+8)
#### James Chang, AMT Regional Manager
[ James\_SC\_Chang@amat.com ](mailto:James_SC_Chang@amat.com)
[ +886 35793185](tel:+88635793185)
[ +886 936259648](tel:+886936259648)
#### 全製品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +886-3-5793111](tel:+88635793111)
---
### [支持中心联系方式](https://appliedsmartfactory.com/support-contacts/)
**Published:** December 9, 2021
**Author:** Applied Smartfactory
**Content:**
全球支持
# 联系方式
## 全方位服务全球软件支持服务
### 获取全球资深工程师支持
- 解决软件问题
- 解决特性和功能问题
- 通过已知的BKM提供协助
### 客户培训
- 特性/功能演示
- 实践指导和培训课程
- 培训选项可能包括：
- 授课地点（在客户处或应用材料办事处）
- 线上/直播课堂
- 自学培训材料
### 购买维保服务的用户登录后可获取：
- 最新的GA版本和补丁
- 产品相关公告
- 软件支持专家的途径
## 如需更多帮助，请选择您所在的地区：
北美
欧洲
中国
日本
韩国
东南亚
中国台湾
北美
### 北美
工作时间：上午 7:00 – 下午 18:00，山地时区
#### 300works
[ 300works\_support@amat.com](mailto:300works_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Activity Manager
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### APF RTD/Reporter
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoMod
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoSched AP
[ autoschedap\_support@amat.com](mailto:autoschedap_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### CELLworks
[ cellworks\_support@amat.com](mailto:cellworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### CLASS MCS 5
[ classmcs5\_support@amat.com](mailto:classmcs5_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### E3 Platform / FDC / R2R
[ e3\_support@amat.com](mailto:e3_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### FAB300
工作时间：上午 9：00 – 下午 18:00，太平洋时区
[ crc\_fab300@amat.com](mailto:crc_fab300@amat.com)
*对于FAB停机情况，铂金客户请拨打支持部门提供的联系电话*
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### iDurables
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### OCAPS
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Patterns
[ patterns\_support@amat.com](mailto:patterns_support@amat.com)
[ 978-394-7725](tel:9783947725)
#### PROMIS
工作时间：上午 8:00 – 下午 20:00，美国东部时间
[ promis\_support@amat.com](mailto:promis_support@amat.com)
[ 800-784-6778](tel:8007846778)
#### Sentinel
[ sentinel\_support@amat.com](mailto:sentinel_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SF Rx Support
[ SF\_Rx\_Support@amat.com](mailto:SF_Rx_Support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SPACE
[ space\_support@amat.com](mailto:space_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### STATIONworks
[ stationworks\_support@amat.com](mailto:stationworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### WinSECS
[ winsecs\_support@amat.com](mailto:winsecs_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Xsite
[ xsite\_support@amat.com](mailto:xsite_support@amat.com)
[ 978-795-8011](tel:9787958011)
欧洲
### 欧洲
工作时间：上午 8:00 – 下午 17:00，格林威治时间
#### 所有产品
[ eur\_customersupport@amat.com](mailto:eur_customersupport@amat.com)
[ +44-118-931-5678](tel:+441189315678)
中国
### 中国
工作时间：上午 8:30 – 下午 17:00
#### 所有产品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +86-21-58958985 x1190](tel:+862158958985x1190)
日本
### 日本
工作时间：上午 9:00 – 下午 17:30 （东9区，没有夏令时）
#### AutoMod/AutoSched
[ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### Activity Manager / APF Reporter / RTD
[ apf\_support\_jp@amat.com](mailto:apf_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### E3 Platform / FDC / R2R
[ e3\_support\_jp@amat.com](mailto:e3_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### CLASS MCS 5
[ mcs\_support\_jp@amat.com](mailto:mcs_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### MES 产品
[ mes\_support\_jp@amat.com]()
[ +81-52-238-2801](tel:+81522382801)
#### 所有产品
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
[ +81-52-238-2801](tel:+81522382801)
韩国
### 韩国
工作时间：上午 8:30 – 下午17:30 （东9区，没有夏令时）
#### William Kang, AMK Regional Manager
[ William\_Kang@amat.com](mailto:William_Kang@amat.com)
[ +82-31-724-5000](tel:+82317245000)
[ +82-10-6340-2706](tel:+821063402706)
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ +82-31-724-5000](tel:+82317245000)
#### 所有其他产品
[ MAS\_JKR\_SWsupport@amat.com](mailto:MAS_JKR_SWsupport@amat.com)
[ +82-31-724-5000](tel:+82317245000)
东南亚
### 东南亚
工作时间：上午 9:00 – 下午 17:00
#### 所有产品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +65-63117311](tel:+6563117311)
中国台湾
### 中国台湾
工作时间：上午 8:30 – 下午 17:30
#### 所有产品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +886-3-5793111](tel:+88635793111)
## 如需更多帮助，请选择您所在的地区：
北美
### 北美
工作时间：上午 7:00 – 下午 18:00，山地时区
#### 300works
[ 300works\_support@amat.com](mailto:300works_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Activity Manager
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### APF RTD/Reporter
[ apf\_support@amat.com](mailto:apf_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoMod
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### AutoSched AP
[ autoschedap\_support@amat.com](mailto:autoschedap_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### CELLworks
[ cellworks\_support@amat.com](mailto:cellworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### CLASS MCS 5
[ classmcs5\_support@amat.com](mailto:classmcs5_support@amat.com)
[ 801-736-3300](tel:8017363300)
#### E3 Platform / FDC / R2R
[ e3\_support@amat.com](mailto:e3_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### FAB300
工作时间：上午 9：00 – 下午 18:00，太平洋时区
[ crc\_fab300@amat.com](mailto:crc_fab300@amat.com)
*对于FAB停机情况，铂金客户请拨打支持部门提供的联系电话*
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### iDurables
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### OCAPS
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Patterns
[ patterns\_support@amat.com](mailto:patterns_support@amat.com)
[ 978-394-7725](tel:9783947725)
#### PROMIS
工作时间：上午 8:00 – 下午 20:00，美国东部时间
[ promis\_support@amat.com](mailto:promis_support@amat.com)
[ 800-784-6778](tel:8007846778)
#### Sentinel
[ sentinel\_support@amat.com](mailto:sentinel_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SF Rx Support
[ SF\_Rx\_Support@amat.com](mailto:SF_Rx_Support@amat.com)
[ 408-563-7798](tel:4085637798)
#### SPACE
[ space\_support@amat.com](mailto:space_support@amat.com)
[ 408-563-7798](tel:4085637798)
#### STATIONworks
[ stationworks\_support@amat.com](mailto:stationworks_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### WinSECS
[ winsecs\_support@amat.com](mailto:winsecs_support@amat.com)
[ 978-795-8011](tel:9787958011)
#### Xsite
[ xsite\_support@amat.com](mailto:xsite_support@amat.com)
[ 978-795-8011](tel:9787958011)
欧洲
### 欧洲
工作时间：上午 8:00 – 下午 17:00，格林威治时间
#### 所有产品
[ eur\_customersupport@amat.com](mailto:eur_customersupport@amat.com)
[ +44-118-931-5678](tel:+441189315678)
中国
### 中国
工作时间：上午 8:30 – 下午 17:00
#### 所有产品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +86-21-58958985 x1190](tel:+862158958985x1190)
日本
### 日本
工作时间：上午 9:00 – 下午 17:30 （东9区，没有夏令时）
#### AutoMod/AutoSched
[ sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### Activity Manager / APF Reporter / RTD
[ apf\_support\_jp@amat.com](mailto:apf_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### E3 Platform / FDC / R2R
[ e3\_support\_jp@amat.com](mailto:e3_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### CLASS MCS 5
[ mcs\_support\_jp@amat.com](mailto:mcs_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### MES 产品
[ mes\_support\_jp@amat.com](mailto:mes_support_jp@amat.com)
[ +81-52-238-2801](tel:+81522382801)
#### 所有产品
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
[ +81-52-238-2801](tel:+81522382801)
韩国
### 韩国
工作时间：上午 8:30 – 下午17:30 （东9区，没有夏令时）
#### William Kang, AMK Regional Manager
[ William\_Kang@amat.com](mailto:William_Kang@amat.com)
[ +82-31-724-5000](tel:+82317245000)
[ +82-10-6340-2706](tel:+821063402706)
#### FACTORYworks
[ factoryworks\_support@amat.com](mailto:factoryworks_support@amat.com)
[ +82-31-724-5000](tel:+82317245000)
#### 所有其他产品
[ MAS\_JKR\_SWsupport@amat.com](mailto:MAS_JKR_SWsupport@amat.com)
[ +82-31-724-5000](tel:+82317245000)
东南亚
### 东南亚
工作时间：上午 9:00 – 下午 17:00
#### 所有产品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +65-63117311](tel:+6563117311)
中国台湾
### 中国台湾
工作时间：上午 8:30 – 下午 17:30
#### 所有产品
[ MAS\_CSR\_SWSupport@amat.com](mailto:MAS_CSR_SWSupport@amat.com)
[ +886-3-5793111](tel:+88635793111)
---
### [Battery Events](https://appliedsmartfactory.com/battery-events/)
**Published:** May 13, 2025
**Author:** Applied Smartfactory
**Content:**
# バッテリー関連イベント
当社の自動化のエキスパートと提携して、バッテリー製造のアドバンテージを迅速に実現しましょう。
## 今後のイベント
There are no upcoming events. Please check later.
## 過去のイベント
### [Cut Downtime in Battery Manufacturing](https://appliedsmartfactory.com/events/battery/agnes-sowa-at-battery-tech-theatre/)
Oct 8, 2025 | 10:00 – 10:45 am Eastern
Battery Tech Theater | Booth 6050
The Battery Show | Detroit, MI
### [Battery + Energy Storage Conference](https://www.aiche.org/cei/conferences/battery-and-energy-storage-conference/2025)
Sep 23-25, 2025
| Lemont, IL
Join scientists, engineers, and policy makers to communicate technology advancements in storage materials, devices, and systems.
### [The Battery Show Europe](https://www.thebatteryshow.eu/en/conference/conference-overview.html/)
June 3-5, 2025
| Stuttgart, Germany
See over 1,100 leading suppliers from the rapidly growing advanced battery and H/EV industry.
---
### [Battery Events](https://appliedsmartfactory.com/battery-events/)
**Published:** May 13, 2025
**Author:** Applied Smartfactory
**Content:**
# Battery Events
Engage with our automation technology experts to gain a competitive advantage in battery manufacturing.
## Upcoming events
There are no upcoming events. Please check later.
## Past events
### [Cut Downtime in Battery Manufacturing](https://appliedsmartfactory.com/events/battery/agnes-sowa-at-battery-tech-theatre/)
### [Battery + Energy Storage Conference](https://www.aiche.org/cei/conferences/battery-and-energy-storage-conference/2025)
Sep 23-25, 2025
| Lemont, IL
### [The Battery Show Europe](https://www.thebatteryshow.eu/en/conference/conference-overview.html/)
June 3-5, 2025
| Stuttgart, Germany
---
### [Semiconductor Events](https://appliedsmartfactory.com/semiconductor-events/)
**Published:** July 17, 2024
**Author:** Jill Oana
**Content:**
# 半導体イベント
半導体製造の未来を切り拓くために、SmartFactoryの自動化技術のエキスパートと共に一歩を踏み出しませんか？
## 今後のイベント
### [SmartFactory Symposium India 2026](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
September 18, 2026
[ Register Now ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
### [A New Design Mindset to Enable AI-Driven Factory Automation](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
October 15, 2026
[ More Info ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
### [SEMICON Europa](https://www.semiconeuropa.org/)
November 10-13, 2026
| Munich, Germany
[ More Info ](https://www.semiconeuropa.org/)
### SmartFactory Symposium Japan 2026
December 8, 2026
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2026/)
December 6-9, 2026
| Glasgow, Scotland
[ More Info ](https://meetings.informs.org/wordpress/wsc2026/)
### [SmartFactory Webinar Replays](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
Available 24/7
[ More Info ](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
## 過去のイベント
### [SEMICON Taiwan](https://semicontaiwan.org/en)
September 2-4, 2026
| Taipei, Taiwan
### [Penang Manufacturing Expo](https://penang-expo.com/)
July 22-24, 2026
| Penang, Malaysia
### [SmartFactory Symposium Penang](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-symposium-penang/)
July 16, 2026
Manufacturers will learn how to elevate performance, optimize production flow, and minimize downtime with our AI-powered automation and advanced scheduling technologies.
USER GROUP
### SmartFactory Maintenance Management Virtual User Group
July 15, 2026
| Virtual
**Customer-Only Event**
USER GROUP
### SmartFactory MES Virtual User Group
July 1, 2026
| Virtual
**Customer-Only Event**
WEBINAR
### SmartFactory Process Quality Webinar
June 16, 2026
| Virtual
WEBINAR
### SmartFactory Defect Classification (ADC) Webinar
June 3, 2026
| Virtual
WEBINAR
### SmartFactory End-to-End Quality 360 Webinar
May 20, 2026
| Virtual
### [Advanced Semiconductor Manufacturing Conference](https://appliedsmartfactory.com/events/semiconductor-event/asmc)
May 11-14, 2026
| Albany, New York
ASMC unites manufacturers, suppliers, and academia to tackle manufacturing challenges with innovative strategies.
### [apc|m Europe](https://www.apcm-europe.eu/)
April 28-30, 2026
| Catania, Sicily, Italy
Topics: process level APC, smart manufacturing, manufacturing effectiveness, packaging & smart integration.
WEBINAR
### SmartFactory AI Webinar
April 21, 2026
| Virtual
**Customer-Only Event**
### APF Virtual User Group
March 11/12, 2026
2 sessions, identical content
Customer-Only Event!
Topics: product roadmaps, new features, user story reviews: APF RTD®, Activity Manager®, AutoSched®, and Productivity
solutions—powered by AI and Cloud Innovations.
### [SmartFactory Maintenance Management Webinar](https://appliedsmartfactory.com/events/semiconductor/smartfactory-maintenance-management-webinar/)
February 10, 2026
Join us as we discuss our approach to accelerating G2G, including through AI advancements.
### [Innovation Forum for Automation](https://appliedsmartfactory.com/events/semiconductor/innovation-forum-automation-2026/)
Jan 29-30, 2026
| Dresden, Germany
**Platinum Sponsor | Keynote & Live Demos**
Experience how SmartFactory solutions are shaping the future of automation.
### [SMART FACTORY Expo Japan](https://appliedsmartfactory.com/events/semiconductor/smart-factory-expo-japan/)
Jan 21-23, 2026
| Tokyo, Japan
Explore AI-driven automation—Visit our booth S15-30 for live demo.
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2025/)
Dec 7-10, 2025
| Seattle, WA
Look to the future. Simulation 2050 and beyond.
### [Boost Manufacturing with AI + Digital Twin](https://appliedsmartfactory.com/events/semiconductor/boost-manufacturing-with-ai-digital-twin/)
SmartFactory Japan Webinar
December 9, 2025
See practical solutions in action and uncover new possibilities with Gen AI
### [See Vishali Ragam at the
AEC/APC Symposium Asia](https://appliedsmartfactory.com/events/semiconductor/aec-apc-symposium-2025/)
Nov 26, 2025 | 10:10-10:30 am
Fukuoka, Japan
Learn how SmartFactory is transforming process control by combining SPC, FDC, and AI-powered Visual Language Models (VLMs).
### [Alarm Containment to Resolution Webinar](https://appliedsmartfactory.com/events/semiconductor/alarm-containment-to-resolution-webinar/)
November 25, 2025
Discover how alarms can be a foundation for smarter, safer, and more efficient operations.
### [SmartFactory MES 300works® Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-mes-300works-virtual-user-group/)
October 28, 2025
Discover AI in MES, roadmap updates, security enhancements, and FactoryView dashboards
### [SmartFactory PROMIS® Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/promis-virtual-user-group/)
October 14 & 15, 2025
(two sessions | same content)
Explore roadmap updates, Red Hat Linux migration, and integration options. Hear from a customer who recently migrated PROMIS to Red Hat Linux.
### [Digital Twins in Manufacturing](https://appliedsmartfactory.com/events/semiconductor/digital-twin-standards-by-sj-wang/)
Oct 9, 2025 | 9:45 am–12:15 pm
Arizona State University
(Polytechnic Campus)
**Project Planning Workshop**
SJ Wang shares how AppliedTwin helps fabs act faster with real-time insights.
### [Smart Manufacturing Lunch Session](https://appliedsmartfactory.com/events/semiconductor/semicon-west-2025/)
Tue Oct 7, 2025 | 1:00–2:00 pm MT
Smart Manufacturing Pavilion Theater
North Building, Lower Level, Expo Floor
**Ecosystem-Connected Digital Twins: Transforming Semi Fabs with NVIDIA Omniverse** Join Scott Rothenberg and industry leaders to explore how digital twins are shaping the future of smart manufacturing.
### [SmartFactory Asset Trace Webinar](https://appliedsmartfactory.com/events/semiconductor/smartfactory-asset-trace-webinar/)
September 17, 2025
(two sessions | same content)
Discover how automating mobile asset tracking can drive quality and efficiency in your fab.
### [SmartFactory Symposium India](https://appliedsmartfactory.com/events/semiconductor/symposiumindia2025/)
Wed Sep 3 at 1 – 4 pm
IICC Conference Room 404-A
### [Advanced Semiconductor Manufacturing Conference – 2025](https://appliedsmartfactory.com/events/semiconductor/asmc/)
May 5-8, 2025
| Albany, New York
ASMC unites manufacturers, suppliers, and academia to tackle manufacturing challenges with innovative strategies.
### [2025 apc|m Europe](https://appliedsmartfactory.com/events/semiconductor/apc-europe-2025/)
April 8-10, 2025
| Prague, Czech Republic
Topics covered: autonomous systems, AI, cloud transformation, cybersecurity, product development, and more.
### SmartFactory Symposium 2025
March 27, 2025
| Shanghai, China
Special event for customers, featuring presentations, technical sessions, user stories, and live product demos.
### [SmartFactory Durables Management Webinar: Unlocking the Power of Automation](https://appliedsmartfactory.com/events/semiconductor/smartfactory-durables-management-webinar/)
February 19, 2025
2 sessions, identical content
Maximize efficiency of your assets through durables and consumables management.
### [22nd Innovation Forum for Automation](https://appliedsmartfactory.com/events/semiconductor/innovation-forum-automation-2025/)
Jan 30-31, 2025
| Dresden, Germany
Are you passionate about automation in high-tech manufacturing? Join us!
### [SMART FACTORY Expo – Tokyo 2025](https://appliedsmartfactory.com/events/semiconductor/smart-factory-expo-japan-2025/)
Jan 22-24, 2025
| Tokyo
Visit Booth S30-14 to see our live solution demos, explore real-world use cases, and meet our team of technology experts.
### [2024 Winter Simulation Conference](https://appliedsmartfactory.com/events/semiconductor-event/winter-simulation-conference-2024/)
Dec 15-18, 2024
| Orlando,FL
Simulation for the Imagination Age: Unlocking the value of imagination with simulation
### [APF Webinar: SmartFactory AI Productivity and RTD Private Cloud](https://appliedsmartfactory.com/events/semiconductor/apf-webinar-ai-productivity-rtd-private-cloud/)
December 11/12, 2024
2 sessions, identical content
Learn about our AI and Cloud capabilities, showcasing real-world use cases, live demos, and more.
### [SmartFactory PROMIS® MES Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-promis-mes-vug/)
October 29/30, 2024
2 sessions, identical content
Learn about the latest PROMIS updates, roadmap, and recent customer experiences
### [Advanced Process Control Smart Manufacturing Conference](https://appliedsmartfactory.com/events/semiconductor/apcsm-conference-2024/)
Oct 7-10, 2024
| Toronto, Canada
Enable you to experience firsthand the latest advancements in technology
### [SmartFactory E3 and APF Joint User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-e3-user-group/)
Sep 25-26, 2024
| Prague, Czech Republic
Attend our SmartFactory E3 and APF Joint User Group
### [SEMICON India](https://appliedsmartfactory.com/events/semiconductor/semicon-india-2024/)
Sep 11-13, 2024
| Delhi, India
Shaping the Semiconductor Future
### [SmartFactory Symposium Malaysia](https://appliedsmartfactory.com/events/semiconductor/malaysiasymposium2024/)
Jul 25, 2024
| Penang, Malaysia
Unleashing the Power of Applied SmartFactory Software
### [Automating the Manual: SmartFactory Durables Management Webinar](https://appliedsmartfactory.com/webinars/semiconductor/automating-the-manual/)
May 20-21, 2024
### [SmartFactory SPC: Mastering Quality Webinar](https://appliedsmartfactory.com/webinars/semiconductor/smartfactory-spc-mastering-quality/)
May 16-17, 2024
### SmartFactory Productivity User Group
Apr 24-25, 2024
| Virtual
### [SEMI Pacific Northwest Chapter Forum](https://www.semi.org/en/semi-americas/pacific-northwest-chapter)
Apr 25, 2024
| Portland, OR
### SmartFactory Maintenance Management User Group
Apr 16-18,2024
| Virtual
### [apc | Europe Conference](https://appliedsmartfactory.com/apceurope2024/)
Apr 16-18, 2024
| Hamburg, Germany
### SmartFactory Materials Control User Group
Apr 10-11, 2024
| Virtual
### [Innovation Forum for Automation](https://appliedsmartfactory.com/innovationforum2024/)
Jan 25-26, 2024
| Dresden, Germany
### [SMART FACTORY EXPO | Factory Innovation Week](https://www.fiweek.jp/hub/en-gb/previous.html#tokyo)
Jan 24-26, 2024
| Tokyo Big Sight, Japan
### [SEMICON Japan 2023](https://www.semiconjapan.org/en)
Dec 13, 2023
| Tokyo Big Sight, Japan
### [AEC/APC Symposium Asia 2023](https://www.semiconportal.com/AECAPC/index_e.html)
Nov 2, 2023
| Tokyo, Japan
---
### [半导体行业活动](https://appliedsmartfactory.com/semiconductor-events/)
**Published:** July 17, 2024
**Author:** Jill Oana
**Content:**
# 半导体行业活动
对话工厂自动化技术专家，赢取半导体制造竞争优势。
## 重磅活动预告
### [SmartFactory Symposium India 2026](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
September 18, 2026
[ Register Now ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
### [A New Design Mindset to Enable AI-Driven Factory Automation](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
October 15, 2026
[ More Info ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
### [SEMICON Europa](https://www.semiconeuropa.org/)
November 10-13, 2026
| Munich, Germany
[ More Info ](https://www.semiconeuropa.org/)
### SmartFactory Symposium Japan 2026
December 8, 2026
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2026/)
December 6-9, 2026
| Glasgow, Scotland
[ More Info ](https://meetings.informs.org/wordpress/wsc2026/)
### [SmartFactory Webinar Replays](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
Available 24/7
[ More Info ](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
## 精彩活动回顾
### [SEMICON Taiwan](https://semicontaiwan.org/en)
September 2-4, 2026
| Taipei, Taiwan
### [Penang Manufacturing Expo](https://penang-expo.com/)
July 22-24, 2026
| Penang, Malaysia
### [SmartFactory Symposium Penang](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-symposium-penang/)
July 16, 2026
USER GROUP
### SmartFactory Maintenance Management Virtual User Group
July 15, 2026
| Virtual
**Customer-Only Event**
USER GROUP
### SmartFactory MES Virtual User Group
July 1, 2026
| Virtual
**Customer-Only Event**
WEBINAR
### SmartFactory Process Quality Webinar
June 16, 2026
| Virtual
WEBINAR
### SmartFactory Defect Classification (ADC) Webinar
June 3, 2026
| Virtual
WEBINAR
### SmartFactory End-to-End Quality 360 Webinar
May 20, 2026
| Virtual
### [Advanced Semiconductor Manufacturing Conference](https://appliedsmartfactory.com/events/semiconductor-event/asmc)
May 11-14, 2026
| Albany, New York
### [apc|m Europe](https://www.apcm-europe.eu/)
April 28-30, 2026
| Catania, Sicily, Italy
WEBINAR
### SmartFactory AI Webinar
April 21, 2026
| Virtual
**Customer-Only Event**
### APF Virtual User Group
March 11/12, 2026
2 sessions, identical content
### [SmartFactory Maintenance Management Webinar](https://appliedsmartfactory.com/events/semiconductor/smartfactory-maintenance-management-webinar/)
February 10, 2026
### [Innovation Forum for Automation](https://appliedsmartfactory.com/events/semiconductor/innovation-forum-automation-2026/)
Jan 29-30, 2026
| Dresden, Germany
### [SMART FACTORY Expo Japan](https://appliedsmartfactory.com/events/semiconductor/smart-factory-expo-japan/)
Jan 21-23, 2026
| Tokyo, Japan
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2025/)
Dec 7-10, 2025
| Seattle, WA
### [Boost Manufacturing with AI + Digital Twin](https://appliedsmartfactory.com/events/semiconductor/boost-manufacturing-with-ai-digital-twin/)
SmartFactory Japan Webinar
December 9, 2025
### [See Vishali Ragam at the
AEC/APC Symposium Asia](https://appliedsmartfactory.com/events/semiconductor/aec-apc-symposium-2025/)
Nov 26, 2025 | 10:10-10:30 am
Fukuoka, Japan
### [Alarm Containment to Resolution Webinar](https://appliedsmartfactory.com/events/semiconductor/alarm-containment-to-resolution-webinar/)
November 25, 2025
### [SmartFactory MES 300works® Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-mes-300works-virtual-user-group/)
October 28, 2025
### [SmartFactory PROMIS® Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/promis-virtual-user-group/)
October 14 & 15, 2025
(two sessions | same content)
### [Digital Twins in Manufacturing](https://appliedsmartfactory.com/events/semiconductor/digital-twin-standards-by-sj-wang/)
Oct 9, 2025 | 9:45 am–12:15 pm
Arizona State University
(Polytechnic Campus)
### [Smart Manufacturing Lunch Session](https://appliedsmartfactory.com/events/semiconductor/semicon-west-2025/)
Tue Oct 7, 2025 | 1:00–2:00 pm MT
Smart Manufacturing Pavilion Theater
North Building, Lower Level, Expo Floor
### [SmartFactory Asset Trace Webinar](https://appliedsmartfactory.com/events/semiconductor/smartfactory-asset-trace-webinar/)
September 17, 2025
(two sessions | same content)
### [SmartFactory Symposium India](https://appliedsmartfactory.com/events/semiconductor/symposiumindia2025/)
Wed Sep 3 at 1 – 4 pm
IICC Conference Room 404-A
### [Advanced Semiconductor Manufacturing Conference – 2025](https://appliedsmartfactory.com/events/semiconductor/asmc/)
May 5-8, 2025
| Albany, New York
### [2025 apc|m Europe](https://appliedsmartfactory.com/events/semiconductor/apc-europe-2025/)
April 8-10, 2025
| Prague, Czech Republic
### SmartFactory Symposium 2025
March 27, 2025
| Shanghai, China
### [SmartFactory Durables Management Webinar: Unlocking the Power of Automation](https://appliedsmartfactory.com/events/semiconductor/smartfactory-durables-management-webinar/)
February 19, 2025
2 sessions, identical content
### [22nd Innovation Forum for Automation](https://appliedsmartfactory.com/events/semiconductor/innovation-forum-automation-2025/)
Jan 30-31, 2025
| Dresden, Germany
### [SMART FACTORY Expo – Tokyo 2025](https://appliedsmartfactory.com/events/semiconductor/smart-factory-expo-japan-2025/)
Jan 22-24, 2025
| Tokyo
### [2024 Winter Simulation Conference](https://appliedsmartfactory.com/events/semiconductor-event/winter-simulation-conference-2024/)
Dec 15-18, 2024
| Orlando,FL
### [APF Webinar: SmartFactory AI Productivity and RTD Private Cloud](https://appliedsmartfactory.com/events/semiconductor/apf-webinar-ai-productivity-rtd-private-cloud/)
December 11/12, 2024
2 sessions, identical content
### [SmartFactory PROMIS® MES Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-promis-mes-vug/)
October 29/30, 2024
2 sessions, identical content
### [Advanced Process Control Smart Manufacturing Conference](https://appliedsmartfactory.com/events/semiconductor/apcsm-conference-2024/)
Oct 7-10, 2024
| Toronto, Canada
### [SmartFactory E3 and APF Joint User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-e3-user-group/)
Sep 25-26, 2024
| Prague, Czech Republic
### [SEMICON India](https://appliedsmartfactory.com/events/semiconductor/semicon-india-2024/)
Sep 11-13, 2024
| Delhi, India
### [SmartFactory Symposium Malaysia](https://appliedsmartfactory.com/events/semiconductor/malaysiasymposium2024/)
Jul 25, 2024
| Penang, Malaysia
### [Automating the Manual: SmartFactory Durables Management Webinar](https://appliedsmartfactory.com/webinars/semiconductor/automating-the-manual/)
May 20-21, 2024
### [SmartFactory SPC: Mastering Quality Webinar](https://appliedsmartfactory.com/webinars/semiconductor/smartfactory-spc-mastering-quality/)
May 16-17, 2024
### SmartFactory Productivity User Group
Apr 24-25, 2024
| Virtual
### [SEMI Pacific Northwest Chapter Forum](https://www.semi.org/en/semi-americas/pacific-northwest-chapter)
Apr 25, 2024
| Portland, OR
### SmartFactory Maintenance Management User Group
Apr 16-18,2024
| Virtual
### [apc | Europe Conference](https://appliedsmartfactory.com/apceurope2024/)
Apr 16-18, 2024
| Hamburg, Germany
### SmartFactory Materials Control User Group
Apr 10-11, 2024
| Virtual
### [Innovation Forum for Automation](https://appliedsmartfactory.com/innovationforum2024/)
Jan 25-26, 2024
| Dresden, Germany
### [SMART FACTORY EXPO | Factory Innovation Week](https://www.fiweek.jp/hub/en-gb/previous.html#tokyo)
Jan 24-26, 2024
| Tokyo Big Sight, Japan
### [SEMICON Japan 2023](https://www.semiconjapan.org/en)
Dec 13, 2023
| Tokyo Big Sight, Japan
### [AEC/APC Symposium Asia 2023](https://www.semiconportal.com/AECAPC/index_e.html)
Nov 2, 2023
| Tokyo, Japan
---
### [Semiconductor Events](https://appliedsmartfactory.com/semiconductor-events/)
**Published:** July 17, 2024
**Author:** Jill Oana
**Content:**
# Semiconductor Events
Engage with our factory automation technology experts to gain a competitive advantage in semiconductor manufacturing.
## Upcoming events
### [SmartFactory Symposium India 2026](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
September 18, 2026
[ Register Now ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
### [A New Design Mindset to Enable AI-Driven Factory Automation](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
October 15, 2026
[ More Info ](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
### [SEMICON Europa](https://www.semiconeuropa.org/)
November 10-13, 2026
| Munich, Germany
[ More Info ](https://www.semiconeuropa.org/)
### SmartFactory Symposium Japan 2026
December 8, 2026
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2026/)
December 6-9, 2026
| Glasgow, Scotland
[ More Info ](https://meetings.informs.org/wordpress/wsc2026/)
### [SmartFactory Webinar Replays](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
Available 24/7
[ More Info ](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
## Past events
### [SEMICON Taiwan](https://semicontaiwan.org/en)
September 2-4, 2026
| Taipei, Taiwan
### [Penang Manufacturing Expo](https://penang-expo.com/)
July 22-24, 2026
| Penang, Malaysia
### [SmartFactory Symposium Penang](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-symposium-penang/)
July 16, 2026
USER GROUP
### SmartFactory Maintenance Management Virtual User Group
July 15, 2026
| Virtual
**Customer-Only Event**
USER GROUP
### SmartFactory MES Virtual User Group
July 1, 2026
| Virtual
**Customer-Only Event**
WEBINAR
### SmartFactory Process Quality Webinar
June 16, 2026
| Virtual
WEBINAR
### SmartFactory Defect Classification (ADC) Webinar
June 3, 2026
| Virtual
WEBINAR
### SmartFactory End-to-End Quality 360 Webinar
May 20, 2026
| Virtual
### [Advanced Semiconductor Manufacturing Conference](https://appliedsmartfactory.com/events/semiconductor-event/asmc)
May 11-14, 2026
| Albany, New York
### [apc|m Europe](https://www.apcm-europe.eu/)
April 28-30, 2026
| Catania, Sicily, Italy
WEBINAR
### SmartFactory AI Webinar
April 21, 2026
| Virtual
**Customer-Only Event**
### APF Virtual User Group
March 11/12, 2026
2 sessions, identical content
### [SmartFactory Maintenance Management Webinar](https://appliedsmartfactory.com/events/semiconductor/smartfactory-maintenance-management-webinar/)
February 10, 2026
### [Innovation Forum for Automation](https://appliedsmartfactory.com/events/semiconductor/innovation-forum-automation-2026/)
Jan 29-30, 2026
| Dresden, Germany
### [SMART FACTORY Expo Japan](https://appliedsmartfactory.com/events/semiconductor/smart-factory-expo-japan/)
Jan 21-23, 2026
| Tokyo, Japan
### [Winter Simulation Conference](https://meetings.informs.org/wordpress/wsc2025/)
Dec 7-10, 2025
| Seattle, WA
### [Boost Manufacturing with AI + Digital Twin](https://appliedsmartfactory.com/events/semiconductor/boost-manufacturing-with-ai-digital-twin/)
SmartFactory Japan Webinar
December 9, 2025
### [See Vishali Ragam at the
AEC/APC Symposium Asia](https://appliedsmartfactory.com/events/semiconductor/aec-apc-symposium-2025/)
Nov 26, 2025 | 10:10-10:30 am
Fukuoka, Japan
### [Alarm Containment to Resolution Webinar](https://appliedsmartfactory.com/events/semiconductor/alarm-containment-to-resolution-webinar/)
November 25, 2025
### [SmartFactory MES 300works® Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-mes-300works-virtual-user-group/)
October 28, 2025
### [SmartFactory PROMIS® Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/promis-virtual-user-group/)
October 14 & 15, 2025
(two sessions | same content)
### [Digital Twins in Manufacturing](https://appliedsmartfactory.com/events/semiconductor/digital-twin-standards-by-sj-wang/)
Oct 9, 2025 | 9:45 am–12:15 pm
Arizona State University
(Polytechnic Campus)
### [Smart Manufacturing Lunch Session](https://appliedsmartfactory.com/events/semiconductor/semicon-west-2025/)
Tue Oct 7, 2025 | 1:00–2:00 pm MT
Smart Manufacturing Pavilion Theater
North Building, Lower Level, Expo Floor
### [SmartFactory Asset Trace Webinar](https://appliedsmartfactory.com/events/semiconductor/smartfactory-asset-trace-webinar/)
September 17, 2025
(two sessions | same content)
### [SmartFactory Symposium India](https://appliedsmartfactory.com/events/semiconductor/symposiumindia2025/)
Wed Sep 3 at 1 – 4 pm
IICC Conference Room 404-A
### [Advanced Semiconductor Manufacturing Conference – 2025](https://appliedsmartfactory.com/events/semiconductor/asmc/)
May 5-8, 2025
| Albany, New York
### [2025 apc|m Europe](https://appliedsmartfactory.com/events/semiconductor/apc-europe-2025/)
April 8-10, 2025
| Prague, Czech Republic
### SmartFactory Symposium 2025
March 27, 2025
| Shanghai, China
### [SmartFactory Durables Management Webinar: Unlocking the Power of Automation](https://appliedsmartfactory.com/events/semiconductor/smartfactory-durables-management-webinar/)
February 19, 2025
2 sessions, identical content
### [22nd Innovation Forum for Automation](https://appliedsmartfactory.com/events/semiconductor/innovation-forum-automation-2025/)
Jan 30-31, 2025
| Dresden, Germany
### [SMART FACTORY Expo – Tokyo 2025](https://appliedsmartfactory.com/events/semiconductor/smart-factory-expo-japan-2025/)
Jan 22-24, 2025
| Tokyo
### [2024 Winter Simulation Conference](https://appliedsmartfactory.com/events/semiconductor-event/winter-simulation-conference-2024/)
Dec 15-18, 2024
| Orlando,FL
### [APF Webinar: SmartFactory AI Productivity and RTD Private Cloud](https://appliedsmartfactory.com/events/semiconductor/apf-webinar-ai-productivity-rtd-private-cloud/)
December 11/12, 2024
2 sessions, identical content
### [SmartFactory PROMIS® MES Virtual User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-promis-mes-vug/)
October 29/30, 2024
2 sessions, identical content
### [Advanced Process Control Smart Manufacturing Conference](https://appliedsmartfactory.com/events/semiconductor/apcsm-conference-2024/)
Oct 7-10, 2024
| Toronto, Canada
### [SmartFactory E3 and APF Joint User Group](https://appliedsmartfactory.com/events/semiconductor/smartfactory-e3-user-group/)
Sep 25-26, 2024
| Prague, Czech Republic
### [SEMICON India](https://appliedsmartfactory.com/events/semiconductor/semicon-india-2024/)
Sep 11-13, 2024
| Delhi, India
### [SmartFactory Symposium Malaysia](https://appliedsmartfactory.com/events/semiconductor/malaysiasymposium2024/)
Jul 25, 2024
| Penang, Malaysia
### [Automating the Manual: SmartFactory Durables Management Webinar](https://appliedsmartfactory.com/webinars/semiconductor/automating-the-manual/)
May 20-21, 2024
### [SmartFactory SPC: Mastering Quality Webinar](https://appliedsmartfactory.com/webinars/semiconductor/smartfactory-spc-mastering-quality/)
May 16-17, 2024
### SmartFactory Productivity User Group
Apr 24-25, 2024
| Virtual
### [SEMI Pacific Northwest Chapter Forum](https://www.semi.org/en/semi-americas/pacific-northwest-chapter)
Apr 25, 2024
| Portland, OR
### SmartFactory Maintenance Management User Group
Apr 16-18,2024
| Virtual
### [apc | Europe Conference](https://appliedsmartfactory.com/apceurope2024/)
Apr 16-18, 2024
| Hamburg, Germany
### SmartFactory Materials Control User Group
Apr 10-11, 2024
| Virtual
### [Innovation Forum for Automation](https://appliedsmartfactory.com/innovationforum2024/)
Jan 25-26, 2024
| Dresden, Germany
### [SMART FACTORY EXPO | Factory Innovation Week](https://www.fiweek.jp/hub/en-gb/previous.html#tokyo)
Jan 24-26, 2024
| Tokyo Big Sight, Japan
### [SEMICON Japan 2023](https://www.semiconjapan.org/en)
Dec 13, 2023
| Tokyo Big Sight, Japan
### [AEC/APC Symposium Asia 2023](https://www.semiconportal.com/AECAPC/index_e.html)
Nov 2, 2023
| Tokyo, Japan
---
### [Smart Manufacturing Faqs](https://appliedsmartfactory.com/smart-manufacturing-faqs/)
**Published:** April 9, 2024
**Author:** Applied Smartfactory
**Content:**
# よくある質問: スマート製造
#### Q: スマート製造とは何ですか？
A: スマート製造とは、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合し、データとコミュニケーションの正確性と品質を向上させるアプローチです。
#### Q: メーカーは半導体の自動化をどのように活用していますか？
A: 半導体の自動化は、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合することで、データとコミュニケーションの正確性と品質を向上させるために活用されています。
#### Q: 製造自動化ソフトウェアは何をするものですか？
A: 製造自動化ソフトウェアは、前工程のウェーハ製造から後工程の組立、検査、パッケージングまで、半導体製造プロセス全体を定義、制御、自動化、監視、記録することができます。
#### Q: 製造自動化ソフトウェアのメリットは何ですか？
A: 製造自動化ソフトウェアは、生産性と品質の向上を図りながら、全体的なコストを削減することができます。具体的には、工場内や複数拠点間での協業を促進し、設備の状態を正確に把握してツール管理を改善し、リアルタイムデータを活用したスケジューリング管理を可能にします。
# よくある質問: スマート製造
#### Q: スマート製造とは何ですか？
A: スマート製造とは、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合し、データとコミュニケーションの正確性と品質を向上させるアプローチです。
#### Q: メーカーは半導体の自動化をどのように活用していますか？
A: 半導体の自動化は、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合することで、データとコミュニケーションの正確性と品質を向上させるために活用されています。
#### Q: 製造自動化ソフトウェアは何をするものですか？
A: 製造自動化ソフトウェアは、前工程のウェーハ製造から後工程の組立、検査、パッケージングまで、半導体製造プロセス全体を定義、制御、自動化、監視、記録することができます。
#### Q: 製造自動化ソフトウェアのメリットは何ですか？
A: 製造自動化ソフトウェアは、生産性と品質の向上を図りながら、全体的なコストを削減することができます。具体的には、工場内や複数拠点間での協業を促進し、設備の状態を正確に把握してツール管理を改善し、リアルタイムデータを活用したスケジューリング管理を可能にします。
---
### [Use Cases Faqs](https://appliedsmartfactory.com/use-cases-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# 常见问题解答：应用案例
#### 半导体行业如何实现自动化制造？
半导体行业通过自动化制造将多个工厂系统（如批次追踪、工艺流程、排程和物料分发系统）集成在一起，提升数据与通信的准确性和质量。
#### 自动化制造有哪些优势？
自动化制造解决方案能够提升生产效率和产品质量，同时降低整体成本。其实现方式包括：促进单一工厂或跨工厂之间的协同作业，提供精准的设备状态洞察以优化设备管理，以及利用实时数据管理排程方案等。
#### 什么是半导体制造执行系统 (MES) ？
制造执行系统是半导体工厂的核心运营支柱，能实时监控、控制和优化生产工艺。MES 制造软件可帮助提升半导体工厂的工艺流程与产品质量。凭借其事件预测与分析能力，还能助力制造商快速做出精准决策。
#### MES 系统能否帮助改善生产周期？
可以。MES 系统软件通过集成多个工厂系统（如批次追踪、工艺控制、排程和物料分发系统），提升数据与通信的准确性和质量。MES 系统软件能够提供实时可视化、自动化数据采集、预测分析、增强协同通信以及优化生产工艺等功能，有效缩短生产周期。
#### 提升半导体制造生产效率的方法有哪些？
提升半导体晶圆厂生产效率的关键方法包括：优化供应链管理以识别并减少瓶颈、缩短计划制定时间并提升计划人员工作效率、提高订单按时交付率与产能利用率。
# 常见问题解答：应用案例
#### 半导体行业如何实现自动化制造？
半导体行业通过自动化制造将多个工厂系统（如批次追踪、工艺流程、排程和物料分发系统）集成在一起，提升数据与通信的准确性和质量。
#### 自动化制造有哪些优势？
自动化制造解决方案能够提升生产效率和产品质量，同时降低整体成本。其实现方式包括：促进单一工厂或跨工厂之间的协同作业，提供精准的设备状态洞察以优化设备管理，以及利用实时数据管理排程方案等。
#### 什么是半导体制造执行系统 (MES) ？
制造执行系统是半导体工厂的核心运营支柱，能实时监控、控制和优化生产工艺。MES 制造软件可帮助提升半导体工厂的工艺流程与产品质量。凭借其事件预测与分析能力，还能助力制造商快速做出精准决策。
#### MES 系统能否帮助改善生产周期？
可以。MES 系统软件通过集成多个工厂系统（如批次追踪、工艺控制、排程和物料分发系统），提升数据与通信的准确性和质量。MES 系统软件能够提供实时可视化、自动化数据采集、预测分析、增强协同通信以及优化生产工艺等功能，有效缩短生产周期。
#### 提升半导体制造生产效率的方法有哪些？
提升半导体晶圆厂生产效率的关键方法包括：优化供应链管理以识别并减少瓶颈、缩短计划制定时间并提升计划人员工作效率、提高订单按时交付率与产能利用率。
---
### [Smart Manufacturing Faqs](https://appliedsmartfactory.com/smart-manufacturing-faqs/)
**Published:** April 9, 2024
**Author:** Applied Smartfactory
**Content:**
# 常见问题解答：智能制造
#### 什么是智能制造？
本质上，智能制造是一种集成多种工厂系统（如批次追踪、工艺流程、排程及物料分发系统），旨在提升数据与通信的准确性和质量。
#### 制造商如何应用半导体自动化制造？
制造商通过应用半导体自动化制造将多个工厂系统（如批次追踪、工艺流程、排程及物料分发系统）集成在一起，提升数据与通信的准确性和质量。
#### 制造自动化软件具备哪些功能？
制造自动化软件使制造商能够定义、控制、自动化、监控和记录从前道晶圆制造到后道封装、测试和包装的完整半导体制造过程。
#### 制造自动化软件有哪些优势？
制造自动化软件能够提升生产效率和产品质量，同时降低整体成本。其实现方式包括：促进单一工厂或跨工厂之间的协同作业，提供精准的设备状态洞察以优化设备管理，以及利用实时数据管理排程方案等。
---
### [Planning Faqs](https://appliedsmartfactory.com/planning-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# よくある質問: プランニング
#### Q: 高度なプランニングおよびスケジューリングソリューションにはどのようなメリットがありますか？
A: 高度な計画およびスケジューリングソリューションは、計画にかかるダウンタイムを削減し、プランナーの生産性を向上させ、設備の稼働率を改善することができます。
#### Q: SmartFactory Enterprise Planningは、半導体メーカーの応答性向上に役立ちますか？
A: はい。SmartFactory Enterprise Planningは、サプライチェーン計画ソリューションであり、高速な計画エンジンを備えているため、納期遵守とメーカーの応答性を向上させます。多くの計画ソリューションとは異なり、複雑な導入やカスタマイズを必要とせず、計画から実行まで統合されており、オープンボックス型のアプローチにより、精度の向上と顧客予測の変化への迅速な対応が可能です。
#### Q: 半導体業界における自動化製造はどのように機能しますか？
A: 半導体業界では、自動化製造を活用して、ロット管理、工程、スケジューリング、配送など複数の工場システムを統合し、データとコミュニケーションの正確性と品質を向上させています。
#### Q: 自動化製造のメリットは何ですか？
A: 自動化製造ソリューションは、生産性と品質を向上させると同時に、全体的なコストを削減することができます。具体的には、工場内や複数拠点間での協業を促進し、設備の状態を正確に把握してツール管理を改善し、リアルタイムデータを活用したスケジューリング管理を可能にします。
---
### [Planning Faqs](https://appliedsmartfactory.com/planning-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# 常见问题解答：计划
#### 先进计划与排程解决方案能带来哪些优势？
先进计划与排程解决方案能够有效减少计划外停机，提升计划员工作效率，并优化产能利用率。
#### SmartFactory Enterprise Planning 能否帮助半导体制造商提升响应能力？
可以。SmartFactory Enterprise Planning 作为供应链规划解决方案，内置快速计划引擎，能有效提升制造商的订单按时交付率与响应速度。与多数需要复杂部署和定制化的计划方案不同，本系统实现了从计划到执行的全流程集成，采用开箱即用的实施模式，不仅能显著提升计划准确性，更能快速响应客户需求预测的变更。
#### 半导体行业如何实现自动化制造？
半导体行业通过自动化制造将多个工厂系统（如批次追踪、工艺流程、排程和物料分发系统）集成在一起，提升数据与通信的准确性和质量。
#### 自动化制造有哪些优势？
自动化制造解决方案能够提升生产效率和产品质量，同时降低整体成本。其实现方式包括：促进单一工厂或跨工厂之间的协同作业，提供精准的设备状态洞察以优化设备管理，以及利用实时数据管理排程方案等。
---
### [Smart Manufacturing Faqs](https://appliedsmartfactory.com/smart-manufacturing-faqs/)
**Published:** April 9, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Smart Manufacturing
#### What is smart manufacturing?
Essentially, smart manufacturing is an approach that integrates multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### How do manufacturers use semiconductor automation?
Semiconductor automation is used by manufacturers to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What does manufacturing automation software do?
Manufacturing automation software allows manufacturers to define, control, automate, monitor, and record the entire semiconductor manufacturing process from front-end wafer fabrication through back-end assembly, test, and packaging.
#### What are the benefits of manufacturing automation software?
Manufacturing automation software can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
---
### [Use Cases Faqs](https://appliedsmartfactory.com/use-cases-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# よくある質問: スケジューリング
#### Q: 半導体業界における自動化製造はどのように機能しますか？
A: 半導体業界では、自動化製造を活用して、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合し、データとコミュニケーションの正確性と品質を向上させています。
#### Q: 自動化製造のメリットは何ですか？
A: 自動化製造ソリューションは、生産性と品質を向上させると同時に、全体的なコストを削減することができます。具体的には、工場内や複数拠点間での協業を促進し、設備の状態を正確に把握してツール管理を改善し、リアルタイムデータを活用したスケジューリング管理を可能にします。
#### Q: 半導体製造におけるMES（製造実行システム）とは何ですか？
A: MES（製造実行システム）は、多くの半導体工場における運用の中核であり、生産プロセスをリアルタイムで監視・制御・最適化するのに役立ちます。MES製造ソフトウェアは、工場のプロセスや製品品質の向上を支援し、イベントの予測や分析機能により、迅速かつ的確な意思決定を可能にします。
#### Q: MESはサイクルタイムの改善に役立ちますか？
A: はい。MESソフトウェアは、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合し、データとコミュニケーションの正確性と品質を向上させます。MESは、リアルタイムの可視化、自動データ収集、予測分析、コミュニケーションと協業の改善、生産プロセスの最適化を通じて、サイクルタイムの短縮に貢献します。
#### Q: 半導体製造における生産性を向上させる方法にはどのようなものがありますか？
A: 半導体工場の生産性を向上させるための重要な方法には、サプライチェーンの管理を改善してボトルネックを特定・解消すること、計画時間の短縮とプランナーの生産性向上、納期遵守と設備稼働率の改善などがあります。
---
### [Use Cases Faqs](https://appliedsmartfactory.com/use-cases-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQ: Use Cases
#### How does automated manufacturing work in the semiconductor industry?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automated manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
#### What is a Manufacturing Execution System (MES) for semiconductor manufacturing?
The manufacturing execution system is the operational backbone of many semiconductor factories and can help monitor, control, and optimize production processes in real-time. MES manufacturing software can help improve a semiconductor factory’s processes and product quality. Because of its ability to predict and analyze events, it also helps manufacturers make informed decisions more quickly.
#### Can a MES help improve cycle time?
Yes, the MES software integrates multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication. MES manufacturing software can help improve cycle time by providing real-time visibility, automating data collection, using predictive analytics, improving communication and collaboration, and optimizing production processes.
#### What are some ways to improve productivity in semiconductor manufacturing?
Among the most important ways to improve productivity in semiconductor fabs is to better manage the supply chain to identify and reduce bottlenecks, reduce planning time and improve planner productivity, and improve on-time delivery and capacity usage.
---
### [Blog](https://appliedsmartfactory.com/blog/)
**Published:** October 18, 2021
**Author:** Applied Smartfactory
**Content:**
# 按行业阅读博客
[](/zh-hans/semiconductor-blog/) [ ](/semiconductor-blog/)
### [ 半导体博客 ](/semiconductor-blog/)
紧跟行业最新趋势，发挥智能制造优势。
[](/battery-blog/) [ ](/battery-blog/)
### [ Battery blog ](/battery-blog/)
Navigating technology, people, and market dynamics to gain a competitive advantage in battery manufacturing.
---
### [Planning Faqs](https://appliedsmartfactory.com/planning-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Planning
#### What are the benefits of advanced planning and scheduling solutions?
An advanced planning and scheduling solution can reduce planning downtime, improve planner productivity, and improve capacity utilization.
#### Can SmartFactory Enterprise Planning help semiconductor manufacturers improve responsiveness?
Yes, SmartFactory Enterprise Planning is a supply chain planning solution that includes a fast planning engine to improve on-time delivery and responsiveness for manufacturers. Unlike many planning solutions, which require complex deployments and customizations, SmartFactory Enterprise Planning is integrated from planning through execution, offering an open-box approach with increased accuracy and faster response to customer forecast changes.
#### How does automated manufacturing work in the semiconductor industry?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automated manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
---
### [Test & Assembly](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **Test & Assembly**
Maintain consistent execution across variable test and assembly environments—adapting to changing product mixes and volumes without disrupting factory performance.
[](/manufacturing-execution-solutions/mesforatp/)### MES Solution
MES for ATP
Optimizes MES intelligence for semiconductor backend manufacturing
---
### [Wafer Fab](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **Wafer Fab**
Execute advanced wafer manufacturing with consistency and control—supporting complex operations across tools, processes, and production flows.
[](/manufacturing-execution-solutions/300works-full-auto/)### MES Solution
MES 300works® Full-Auto
Improves high volume manufacturing by automating flow of materials
---
### [Wafer Substrate](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-substrate/)
**Published:** April 15, 2026
**Author:** Sushmita Kumari
**Content:**
# **Wafer Substrate**
Reliable, production-grade MES for ingot and wafer environments—supporting crystal growth, wafering operations, and upstream production workflows with consistency and control.
[](/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)### MES Blog
Manufacturing discipline starts at the substrate: Why execution can’t wait for the fab
Front-end execution increasingly determines semiconductor outcomes
---
### [Classic MES](https://appliedsmartfactory.com/manufacturing-execution-solutions/classic-mes/)
**Published:** April 10, 2026
**Author:** Sushmita Kumari
**Content:**
# **Classic MES**
Classic MES solutions represent established Manufacturing Execution (MES) platforms trusted by semiconductor manufacturers for decades. These systems provide proven execution foundations, supporting high volume operations where stability, reliability, and depth matter most. Many customers continue to rely on these platforms as core components of their manufacturing environments.
[](/semiconductor/manufacturing-execution-solutions/promis/)### MES PROMIS®
Established MES platform supporting mission critical semiconductor manufacturing.
[](/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
Improves yield by optimizing equipment and process performance.
[](/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
Extended FACTORYworks capabilities for advanced operational needs.
[](/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
High volume MES platform designed for large scale manufacturing.
[](/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### Alarm Management
Centralized alarm handling to support operational stability.
[](/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
Visibility and monitoring capabilities for manufacturing execution.
---
### [Manufacturing Execution Solutions](https://appliedsmartfactory.com/manufacturing-execution-solutions/)
**Published:** September 13, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory MES Solutions
Streamline manufacturing execution by integrating and optimizing operations for better control and efficiency.
[](/semiconductor/manufacturing-execution-solutions/alarmmanagement/)### SmartFactory Alarm Management
Reduces production noise and boosts operation efficiency
[](/semiconductor/manufacturing-execution-solutions/asset-trace/)### SmartFactory Asset Trace
Improves asset utilization with asset trace throughout entire life cycle
[](/semiconductor/manufacturing-execution-solutions/300works-full-auto/)### MES 300works® Full-Auto
Improves high volume manufacturing by automating flow of materials
[](/semiconductor/manufacturing-execution-solutions/factoryworks-plus/)### MES FACTORYworks+™
Augments the FACTORYworks platform with additional out-of-box functionality to support semiconductor assembly and adjacent industries
[](/semiconductor/manufacturing-execution-solutions/factoryworks/)### MES FACTORYworks®
Accelerates high volume manufacturing improvements with special feature extensions
[](/semiconductor/manufacturing-execution-solutions/material-control/)### Material Control
Automates WIP movement to increase throughput and decrease equipment idle time
[](/semiconductor/manufacturing-execution-solutions/promis)### MES PROMIS®
Boosts efficiency with fab operation modeling capabilities
[](/semiconductor/manufacturing-execution-solutions/fab300/)### MES FAB300®
Implements your proprietary business rules without programming
[](/semiconductor/manufacturing-execution-solutions/maintenance-management/)### Maintenance Management
Improves power of equipment maintenance – scheduled and unscheduled activities
[](/semiconductor/manufacturing-execution-solutions/monitor/)### Monitor
Detects and predicts system failures
[](/semiconductor/manufacturing-execution-solutions/mesforatp/)### SmartFactory MES for ATP
Optimizes MES intelligence for semiconductor backend manufacturing
# MES for predictable factory execution—at any scale or complexity
### Consistent factory execution across the entire semiconductor manufacturing lifecycle
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-substrate/)#### Wafer Substrate
Reliable, production‑grade MES for ingot and wafer environments—supporting crystal growth, wafering operations, and upstream production workflows with consistency and control.
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/wafer-fab/)#### Wafer Fab
Execute advanced wafer manufacturing with consistency and control–supporting complex operations across tools, processes, and production flows.
[](https://appliedsmartfactory.com/manufacturing-execution-solutions/test-and-assembly/)#### Test & Assembly
Maintain consistent execution across variable test and assembly environments–adapting to changing product mixes and volumes without disrupting factory performance.
[](/semiconductor/classic-mes/)#### Classic MES
Run established factory operations on proven MES foundations—supporting critical manufacturing environments with stability and depth at scale.
---
### [Supply Chain Solutions](https://appliedsmartfactory.com/supply-chain-solutions/)
**Published:** September 14, 2021
**Author:** Applied Smartfactory
**Content:**
## SmartFactory Supply Chain Solutions
Enhance supply chain management to improve planning, execution, and overall performance.
[](/semiconductor/supply-chain-solutions/enterprise-planning/)### Enterprise Planning
Increases capacity planning accuracy and responds faster to customer forecast changes
[](/semiconductor/productivity-solutions/production-control/)### Production Control
Runs high-speed what-if scenarios to improve WIP throughput and capacity utilization—without disrupting manufacturing operations
[](/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/)### Simulation AutoMod
Continuously improves productivity throughout the life of the facility with Powerful 3-D simulation modeling
# Improving planning and production control performance across manufacturing
### Plan, control, and simulate the impact of supply chain decisions across factories
[](/semiconductor/supply-chain-solutions/enterprise-planning/)#### Enterprise Planning
Increases capacity planning accuracy and responds faster to customer forecast changes.
[](/semiconductor/supply-chain-solutions/production-control/)#### Production Control
Runs high-speed what-if scenarios to improve WIP throughput and capacity utilization—without disrupting manufacturing operations.
[](/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/)#### Simulation AutoMod
Continuously improves productivity throughout the life of the facility with powerful 3-D simulation modeling.
---
### [Simulation AutoMod](https://appliedsmartfactory.com/supply-chain-solutions/simulation-automod/for-students-and-academics/)
**Published:** July 21, 2022
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoMod®
# Student Version and Academic License
[ Read Semi Blog ](/semiconductor-blog/)
## AutoMod Academic Program
**Affordable university program for powerful simulation software**
Applied Materials, the industry leader in manufacturing and material handling simulation software, is committed to assisting students and instructors in having the most powerful simulation software available for teaching and research. Simulation is taught in university engineering department curriculums worldwide, together with the AutoMod Student Version and Getting Started with AutoMod text.
In true 3-D scale, AutoMod enables the student to transfer manufacturing and material handling concepts into working computer simulations that test the validity of their concepts and verify the effectiveness of classroom instruction.
Academic license Professors and universities can purchase an academic license of AutoMod at a reduced rate. This version is fully functional but cannot be used for commercial projects.
For additional details, contact [AutoMod Support](mailto:automod_support@amat.com) or your [local distributor](/worldwide-automod-distributors/).
## AutoMod Student Version
The AutoMod Student Version software has all the design capabilities and controls of the full version though it limits the number of simulation entities that can be defined (i.e., queues, resources, vehicles, conveyor sections, etc.).
You can download and install the AutoMod Student Version, and then authorize it without a hardware key, but you are limited to 200 named entities. Examples of entities are conveyor sections, queues, resources, processes, control points, and order lists.
The download includes the Getting Started with AutoMod book, which includes a variety of simulation examples for teaching purposes. Written by Dr. Jerry Banks, the text discusses simulation principles, modeling and statistical analysis.
Available Downloads Version 12.6.1
[ Download ](https://amfiles.amat.com/student/studentversion126.zip)
Installation instructions
[ Download ](https://amfiles.amat.com/student/aminstall.zip)
---
### [Simulation AutoMod](https://appliedsmartfactory.com/supply-chain-solutions/simulation-automod/for-students-and-academics/)
**Published:** July 21, 2022
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoMod®
# Student Version and Academic License
[ Read Semi Blog ](/semiconductor-blog/)
## AutoMod Academic Program
**Affordable university program for powerful simulation software**
Applied Materials, the industry leader in manufacturing and material handling simulation software, is committed to assisting students and instructors in having the most powerful simulation software available for teaching and research. Simulation is taught in university engineering department curriculums worldwide, together with the AutoMod Student Version and Getting Started with AutoMod text.
In true 3-D scale, AutoMod enables the student to transfer manufacturing and material handling concepts into working computer simulations that test the validity of their concepts and verify the effectiveness of classroom instruction.
Academic license Professors and universities can purchase an academic license of AutoMod at a reduced rate. This version is fully functional but cannot be used for commercial projects.
For additional details, contact [AutoMod Support](mailto:automod_support@amat.com) or your [local distributor](/worldwide-automod-distributors/).
## AutoMod Student Version
The AutoMod Student Version software has all the design capabilities and controls of the full version though it limits the number of simulation entities that can be defined (i.e., queues, resources, vehicles, conveyor sections, etc.).
You can download and install the AutoMod Student Version, and then authorize it without a hardware key, but you are limited to 200 named entities. Examples of entities are conveyor sections, queues, resources, processes, control points, and order lists.
The download includes the Getting Started with AutoMod book, which includes a variety of simulation examples for teaching purposes. Written by Dr. Jerry Banks, the text discusses simulation principles, modeling and statistical analysis.
Available Downloads Version 12.6.1
[ Download ](https://amfiles.amat.com/student/studentversion126.zip)
Installation instructions
[ Download ](https://amfiles.amat.com/student/aminstall.zip)
---
### [联系我们](https://appliedsmartfactory.com/connect/)
**Published:** July 22, 2021
**Author:** Applied Smartfactory
**Content:**
# 共启全球智造未来，期待与您携手合作
### 联系我们
请填写以下信息，我们将尽快与您联系。所有信息均为必填项。
First Name: \*
Last Name: \*
Company Name: \*
Business Email: \*
Country/Region: \*
Please select countryAfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
No. of Employees: \*
Please select1-2021-200201-10,00010,000+
Let us know how we can assist: \*
Tell us a bit about your role, goals, or questions so we can route your request appropriately.
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Thank you for contacting us; we will get back to you shortly. In the meantime, please visit our LinkedIn page dedicated to [semiconductor](https://www.linkedin.com/showcase/applied-smartfactory/) industry for the latest updates.
Δ
---
### [ブログ](https://appliedsmartfactory.com/blog/)
**Published:** October 18, 2021
**Author:** Applied Smartfactory
**Content:**
# 業界別のブログ
[](/ja/semiconductor-blog/) [ ](/ja/semiconductor-blog/)
### [ 半導体ブログ ](/ja/semiconductor-blog/)
業界の最新トレンドを追うことで、スマート製造のアドバンテージを最大化ましょう。
### 製薬ブログ（近日公開）
ビジネスオペレーションにおける知識の獲得と新製品の市場投入までの時間の短縮を可能にします。
[](/ja/battery-blog/)
### バッテリーブログ
技術、人材、市場の動向のかじ取りして、バッテリー製造において競争優位性を獲得しましょう。
---
### [Cookie Policy](https://appliedsmartfactory.com/cookie-policy/)
**Published:** April 29, 2025
**Author:** Applied Smartfactory
**Content:**
---
### [AI-ML Faqs](https://appliedsmartfactory.com/ai-ml-faqs/)
**Published:** March 20, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: AI/ML Technologies
#### What do AI and ML stand for and how are they different?
AI is artificial intelligence and ML represents machine learning. Artificial intelligence represents the ability of computers to mimic human thought and tasks. Machine learning is a subcategory of AI. ML uses algorithms to learn from data, finding patterns and applying that understanding to decision making. Both are integral to achieving automation in semiconductor manufacturing.
#### How are AI and ML technologies used in the semiconductor industry?
AI and ML technologies are used by semiconductor manufacturers to solve quality, productivity and supply chain challenges using the next-generation approach of advanced and intelligent algorithms.
#### How does automation in semiconductor manufacturing work?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automation in semiconductor manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
#### How can manufacturing simulation software be used in semiconductor manufacturing?
Manufacturing simulation software can predict the impact of a particular change to the manufacturing process before it is made live in the production environment. This can identify potential problems to address prior to implementation, as well as help manufacturers find the most advantageous solutions.
#### How can manufacturing simulation software help when little historical data is available?
Simulation software can model scenarios and generate synthetic data to use in AI training. Training models on rich datasets develop more robust, resilient models. Evaluating on-edge cases or other diverse scenarios that seldom occur in historical data increases generalization abilities of models, which improves accuracy overall.
#### Can manufacturing simulation software support AI implementation in semiconductor manufacturing?
Yes, simulation can overcome data collection challenges when implementing AI in semiconductor manufacturing. Simulation allows models to be trained on a rich, multi-year dataset, which aids prediction accuracy. Operational efficiency gains are then possible as planners are given the opportunity, in a non-production, simulated environment, to test and validate changes such as updating dispatching and scheduling parameters required for late lot predictions. Simulation also can find key performance indicator (KPI) differences by evaluating ML models versus existing dispatching rules or scheduling models. This provides the powerful opportunity to compare those differences.
## FAQs: RAG
#### What is Retrieval-Augmented Generation (RAG)?
RAG is a hybrid AI approach that combines the generative power of large language models (LLMs) with the accuracy of document retrieval systems. It first searches a knowledge base for relevant data, then synthesizes and contextualizes that information to generate a natural language response.
#### How does Retrieval-Augmented Generation benefit semiconductor manufacturing?
RAG helps manufacturers by:
- Reducing the risk of hallucinations (incorrect answers) by grounding responses in relevant documents.
- Providing up-to-date, transparent answers with references to source materials.
- Navigating complex, evolving information landscapes—like thousands of specs, SOPs, and tool logs—to surface what matters most.
#### What is an example of RAG in action?
The SmartFactory Genie assistant uses RAG to help engineers troubleshoot issues or onboard new tools. Instead of searching through manuals, an engineer can ask a question and receive a synthesized, context-aware answer with actionable steps, saving time and reducing friction in problem-solving and training.
#### What are the main limitations of Retrieval-Augmented Generation?
- RAG can be slower than purely generative models because it must search before generating a response.
- Its effectiveness depends on the quality of the retriever—if relevant documents aren’t found, it may not provide an answer.
- RAG is not designed for complex, multistep reasoning or autonomous task execution; it excels at answering questions and summarizing information.
#### How is Retrieval-Augmented Generation evolving?
RAG is advancing with innovations like multimodal retrieval (integrating text, images, and sensor data) and personalized retrieval tailored to user roles and history. These improvements will make RAG even more powerful and efficient for manufacturing environments.
Also, while RAG focuses on retrieving and summarizing the right information, Agentic AI builds on those foundations to plan, reason, and take action. As RAG systems grow more capable, they extend into agentic behaviors: detecting anomalies, analyzing context, and autonomously coordinating the right next steps.
---
### [AI-ML Faqs](https://appliedsmartfactory.com/ai-ml-faqs/)
**Published:** March 20, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: AI/ML Technologies
#### What do AI and ML stand for and how are they different?
AI is artificial intelligence and ML represents machine learning. Artificial intelligence represents the ability of computers to mimic human thought and tasks. Machine learning is a subcategory of AI. ML uses algorithms to learn from data, finding patterns and applying that understanding to decision making. Both are integral to achieving automation in semiconductor manufacturing.
#### How are AI and ML technologies used in the semiconductor industry?
AI and ML technologies are used by semiconductor manufacturers to solve quality, productivity and supply chain challenges using the next-generation approach of advanced and intelligent algorithms.
#### How does automation in semiconductor manufacturing work?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automation in semiconductor manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
#### How can manufacturing simulation software be used in semiconductor manufacturing?
Manufacturing simulation software can predict the impact of a particular change to the manufacturing process before it is made live in the production environment. This can identify potential problems to address prior to implementation, as well as help manufacturers find the most advantageous solutions.
#### How can manufacturing simulation software help when little historical data is available?
Simulation software can model scenarios and generate synthetic data to use in AI training. Training models on rich datasets develop more robust, resilient models. Evaluating on-edge cases or other diverse scenarios that seldom occur in historical data increases generalization abilities of models, which improves accuracy overall.
#### Can manufacturing simulation software support AI implementation in semiconductor manufacturing?
Yes, simulation can overcome data collection challenges when implementing AI in semiconductor manufacturing. Simulation allows models to be trained on a rich, multi-year dataset, which aids prediction accuracy. Operational efficiency gains are then possible as planners are given the opportunity, in a non-production, simulated environment, to test and validate changes such as updating dispatching and scheduling parameters required for late lot predictions. Simulation also can find key performance indicator (KPI) differences by evaluating ML models versus existing dispatching rules or scheduling models. This provides the powerful opportunity to compare those differences.
## FAQs: RAG
#### What is Retrieval-Augmented Generation (RAG)?
RAG is a hybrid AI approach that combines the generative power of large language models (LLMs) with the accuracy of document retrieval systems. It first searches a knowledge base for relevant data, then synthesizes and contextualizes that information to generate a natural language response.
#### How does Retrieval-Augmented Generation benefit semiconductor manufacturing?
RAG helps manufacturers by:
- Reducing the risk of hallucinations (incorrect answers) by grounding responses in relevant documents.
- Providing up-to-date, transparent answers with references to source materials.
- Navigating complex, evolving information landscapes—like thousands of specs, SOPs, and tool logs—to surface what matters most.
#### What is an example of RAG in action?
The SmartFactory Genie assistant uses RAG to help engineers troubleshoot issues or onboard new tools. Instead of searching through manuals, an engineer can ask a question and receive a synthesized, context-aware answer with actionable steps, saving time and reducing friction in problem-solving and training.
#### What are the main limitations of Retrieval-Augmented Generation?
- RAG can be slower than purely generative models because it must search before generating a response.
- Its effectiveness depends on the quality of the retriever—if relevant documents aren’t found, it may not provide an answer.
- RAG is not designed for complex, multistep reasoning or autonomous task execution; it excels at answering questions and summarizing information.
#### How is Retrieval-Augmented Generation evolving?
RAG is advancing with innovations like multimodal retrieval (integrating text, images, and sensor data) and personalized retrieval tailored to user roles and history. These improvements will make RAG even more powerful and efficient for manufacturing environments.
Also, while RAG focuses on retrieving and summarizing the right information, Agentic AI builds on those foundations to plan, reason, and take action. As RAG systems grow more capable, they extend into agentic behaviors: detecting anomalies, analyzing context, and autonomously coordinating the right next steps.
---
### [AI-ML Faqs](https://appliedsmartfactory.com/ai-ml-faqs/)
**Published:** March 20, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: AI/ML Technologies
#### What do AI and ML stand for and how are they different?
AI is artificial intelligence and ML represents machine learning. Artificial intelligence represents the ability of computers to mimic human thought and tasks. Machine learning is a subcategory of AI. ML uses algorithms to learn from data, finding patterns and applying that understanding to decision making. Both are integral to achieving automation in semiconductor manufacturing.
#### How are AI and ML technologies used in the semiconductor industry?
AI and ML technologies are used by semiconductor manufacturers to solve quality, productivity and supply chain challenges using the next-generation approach of advanced and intelligent algorithms.
#### How does automation in semiconductor manufacturing work?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automation in semiconductor manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
#### How can manufacturing simulation software be used in semiconductor manufacturing?
Manufacturing simulation software can predict the impact of a particular change to the manufacturing process before it is made live in the production environment. This can identify potential problems to address prior to implementation, as well as help manufacturers find the most advantageous solutions.
#### How can manufacturing simulation software help when little historical data is available?
Simulation software can model scenarios and generate synthetic data to use in AI training. Training models on rich datasets develop more robust, resilient models. Evaluating on-edge cases or other diverse scenarios that seldom occur in historical data increases generalization abilities of models, which improves accuracy overall.
#### Can manufacturing simulation software support AI implementation in semiconductor manufacturing?
Yes, simulation can overcome data collection challenges when implementing AI in semiconductor manufacturing. Simulation allows models to be trained on a rich, multi-year dataset, which aids prediction accuracy. Operational efficiency gains are then possible as planners are given the opportunity, in a non-production, simulated environment, to test and validate changes such as updating dispatching and scheduling parameters required for late lot predictions. Simulation also can find key performance indicator (KPI) differences by evaluating ML models versus existing dispatching rules or scheduling models. This provides the powerful opportunity to compare those differences.
## FAQs: RAG
#### What is Retrieval-Augmented Generation (RAG)?
RAG is a hybrid AI approach that combines the generative power of large language models (LLMs) with the accuracy of document retrieval systems. It first searches a knowledge base for relevant data, then synthesizes and contextualizes that information to generate a natural language response.
#### How does Retrieval-Augmented Generation benefit semiconductor manufacturing?
RAG helps manufacturers by:
- Reducing the risk of hallucinations (incorrect answers) by grounding responses in relevant documents.
- Providing up-to-date, transparent answers with references to source materials.
- Navigating complex, evolving information landscapes—like thousands of specs, SOPs, and tool logs—to surface what matters most.
#### What is an example of RAG in action?
The SmartFactory Genie assistant uses RAG to help engineers troubleshoot issues or onboard new tools. Instead of searching through manuals, an engineer can ask a question and receive a synthesized, context-aware answer with actionable steps, saving time and reducing friction in problem-solving and training.
#### What are the main limitations of Retrieval-Augmented Generation?
- RAG can be slower than purely generative models because it must search before generating a response.
- Its effectiveness depends on the quality of the retriever—if relevant documents aren’t found, it may not provide an answer.
- RAG is not designed for complex, multistep reasoning or autonomous task execution; it excels at answering questions and summarizing information.
#### How is Retrieval-Augmented Generation evolving?
RAG is advancing with innovations like multimodal retrieval (integrating text, images, and sensor data) and personalized retrieval tailored to user roles and history. These improvements will make RAG even more powerful and efficient for manufacturing environments.
Also, while RAG focuses on retrieving and summarizing the right information, Agentic AI builds on those foundations to plan, reason, and take action. As RAG systems grow more capable, they extend into agentic behaviors: detecting anomalies, analyzing context, and autonomously coordinating the right next steps.
---
### [Scheduling Faqs](https://appliedsmartfactory.com/scheduling-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# 常见问题解答：排程
#### 生产排程在半导体晶圆厂中有多重要？
生产排程是半导体工厂运营的核心环节，它直接关系到设备生产效率、产品质量管控以及客户订单按时交付等关键业务指标的达成。
#### 生产排程系统（或称工厂排程解决方案系统）对半导体制造商有何益处？
生产排程系统帮助半导体制造商最大限度地利用设备和人力资源。一套优秀的工厂排程解决方案能有效提升设备综合效率、产品质量以及产品的按时交付率。
#### 制造仿真件如何应用于半导体制造？
制造仿真软件可在生产环境实际实施前，预测诸如排程规则等变更对制造流程的影响。这有助于在实施前发现并解决潜在问题，同时协助制造商找到最优解决方案。
#### SmartFactory Simulation AutoSched 如何帮助晶圆厂建立设备决策模型？
SmartFactory Simulation AutoSched 是一个产能规划系统，可通过模拟复杂的工作流程识别隐藏和浪费的工厂产能。该系统支持用户创建晶圆厂虚拟模型，在离线环境下进行运营分析、预测与优化，并对排程规则、设备及操作员周期进行模拟测试。
#### 半导体行业如何实现自动化制造？
半导体行业通过自动化制造将多个工厂系统（如批次追踪、工艺流程、排程和物料分发系统）集成在一起，提升数据与通信的准确性和质量。
#### 自动化制造有哪些优势？
自动化制造解决方案能够提升生产效率和产品质量，同时降低整体成本。其实现方式包括：促进单一工厂或跨工厂之间的协同作业，提供精准的设备状态洞察以优化设备管理，以及利用实时数据管理排程方案等。
---
### [Productivity Faqs](https://appliedsmartfactory.com/productivity-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# 常见问题解答：生产效率
#### 提升半导体制造生产效率的方法有哪些？
提升半导体晶圆厂生产效率的关键方法包括：优化供应链管理以识别并减少瓶颈、缩短计划制定时间并提升计划人员工作效率、提高订单按时交付率与产能利用率。
#### 制造仿真软件如何帮助提升晶圆厂生产效率？
通过在仿真环境中复现生产派工流程，该软件系统能够在不影响实际生产运营的前提下，识别提升在制品 (WIP) 产出和产能利用率的优化空间。
#### SmartFactory Enterprise Planning 能否帮助半导体制造商提升响应能力？
可以。SmartFactory Enterprise Planning 作为供应链规划解决方案，内置快速计划引擎，能有效提升制造商的订单按时交付率与响应速度。与多数需要复杂部署和定制化的计划方案不同，本系统实现了从计划到执行的全流程集成，采用开箱即用的实施模式，不仅能显著提升计划准确性，更能快速响应客户需求预测的变更。
#### 半导体行业如何实现自动化制造？
半导体行业通过自动化制造将多个工厂系统（如批次追踪、工艺流程、排程和物料分发系统）集成在一起，提升数据与通信的准确性和质量。
#### 自动化制造有哪些优势？
自动化制造解决方案能够提升生产效率和产品质量，同时降低整体成本。其实现方式包括：促进单一工厂或跨工厂之间的协同作业，提供精准的设备状态洞察以优化设备管理，以及利用实时数据管理排程方案等。
---
### [Productivity Faqs](https://appliedsmartfactory.com/productivity-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Productivity
#### What are some ways to improve productivity in semiconductor manufacturing?
Among the most important ways to improve productivity in semiconductor fabs is to better manage the supply chain to identify and reduce bottlenecks, reduce planning time and improve planner productivity, and improve on-time delivery and capacity usage.
#### How can manufacturing simulation software help improve a fab’s productivity?
By replicating production dispatching in a simulation environment, the software system identifies opportunities for improving WIP throughput and capacity utilization without disrupting factory operations.
#### Can SmartFactory Enterprise Planning help semiconductor manufacturers improve responsiveness?
Yes, SmartFactory Enterprise Planning is a supply chain planning solution that includes a fast planning engine to improve on-time delivery and responsiveness for manufacturers. Unlike many planning solutions, which require complex deployments and customizations, SmartFactory Enterprise Planning is integrated from planning through execution, offering an open-box approach with increased accuracy and faster response to customer forecast changes.
#### How does automated manufacturing work in the semiconductor industry?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automated manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
---
### [Productivity Faqs](https://appliedsmartfactory.com/productivity-faqs/)
**Published:** May 17, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Productivity
#### What are some ways to improve productivity in semiconductor manufacturing?
Among the most important ways to improve productivity in semiconductor fabs is to better manage the supply chain to identify and reduce bottlenecks, reduce planning time and improve planner productivity, and improve on-time delivery and capacity usage.
#### How can manufacturing simulation software help improve a fab’s productivity?
By replicating production dispatching in a simulation environment, the software system identifies opportunities for improving WIP throughput and capacity utilization without disrupting factory operations.
#### Can SmartFactory Enterprise Planning help semiconductor manufacturers improve responsiveness?
Yes, SmartFactory Enterprise Planning is a supply chain planning solution that includes a fast planning engine to improve on-time delivery and responsiveness for manufacturers. Unlike many planning solutions, which require complex deployments and customizations, SmartFactory Enterprise Planning is integrated from planning through execution, offering an open-box approach with increased accuracy and faster response to customer forecast changes.
#### How does automated manufacturing work in the semiconductor industry?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automated manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
---
### [MES Faqs](https://appliedsmartfactory.com/mes-faqs/)
**Published:** March 13, 2024
**Author:** Applied Smartfactory
**Content:**
# 常见问题解答：制造执行解决方案
#### 半导体行业如何实现自动化制造？
半导体行业通过自动化制造将多个工厂系统（如批次追踪、工艺流程、排程及分发系统）集成在一起，提升数据与通信的准确性和质量。
#### 自动化制造有哪些优势？
自动化制造解决方案可提升生产效率与产品质量，同时降低整体成本。其实现途径包括：促进单一工厂或跨工厂之间的协同作业，提供精确的设备状态洞察以优化设备管理，以及利用实时数据实现生产排程。
#### 什么是半导体制造执行系统 (MES) ？
制造执行系统是半导体工厂的核心运营支柱，能实时监控、控制和优化生产工艺。MES 制造软件可帮助提升半导体工厂的工艺流程与产品质量。凭借其事件预测与分析能力，还能助力制造商快速做出明智的决策。
#### 哪种规模的半导体厂适合部署 MES 系统？
无论是最初实施自动化制造还是迈向无人化生产，各种规模的工厂都能通过部署 MES 系统获益。MES 制造软件可随工厂规模及自动化需求增长，与更多系统实现集成。
#### MES 系统与计算机集成制造 (CIM) 系统有何关联？
计算机集成制造 (CIM) 系统可控制生产过程的每个环节，而 MES 系统是其核心基础。即使是最基础的制造环境，正确配置的 MES 系统也能定义和协调所有加工作业。随着制造商需求变化，还可持续为 MES 系统添加功能模块，从而增强 CIM 系统的整体能力。
#### CIM 解决方案具备哪些功能？
计算机集成制造 (CIM) 解决方案使制造商能够定义、控制、自动化、监控和记录从前道晶圆制造到后道封装、测试和包装的完整半导体制造流程。
#### MES 系统能否帮助改善生产周期？
可以。MES 系统软件通过集成多个工厂系统（如批次追踪、工艺控制、排程和物料分发系统），提升数据与通信的准确性和质量。MES 系统软件能够提供实时可视化、自动化数据采集、预测分析、增强协同通信以及优化生产工艺等功能，有效缩短生产周期。
#### 计算机维护管理系统 (CMMS) 对半导体制造有何益处？
计算机维护管理系统 (CMMS) 能有效管理计划内、计划外及应急维护活动，优化库存管理水平，提高设备可用性，降低人力与备件成本。
#### 我的晶圆厂是否需要供应链企业规划解决方案？
供应链企业规划能帮助晶圆厂最大化利用资源、快速响应客户需求变化，提高订单交付及时性与市场响应能力。高效的供应链规划解决方案可收集并加载所有必要规划数据，通过成熟的高速数据提取处理技术快速生成供应计划。
---
### [SmartFactory AI](https://appliedsmartfactory.com/ai/)
**Published:** April 3, 2025
**Author:** Applied Smartfactory
**Content:**
# SmartFactory AI™ ソリューション で自律型生産を向上
生産性を加速し、精度を向上させる
# 次世代のAIアシスタント—
SmartFactory Genie
SmartFactory Genieは、大規模言語モデル(LLM)を搭載した高度なAIツールです。初心者でもプロでも、SmartFactory Genieは専門家によるヘルプとサポートを提供し、すべてのステップをガイドします。
[ AIエキスパートとの相談を申し込む ](https://appliedsmartfactory.com/ja/ai/schedule-a-meeting/)
## AIが製造業を大きく変革して
います
AIは大規模なデータセットに基づいて即座に洞察を提供し、より迅速で正確な意思決定を可能にします。これは単なる生産性の向上ではなく、製造業全体の風景を変革しています。
## なぜなら
競合他社が休まないからです。
センサー、機械、人からのデータを統合することで、歩留まりを高め、生産をスピードアップし、コストを削減し、製品の品質を向上させます。
AIは設備の故障を予測し、設備のメンテナンスを計画し、サプライ・チェーンを最適化することで、中断を減らし、効率を向上させます。
### SmartFactory AI IQworksTMを使用して、既存のインフラストラクチャでスケーラブルなAIソリューションを管理する。
### エッジとクラウドの統合
スケーラブルなAIフレームワーク
### 品質管理
ハイミックス、ローボリューム
### レイテンシーの削減
迅速なデータと意思決定
### シグナル管理
実用的なインサイト（洞察）
### ダイナミック・スケジューリング
工場の適応性
### リアルタイム学習環境
継続的改善機能
### 生成AI
生産性の向上
### 適正製造規範
規格順守と監査管理
[ SmartFactory AI IQworks について ](https://appliedsmartfactory.com/ja/ai/smartfactory-iqworks/)
### 見て学ぶ
#### SmartFactory AIソリューションでシームレスな製造の未来を形作る
[ ビデオを見る ](#)
[](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-transforming-manufacturing-kpis/)
#### AIの統合が製造のKPIを変革
半導体メーカーは工場のパフォーマンスを加速させ、新たなビジネスチャンスを発見しています。
[ もっと読む ](#)
[](https://appliedsmartfactory.com/ai/smartfactory-iqworks/)
#### SmartFactory AI IQworksを活用して、既存のインフラストラクチャでスケーラブルなAIソリューションを管理しましょう。
[ 詳細はこちら ](#)
---
### [MES Faqs](https://appliedsmartfactory.com/mes-faqs/)
**Published:** March 13, 2024
**Author:** Applied Smartfactory
**Content:**
# よくある質問: 製造実行システム（MES）
#### Q: 半導体業界における自動化製造はどのように機能しますか？
A: 半導体業界では、自動化製造を活用して、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合し、データとコミュニケーションの精度と品質を向上させています。
#### Q: 自動化製造のメリットは何ですか？
A: 自動化製造ソリューションは、生産性と品質を向上させながら、全体的なコストを削減することができます。その方法の一例としては、工場内や複数拠点間での協業の強化、装置の状態に関する正確な洞察によるツール管理の改善、リアルタイムデータを活用したスケジューリングの最適化などがあります。
#### Q: 半導体製造における製造実行システム（MES）とは何ですか？
A: 製造実行システム（MES）は、多くの半導体工場の運用の中核を担うシステムであり、リアルタイムで生産プロセスを監視、制御、最適化することができます。MES製造ソフトウェアは、工場のプロセスや製品品質の向上に貢献します。また、イベントの予測と分析が可能なため、迅速かつ的確な意思決定を支援します。
#### Q: どの規模の半導体工場がMESの恩恵を受けられますか？
A: 工場の規模に関係なく、MESの導入によって恩恵を受けることができます。
自動化製造を始めたばかりの工場でも、完全自動化（lights out）を目指す工場でも、MESは他のシステムと統合しながら、成長する自動化ニーズに対応します。
#### Q: MESはコンピューター統合製造（CIM）システムとどのように関連していますか？
A: コンピューター統合製造（CIM）システムは、生産プロセスのすべての部分を制御することができます。MESはCIMの中心であり、その基盤です。適切に構成されたMESは、基本的な製造においてもすべての処理を定義・調整します。MESには、メーカーのニーズの進化に応じて、追加機能を統合することができ、CIMシステムの機能をさらに豊かにします。
#### Q: CIM（コンピューター統合製造）ソリューションは何ができるのですか？
A: CIMソリューションは、半導体製造プロセス全体を定義、制御、自動化、監視、記録することができます。
これには、前工程のウェーハ製造から後工程の組立、テスト、パッケージングまでが含まれます。
#### Q: MESはサイクルタイムの改善に役立ちますか？
A: はい、MESソフトウェアは、ロット管理、工程、スケジューリング、配送などの複数の工場システムを統合し、データとコミュニケーションの精度と品質を向上させます。
MESは、リアルタイムの可視化、自動データ収集、予測分析、コミュニケーションと協業の改善、生産プロセスの最適化を通じて、サイクルタイムの短縮に貢献します。
#### Q: コンピューター化された保守管理システム（CMMS）は半導体製造にどのようなメリットがありますか？
A: CMMS（コンピューター化保守管理システム）は、計画的、定期的、突発的な保守活動を効果的に管理することができます。
CMMSは、在庫レベルの最適化、装置の稼働率向上、労働力と部品コストの削減に貢献します。
#### Q: 半導体工場にサプライチェーン・エンタープライズ・プランニング・ソリューションは有効ですか？
A: はい、サプライチェーン・エンタープライズ・プランニングは、半導体工場がリソースを最大限に活用するために役立ちます。これにより、顧客の需要予測の変化に迅速に対応し、納期遵守と応答性を向上させることができます。
効果的なサプライチェーン・エンタープライズ・プランニングは、必要な計画データを収集・読込、高速なデータ抽出と処理により迅速に供給計画を生成します。
---
### [お問い合わせ](https://appliedsmartfactory.com/connect/)
**Published:** June 27, 2021
**Author:** Applied Smartfactory
**Content:**
# 世界にポジティブな変化を、
一緒に生み出しませんか？
### お問い合わせ
フォームにご記入いただき、担当者からご連絡いたします。すべての項目は必須です。
First Name: \*
Last Name: \*
Company Name: \*
Business Email: \*
Country/Region: \*
Please select countryAfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
No. of Employees: \*
Please select1-2021-200201-10,00010,000+
Let us know how we can assist: \*
Tell us a bit about your role, goals, or questions so we can route your request appropriately.
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Thank you for contacting us; we will get back to you shortly. In the meantime, please visit our LinkedIn page dedicated to [semiconductor](https://www.linkedin.com/showcase/applied-smartfactory/) industry for the latest updates.
Δ
---
### [SmartFactory MES for ATP](https://appliedsmartfactory.com/manufacturing-execution-solutions/mesforatp/)
**Published:** January 6, 2025
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES for ATP
# 半導体後工程製造向けの先進MES
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 製造現場全体でのマテリアルフローを効率化したいと思っていませんか？
SmartFactory MES for ATPは、半導体後工程（アセンブリ・テスト・パッケージング）におけるモノの流れを可視化・最適化するための包括的なMESソリューションです。このソリューションは、自動化を前提とした「無人化製造」に対応し、先進的なアセンブリやテスト、パッケージングのシナリオをサポートします。また、工場制御を最適化し、異常発生時の対応も自動化されます。SmartFactory MES for ATPを活用することで、新工場の立ち上げや市場投入までの時間を大幅に短縮することが可能です。
## SmartFactory MES for ATPを選ぶ理由
### 90日以内に初回ウェーハ出荷を実現
### 誤処理を最大70%削減
### 稼働率99.99%を達成した確かな実績
## 私たちの取り組みから得られる効果
### 製造効率の向上
- チップアタッチ工程における基板位置や配置順序制御などを実現する柔軟な工程モデリング
- 製造工程全般を通して基板、ロット、チップの確実なトレーサビリティを実現
- 統合化されたMESプラットフォームで従来のアセンブリ、テスト工程から、完全自動化された先進パッケージング工程まで、すべてを一元管理
### 超短期導入
- 事前構築された「ベストプラクティス」製造シナリオにより、90日以内の立ち上げが可能
- 生産立ち上げ期間を短縮し、歩留まり改善を加速させる統合化された機能群
### 無人化製造への対応
- すべて手動運用の製造現場から完全自動化設備まで、柔軟な導入が可能
- 事前定義されたエラーハンドリングにより、予期せぬ製造トラブルにも自動で対応
- 実績に裏付けられたソリューションで、1年以内に無人化製造への移行を実現
---
### [Alarm Management](https://appliedsmartfactory.com/manufacturing-execution-solutions/alarmmanagement/)
**Published:** November 4, 2022
**Author:** Applied Smartfactory
**Content:**
SmartFactory Alarm Management
# 品質と生産性を守るために、アラームを効率的に管理
[ MESブログを見る ](/ja/semiconductor-blog-category/manufacturing-execution-ja/)
## 工場内の膨大なアラームの中から、重要なものをどう見極めますか？
SmartFactory Alarm Managementは、アラームを効率的に管理することで、重要なアラートを迅速に特定・優先順位付け・対応し、適切なアクションを取ることを可能にします。
## SmartFactory Alarm Managementを選ぶ理由
### すべてのアラームをカバーしつつ、「アラーム疲労」を大幅に軽減
### 即時通知により、稼働率が1%向上
### 「重要なアラーム」の特定と意思決定の自動化により、歩留まりが0.5%改善
## 私たちの取り組みから得られる効果
### 解決の迅速化
- リアルタイムのアラーム処理を一元化
- 重複排除アルゴリズムでアラートノイズを削減
- 品質に影響する問題を早期に検出
### ツールの稼働率向上
- CIMスタックからアラームデータを統合し、迅速なトラブルシューティングを実現
- 根本原因分析を加速
- MES、装置自動化、その他のシステム間で、ロットの保留やツールの停止などの事前定義された自動アクションを作成
### コミュニケーションの改善
- アラートの受信者とエスカレーション経路を設定
- 工場全体のリアルタイムビューを提供
---
### [SmartFactory IQworks](https://appliedsmartfactory.com/ai/smartfactory-iqworks/)
**Published:** April 23, 2025
**Author:** Applied Smartfactory
**Content:**
SmartFactory AI IQworksTM
# スケーラブルなAI
ソリューションの統合管理
## 製造現場におけるAIソリューションのスケーリング、どう取り組まれていますか？
SmartFactory AI IQworks は、データおよびモデル管理のための製品です。AI/MLライフサイクル全体を支援し、既存インフラとのシームレスな統合を実現します。当社のアプローチは、AI/MLに必要なデータ準備、モデル構築、展開、監視といった各フェーズを加速・簡素化・スケーラブルにします。
## SmartFactory AI IQworksを選ぶ理由
### OTD改善
（2-3%）
### 歩留まり/スループットの共同最適化
（1-2%）
### Cpk改善
（10-15%）
## 当社のアプローチから得られるもの
### スケーラビリティ
- 大規模なデータ処理と分析、および生産ワークフローを処理するインフラストラクチャ
- AI/MLモデルの強化と維持のためのIP統合能力
### より迅速な展開
- コーディングの専門知識がなくても、AIモデルの導入とモニタリングが可能。
- AI/MLに必要な学習データを作成するためのAIシミュレーターエンジンを提供。
- すぐに使用できるEngineeredWorks®ソリューションを提供
### 共通フレームワーク
- 実績のある生産性および品質製品を活用して、既存のソリューションにAI/MLを実行
---
### [SmartFactory IQworks](https://appliedsmartfactory.com/ai/smartfactory-iqworks/)
**Published:** April 23, 2025
**Author:** Applied Smartfactory
**Content:**
SmartFactory AI IQworks™
# 构建可扩展的 AI 解决方案
## 在您的晶圆厂中，如何实现 AI 解决方案的规模化部署？
SmartFactory AI IQworks 作为专业的数据与模型管理平台，全面支持 AI/ML 全生命周期管理，确保模型与客户现有基础设施的无缝集成。我们的解决方案显著加速，简化以及扩展 AI/ML 所需的数据准备、模型构建、部署及监控等关键环节。
## 为何选择 SmartFactory AI IQworks？
### 准时交付率提升
（2-3%）
### 良率与产能协同优化
（1-2%）
### 制程能力指数（CpK）提升
（10-15%）
## 采用我们的解决方案能为您带来什么？
### 可扩展性
- 可处理海量数据分析与生产工作流的基础设施
- 集成知识产权（IP）以优化和维护 AI/ML 模型的能力
### 更快的部署
- 用户无需编码专业知识即可快速部署与监控 AI 模型
- 提供 AI 模拟器引擎，帮助用户创建 AI/ML 所需的训练数据
- 提供开箱即用的 EngineeredWorks™ 解决方案
### 通用实施框架
- 利用经过验证的生产力与优质产品，将 AI/ML 技术无缝集成至现有解决方案
---
### [SmartFactory IQworks](https://appliedsmartfactory.com/ai/smartfactory-iqworks/)
**Published:** April 23, 2025
**Author:** Applied Smartfactory
**Content:**
SmartFactory AI IQworksTM
# Orchestrating Scalable AI Solutions
## In your fab, how do you scale AI solutions?
SmartFactory AI IQworks is a data and model management product. It facilitates the entire AI/ML lifecycle, ensuring seamless integration of models with a customer’s existing infrastructure. Our approach accelerates, simplifies, and scales the data preparation, model building, deployment, and monitoring phases required for AI/ML.
## Why choose SmartFactory AI IQworks?
### OTD Improvement (2-3%)
### Co-Optimization of Yield / Throughput (1-2%)
### Cpk Improvement (10-15%)
## What can you gain from our approach?
### Scalability
- An infrastructure to handle large-scale data processing and analysis, along with production workflows
- Ability to integrate IP for enhancing and maintaining AI/ML models
### Faster deployment
- Enable users to deploy and monitor AI models without coding expertise
- Offers AI Simulator engine to empower users to create the necessary training data for AI/ML
- Offers ready to use EngineeredWorks® Solutions
### Common framework
- Utilizing proven productivity and quality products to execute AI/ML into existing solutions
---
### [Simulation AutoMod](https://appliedsmartfactory.com/supply-chain-solutions/simulation-automod/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoMod™
# 模拟现实
[ 全球经销商 ](/zh-hans/worldwide-automod-distributors/)
[ 学术许可 ](/zh-hans/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/)
[ 学生版 ](/zh-hans/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/#student-version)
经慎重考虑，应用材料公司已经做出了业务决定，将在2026年12月31日之后停止销售和支持 AutoMod。我们的首要任务是确保客户的业务的连续性和成功。如果您有任何进一步的问题，请随时与我们[联系。](/zh-hans/connect/)
## 您用的是不是二维仿真软件或者运行非常缓慢？
不是所有仿真软件都能完成您所期待的任务。 SmartFactory Simulation AutoMod是一套全球领先的图形化仿真模拟软件，它可以用于建模、仿真和分析复杂的制造和材料处理系统。 该软件中融入了应用材料公司30年的行业经验，使得AutoMod成为了全球顶级材料处理供应商和系统集成商的首选，支持用户将细节信息引入他们的模型，从而准确反映现实情况。
## 为什么选择SmartFactory Simulation AutoMod？
### 降低了设计错误的风险
### 降低操作瓶颈风险
### 提高产出、改善物流
## 您能从我们的解决方案中获得什么？
## 更高的准确度
- 将细节信息引入模型，从而准确地反映现实情况
- 将正在运行的设施形象化，并可从任何角度进行查看
## 更大的灵活性
- 可实现任何大小或细节程度的仿真模拟，从手动操作、工作单元、叉车到机票柜台和半导体工厂
- 该模型也可以被用作仿真器来模拟电机、传感器及其他设备
## 更高的盈利
- 优化设备、人员和资源
- 通过识别和解决产能限制和瓶颈问题，提高系统集成能力
- 降低设备要求
---
### [Schedule a Meeting](https://appliedsmartfactory.com/ai/schedule-a-meeting/)
**Published:** May 2, 2025
**Author:** Jill Oana
**Content:**
# お問い合わせ
フォームにご記入いただき、担当者からご連絡いたします。
※印のある項目は必須です。
First Name: \*
Last Name: \*
Business Email: \*
Country: \*
Select your countryAfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Job Title: \*
Department:
Company Name: \*
No. of Employees: \*
Please select1-2021-200201-10,00010,000+
Meeting Topics (check all that apply) \*
Current Generative AI CapabilitiesGetting Started GuideGenerative AI RoadmapOther (Mention in Message)
Let us know how we can assist:
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
---
### [SmartFactory MES for ATP](https://appliedsmartfactory.com/manufacturing-execution-solutions/mesforatp/)
**Published:** January 6, 2025
**Author:** Applied Smartfactory
**Content:**
SmartFactory MES for ATP
# 半导体后段制造先进 MES 系统
## 您是否希望简化整个生产设施中的物料流转？
SmartFactory MES for ATP 是一套完整的系统，可简化并监控半导体后段制造工厂的物料流转。MES for ATP 专为支持无人工厂生产而设计，提供先进的封装、测试和包装自动化方案，优化工厂控制并自动处理生产异常。使用 SmartFactory MES for ATP，您可以加速新工厂投产并缩短产品上市时间。
## 为何选择 SmartFactory MES for ATP？
### 90 天内实现首片晶圆产出
### 减少高达 70% 的误操作
### 实际验证 99.99% 生产运行时间
## 采用我们的解决方案能为您带来什么？
### 提升制造效率
- 灵活的芯片贴装建模，包括基板定位和贴装顺序
- 精确追踪芯片、基板和批次在整个制造过程中的流向
- 统一的 MES 系统平台处理从传统测试封装到全自动化先进封装的所有环节
### 快速部署
- 预构建的“最佳实践”制造方案，90天内实现首片晶圆产出
- 集成功能最大限度缩短生产爬坡时间并加快良率提升
### 实现无人工厂生产
- 支持从手动操作到全自动制造的灵活部署
- 预定义错误处理方案，自动恢复意外制造事件
- 实际验证可在一年内实现从投产到全自动化无人工厂的完整过渡
---
### [サポート](https://appliedsmartfactory.com/support/)
**Published:** December 3, 2021
**Author:** Applied Smartfactory
**Content:**
グローバルサポート
# ソフトウェアポータル
## サービス一覧
[ ](https://amat.service-now.com/csm)
#### [ ポータルログイン ](https://amat.service-now.com/csm)
[ ](https://partner.amat.com/identityiq/external/amat/resetPassword/rstPwdBaseForm.jsf)
#### [ パスワードのリセット ](https://partner.amat.com/identityiq/external/amat/resetPassword/rstPwdBaseForm.jsf)
[ ](/ja/support-contacts/)
#### [ 地域別のサポート
センター連絡先 ](/ja/support-contacts/)
[ ](mailto:customer_portal_support@amat.com)
#### [ ポータルに関するヘルプ ](mailto:customer_portal_support@amat.com)
**Apache log4j脆弱性による影響について**
アプライド マテリアルズの自動化製品グループ（APG）は、「Log4Shell」と呼ばれるApache Log4Jの脆弱性（CVE-2021-44228）の調査と緩和策の特定に
引き続き取り組んでいます。APG は引き続き、この脆弱性の調査と修復を最優先課題として取り組んでいます。
CVE-2021-44228に関する詳細はApache Announcementから入手可能です：
影響を受ける可能性のある製品、および解決方法の技術的な詳細などの情報については、APG サポートチームまでお問い合わせください。
#### ソフトウェアポータルでは、現在保守契約を結んでいるユーザーが以下の情報を受け取ることができます：
- 最新のGAリリースとパッチ
- 製品関連のお知らせ
- ソフトウェアサポート専門家へのアクセス
#### ログインしている間、ユーザーは以下の項目を行うことができます：
- 現在のケースのステータスの確認
- 新しいケースのログ
- アプライド・ボックスのFTPオプションへのアクセス
- ナレッジベース資料の閲覧
---
### [Solution Brief AI ML](https://appliedsmartfactory.com/productivity-solutions/ai-productivity/solution-brief/)
**Published:** October 7, 2024
**Author:** Applied Smartfactory
**Content:**
# Take intelligent manufacturing to the next level
## Easily deploy AI/ML model predictions into your current manufacturing environment
#### Solution Brief
# Take intelligent manufacturing to the next level
Learn how to easily deploy AI/ML model predictions into your current manufacturing environment with SmartFactory AI™ Productivity.
Role of Automation in Semiconductor Manufacturing
Increased demand and complex designs are challenging semiconductor manufacturers to become more efficient, develop higher quality products and do so significantly faster. Automating manual processes has been a valuable first step toward meeting customer and global trade needs. The next generation of intelligent manufacturing will be quality-aware, able to respond to events in real-time, and focused on optimizing yield and throughput.
Download the solution brief to learn more about:
### Addressing quality and productivity obstacles
### Ready-to-use machine learning models
### Potential gains in throughput and yield
## Download the solution brief now
First Name: \*
Last Name: \*
Company Email: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist. To stay updated on our products and services, please also check the box below. You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
---
### [Innovation Forum 2022](https://appliedsmartfactory.com/innovationforum2022/)
**Published:** June 7, 2022
**Author:** Applied Smartfactory
**Content:**
# Optimizing existing assets
#### SmartFactory productivity solutions fully integrated
### 19th Innovation Forum for Automation
##### June 30 – July 1, 2022 | Dresden, Germany
## Keynote | **Manufacturing Limitations and Opportunities**
### Thursday, June 30 at 13:10 - 13:45
### David F. Hanny
##### Sr. Director, Strategy and Marketing
Applied Materials | Automation Products Group
### Madhav Kidambi
##### Director, Technical Marketing
Applied Materials | Automation Products Group
### Keynote topics:
### Why technology advancement and integration are both necessary to make intelligent decisions in real-time
### How semiconductor factories are accelerating real-time decision-making
### Use cases on how to expedite your journey to increase manufacturing performance
### For questions, contact
[Thomas\_Wimmer@amat.com](mailto:Thomas_Wimmer@amat.com)
### To view full conference agenda
[ Visit agenda ](https://www.innovation-forum-automation.com/conference/agenda/)
[ SmartFactory Productivity Solutions ](/semiconductor/productivity-solutions/)
Optimizing Existing Assets
- [ SmartFactory Insights Blog ](/blog/category/productivity/)
- [ SmartFactory Semiconductor Solutions ](https://www.linkedin.com/showcase/applied-smartfactory/)
- [ appliedsmartfactory.com ](/semiconductor)
## 19th Innovation Forum for Automation
June 30 – July 1, 2022 | Dresden, Germany
---
### [Symposium China](https://appliedsmartfactory.com/symposium-china/)
**Published:** April 7, 2023
**Author:** Applied Smartfactory
**Content:**
[ 简体中文 (Simplified Chinese) ](/zh-hans/symposium-china/)
[ English (英语) ](#)
## SmartFactory Symposium 2023
**Breakthroughs in Manufacturing Intelligence**
Shanghai, China | Friday, June 30, 2023
### Highlights
### Full day symposium
### Technical breakout sessions
### Live SmartFactory product demos
### For questions, contact
[Housman\_Chen@amat.com](mailto:Housman_Chen@amat.com)*Applied Materials China*[Jardon\_Xiao@amat.com](mailto:Jardon_Xiao@amat.com)*Applied Materials China*[James\_SC\_Chang@amat.com](mailto:James_SC_Chang@amat.com)*Applied Materials Chinese Taiwan*[Sean\_Yong@amat.com](mailto:Sean_Yong@amat.com)*Applied Materials Southeast Asia*
### To view schedule
[ View Full Agenda ](#)
---
### [E3 User Group 2022](https://appliedsmartfactory.com/e3usergroup2022/)
**Published:** September 1, 2022
**Author:** Applied Smartfactory
**Content:**
Striving for Zero Defects
SmartFactory Process Quality solutions fully integrated
## Applied E3® User Group
#### Featuring SmartFactory quality solutions
##### Thu October 13, 2022 | 9 am – 4 pm
Hilton Austin Airport | Austin, TX
[ Register ](#)
## Meet our Presenters at [APCSM Conference](https://web.cvent.com/event/31e2fdca-5d2b-4348-9b21-7b42239692f3/summary)
### Pratik Kotcher
Quality Solutions Architect
Applied Materials | Automation Products Group
Presenting:#### Investigating Context Grouping vs Machine Learning Technique of Clustering
### SJ Wang
Global Product Manager
Applied Materials | Automation Products Group
Presenting:#### Reducing Tool Matching Time by Integrating YMS and Process Quality Systems
### Highlights of the event:
### New features and functions in versions 8.7 and 8.9
### E3 roadmap collaborative discussion for future design enhancements
### Launch and demo of new OCAP module, Knowledge Advisor
### Technical presentations on optimizing Fault Detection, SPC3D, and Run-to-Run implementations
### Attend Applied E3® User Group
Featuring SmartFactory quality solutions
Fault Detection | SPC3D | Run-to-Run
##### **Thu October 13, 2022 | 9 am – 4 pm**
Hilton Austin Airport | Austin, TX
[ Register ](#)
[ SmartFactory Process Quality Solutions ](/semiconductor/process-quality-solutions/)
Striving for Zero Defects
- [ SmartFactory Insights Blog ](https://appliedsmartfactory.com/blog/)
- [ SmartFactory Semiconductor Solutions ](https://www.linkedin.com/showcase/applied-smartfactory/)
- [ appliedsmartfactory.com ](https://appliedsmartfactory.com/)
## Applied E3®User Group
Oct 13, 2022 in Austin, TX
---
### [APC Network BBQ](https://appliedsmartfactory.com/apcnetworkbbq/)
**Published:** September 30, 2022
**Author:** Applied Smartfactory
**Content:**
#### Join Us
### at our Networking BBQ
## Thu Oct 13 @ 6:00 pm
Lamberts Downtown Barbecue
##### 401 W. 2nd Street. Austin, TX 78701
[ Restaurant details ](https://goo.gl/maps/X5gW4h7pht1kFUMG9)
### Hosted by SmartFactory
Process Quality team
For more info, contact [Christopher\_Reeves@amat.com ](mailto:Christopher_Reeves@amat.com)
## Networking BBQ
Hosted by SmartFactory Process Quality team
---
### [APC Europe 2023](https://appliedsmartfactory.com/apceurope2023/)
**Published:** February 22, 2023
**Author:** Applied Smartfactory
**Content:**
# Striving for Zero Defects
SmartFactory Process Quality solutions fully integrated
## apc|m europe
#### Bruges, Belgium March 28 - 30, 2023
[ Schedule Onsite Demo ](/apceurope2023/schedule-onsite-demo/)
## Prime Sponsorship Presentation
## Unifying Process Control to Disrupt Manufacturing Principles
### Wed March 29, 2023 | 09:00
### Christopher Reeves
##### Global Product Manager, E3 Platform
Applied Materials
## Poster Sessions
### Tue, March 28, 2023 | 17:00
### K Means Clustering for Solving Matching Problems in Semiconductor Factories
### Vishali Ragam
##### Quality Solutions Architect
Applied Materials
### The Impact of Tool Allocation and Dedication on Cycle Time
### Gary O’Driscoll
##### Module Process Engineer
Applied Materials
### Our team of quality solution experts are here to
### Explore your challenges in the factory
### Identify zero defect strategies to increase quality and reliability
### Host 1:1 onsite demos of our fully integrated quality solutions
### For questions or to schedule a demo, contact
[Christopher\_Reeves@amat.com](mailto:Christopher_Reeves@amat.com)
[ Schedule Onsite Demo ](/apceurope2023/schedule-onsite-demo/)
### To view full conference agenda
[ Visit agenda ](https://www.apcm-europe.eu/conference/agenda/)
[ SmartFactory Process Quality Solutions ](/semiconductor/process-quality-solutions/)
Striving for Zero Defects
- [ SmartFactory Insights Blog ](/blog/)
- [ SmartFactory Semiconductor Solutions ](https://www.linkedin.com/showcase/applied-smartfactory/)
- [ appliedsmartfactory.com ](/)
---
### [APC Europe 2022](https://appliedsmartfactory.com/apceurope2022/)
**Published:** March 23, 2022
**Author:** Applied Smartfactory
**Content:**
# Striving for Zero Defects
SmartFactory Process Quality solutions fully integrated
## European apc|m Conference
#### April 4-6 in Toulon, France
Vishali Ragam
Quality Solutions Architect
Applied Materials
Presenting:
#### Contextual Pattern Mining to Drive Process Quality
##### Session 1 | Mon, April 4
15:00 – 16:15
[ View Agenda ](https://www.apcm-europe.eu/conference/agenda/conference-program/)
## Our team of quality solution experts are here to:
- Explore your challenges in the factory
- Identify zero-defect strategies to increase quality and reliability
- Host 1:1 sessions to see demos of our fully integrated quality solutions
[ SmartFactory Process Quality Solutions ](/semiconductor/process-quality-solutions/)
Striving for Zero Defects
- [ SmartFactory Insights Blog ](https://appliedsmartfactory.com/blog/)
- [ SmartFactory Semiconductor Solutions ](https://www.linkedin.com/showcase/applied-smartfactory/)
- [ appliedsmartfactory.com ](https://appliedsmartfactory.com/)
## European apc|m Conference
April 4-6 in Toulon, France
---
### [APC Europe 2024](https://appliedsmartfactory.com/apceurope2024/)
**Published:** March 6, 2024
**Author:** Applied Smartfactory
**Content:**
# Striving for Zero Defects
SmartFactory Process Quality solutions fully integrated
## apc|m europe
#### Hamburg, Germany April 16-18, 2024
###### [Semiconductor Quality ](https://appliedsmartfactory.com/semiconductor-blog-category/quality/)
#### [ Synergizing Fault Detection and SPC: smarter manufacturing solution for cost reduction ](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
Integrating the functions of Statistical Process Control (SPC) and Fault Detection (FD) helps semiconductor manufacturers achieve higher quality, reliability, a...
###### [By Vishali Ragam, Global Product Manager, SPC](https://appliedsmartfactory.com/author/vishali-ragam/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
### For questions or to schedule a demo, contact
[Christopher\_Reeves@amat.com](mailto:Christopher_Reeves@amat.com)
### To view full conference agenda
[ Visit agenda ](https://www.apcm-europe.eu/home/)
---
### [MES Faqs](https://appliedsmartfactory.com/mes-faqs/)
**Published:** March 13, 2024
**Author:** Applied Smartfactory
**Content:**
# FAQs: Manufacturing Execution Solutions
#### How does automated manufacturing work in the semiconductor industry?
The semiconductor industry uses automated manufacturing to integrate multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication.
#### What are the benefits of automated manufacturing?
Automated manufacturing solutions can improve productivity and quality while reducing overall costs. Among the many ways they do so is by enabling improved collaboration in one factory or across sites, providing accurate insights into equipment states for better tool management, and managing scheduling solutions using real-time data.
#### What is a Manufacturing Execution System (MES) for semiconductor manufacturing?
The manufacturing execution system is the operational backbone of many semiconductor factories and can help monitor, control, and optimize production processes in real-time. MES manufacturing software can help improve a semiconductor factory’s processes and product quality. Because of its ability to predict and analyze events, it also helps manufacturers make informed decisions more quickly.
#### What size semiconductor factory can benefit from a MES?
Factories of all sizes can benefit from deploying a manufacturing execution system, whether they are just getting started with automated manufacturing or looking to go lights out. MES manufacturing software integrates with additional systems as the factory and its automation needs grow.
#### How is the MES related to the Computer Integrated Manufacturing (CIM) system?
The Computer Integrated Manufacturing (CIM) system can control every part of the production process. The MES is at the heart of the CIM, its foundation. A properly configured MES defines and coordinates all processing within even the most basic manufacturing. Additional capabilities can be added to and integrated with the MES over time to enable richer functionality in the CIM system as a manufacturer’s needs evolve.
#### What can the CIM solution do?
A Computer Integrated Manufacturing (CIM) solution allows manufacturers to define, control, automate, monitor, and record the entire semiconductor manufacturing process from front-end wafer fabrication through back-end assembly, test, and packaging.
#### Can a MES help improve cycle time?
Yes, the MES software integrates multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication. MES manufacturing software can help improve cycle time by providing real-time visibility, automating data collection, using predictive analytics, improving communication and collaboration, and optimizing production processes.
#### How does a Computerized Maintenance Management System (CMMS) benefit semiconductor manufacturing?
Computerized maintenance management systems (CMMS) can effectively manage planned, scheduled, and unscheduled maintenance activities. A CMMS optimizes the management of overall inventory levels, improves equipment availability, and decreases labor and parts costs.
#### Would my semiconductor fab benefit from a supply chain enterprise planning solution?
Supply chain enterprise planning helps a semiconductor fab manage its resources to its greatest advantage. This helps manufacturers respond to customer forecast changes and improve on-time delivery and responsiveness. An effective supply chain enterprise planning solution can gather and load all necessary planning data and quickly generate supply plans using proven, high speed data extraction and processing.
---
### [MES Series](https://appliedsmartfactory.com/series/mes/)
**Published:** July 21, 2023
**Author:** Applied Smartfactory
**Content:**
# SmartFactory MES
[ 最新发布 ](#newly-released)
[ 热门博客 ](#popular)
[ 值得一看 ](#bingeworthy)
#### 最新发布
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Automated tool recovery increases equipment efficiency ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
SmartFactory 300works® can help reduce an often-overlooked component of maintenance downtime
###### [By Seong Hoon Lee and Boon Guan Lim](https://appliedsmartfactory.com/author/boon-guan-lim/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Are you ready to achieve new levels of real-time decision intelligence in your factory? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
New SmartFactory message bus – critical to enable advanced automated manufacturing
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Reduce cycle time with a powerful MES strategy ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
Increase KPIs by automating repetitive tasks and improving communication
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Reduce production noise and boost operation efficiency ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
SmartFactory team unveils new solution for handling alarms
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Improving operational efficiency through better data visualization ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
Make easy, consistent, and visually appealing charts for data-driven decisions using SmartFactory Material Control and APF Reporter
###### [By John Robinson](https://appliedsmartfactory.com/author/john-robinson/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
###### [Semiconductor Quality ](https://appliedsmartfactory.com/semiconductor-blog-category/quality/)
#### [ The Point of Truth for Runtime Recipe Control ](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
The latest release of SmartFactory Recipe Management offers better data synchronization options for runtime recipe control.
###### [By Eric Warren](https://appliedsmartfactory.com/author/eric-warren/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Ready to optimize your packaging solutions? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
Overview on ways we can help you to leverage the latest trends in solving packaging challenges.
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Optimize system performance, detect and predict system failures. ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
Keep your factory healthy and running smoothly using run-time monitoring and predictive analytics algorithms
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ EngineeredWorks® increases speed-to-value for manufacturers and provides quicker deployment times ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
Gain continuous improvements in operations and construction of new factories.
###### [By David Hanny](https://appliedsmartfactory.com/author/david-hanny/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
###### [Semiconductor Use Cases ](https://appliedsmartfactory.com/semiconductor-blog-category/use-cases/)
#### [ UMC describes how they achieved manufacturing operations excellence ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
UMC integrates real-time dispatching, full automation workflow, MES 300works® and more.
###### [By YY Chen](https://appliedsmartfactory.com/author/yy-chen/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
#### 热门博客
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Manufacturing discipline starts at the substrate: Why execution can’t wait for the fab ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
Front-end execution increasingly determines semiconductor outcomes
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Predict, don’t react ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
Why predictive monitoring is essential for maximizing uptime in semiconductor manufacturing
###### [By Yoram Barak, Global Product Manager](https://appliedsmartfactory.com/author/yoram-barak-phd/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Are you ready to achieve new levels of real-time decision intelligence in your factory? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
New SmartFactory message bus – critical to enable advanced automated manufacturing
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Applied pathway for faster automation – MES deployment in 90 days (Part 1/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
Deploy SmartFactory MES 300works® in 90 days: rely on experienced team and proven process
###### [By Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®](https://appliedsmartfactory.com/author/seong-hoon-lee/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Achieve critical factory KPIs with industry-proven turnkey CIM solution ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
Integrate automation capabilities across your entire factory domain with our SmartFactory CIM solution.
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Using plug & play Spares and ERP modules with maintenance management lowers integration costs, reduces complexity, and improves OEE ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
The right parts at the right tool at the right time
###### [By John Robinson](https://appliedsmartfactory.com/author/john-robinson/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Bringing production reality closer to target ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
Driving the “S curve” to enable performance throughout your fab’s life cycle
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Ready to improve operations, increase yields and drive profits? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
Rely on our integrated solutions to prioritize quality and reliability across every stage of the manufacturing process.
###### [By Wei Xiaowei, ChinaAET.com](https://appliedsmartfactory.com/author/wei-xiaowei-chinaaet-com/)
[Download PDF](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Ready to optimize your packaging solutions? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
Overview on ways we can help you to leverage the latest trends in solving packaging challenges.
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ EngineeredWorks® increases speed-to-value for manufacturers and provides quicker deployment times ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
Gain continuous improvements in operations and construction of new factories.
###### [By David Hanny](https://appliedsmartfactory.com/author/david-hanny/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
###### [Semiconductor Use Cases ](https://appliedsmartfactory.com/semiconductor-blog-category/use-cases/)
#### [ UMC describes how they achieved manufacturing operations excellence ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
UMC integrates real-time dispatching, full automation workflow, MES 300works® and more.
###### [By YY Chen](https://appliedsmartfactory.com/author/yy-chen/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
#### 值得一看
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Beyond the MES: Crawl. Walk. Run. (Part 1/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
The MES provides a critical foundation for the semiconductor factory as needs change over time.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Beyond the MES: Fly. (Part 2/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
Advanced capabilities and MES provide the intelligence that is key to the ‘lights out’ factory
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
An aspirational view from the factory floor (Part 1/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
The MES is the operational backbone of the factory. But it should be so much more!
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
All about process configurations (Part 2/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
Taking a deep dive into MES configurations.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Lot tracking: the MES at run-time (Part 3/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
Keeping track of all the moving parts through lot tracking.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Data and metrics that drive the factory (Part 4/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
Key MES data and metrics…and how manufacturers use them.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Reporting and analytics for continuous improvement (Part 5/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
MES reporting and analysis | your tools to answer questions and solve problems.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Emerging Challenges (Part 1 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
Learn what matters most to experts as they address emerging challenges and complexities in semiconductor backend manufacturing.
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – SmartFactory Roadmap (Part 2 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
Roadmap to achieve full automation in semiconductor backend manufacturing.
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Overcoming Roadblocks (Part 3 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
Organization readiness, data, equipment, factory layout, material handling….do these roadblocks sound familiar? Watch this video (part 3 of 3) to get tips from...
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
[mv_grow_share url="https://appliedsmartfactory.com/series/mes/"]
---
### [MES Series](https://appliedsmartfactory.com/series/mes/)
**Published:** May 22, 2023
**Author:** Applied Smartfactory
**Content:**
# Smartfactory MES
[ Newly Released ](#newly-released)
[ Popular ](#popular)
[ Bingeworthy ](#bingeworthy)
#### Newly Released
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Automated tool recovery increases equipment efficiency ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
SmartFactory 300works® can help reduce an often-overlooked component of maintenance downtime
###### [By Seong Hoon Lee and Boon Guan Lim](https://appliedsmartfactory.com/author/boon-guan-lim/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Are you ready to achieve new levels of real-time decision intelligence in your factory? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
New SmartFactory message bus – critical to enable advanced automated manufacturing
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Reduce cycle time with a powerful MES strategy ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
Increase KPIs by automating repetitive tasks and improving communication
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Reduce production noise and boost operation efficiency ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
SmartFactory team unveils new solution for handling alarms
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Improving operational efficiency through better data visualization ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
Make easy, consistent, and visually appealing charts for data-driven decisions using SmartFactory Material Control and APF Reporter
###### [By John Robinson](https://appliedsmartfactory.com/author/john-robinson/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
###### [Semiconductor Quality ](https://appliedsmartfactory.com/semiconductor-blog-category/quality/)
#### [ The Point of Truth for Runtime Recipe Control ](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
The latest release of SmartFactory Recipe Management offers better data synchronization options for runtime recipe control.
###### [By Eric Warren](https://appliedsmartfactory.com/author/eric-warren/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Ready to optimize your packaging solutions? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
Overview on ways we can help you to leverage the latest trends in solving packaging challenges.
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Optimize system performance, detect and predict system failures. ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
Keep your factory healthy and running smoothly using run-time monitoring and predictive analytics algorithms
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ EngineeredWorks® increases speed-to-value for manufacturers and provides quicker deployment times ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
Gain continuous improvements in operations and construction of new factories.
###### [By David Hanny](https://appliedsmartfactory.com/author/david-hanny/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
###### [Semiconductor Use Cases ](https://appliedsmartfactory.com/semiconductor-blog-category/use-cases/)
#### [ UMC describes how they achieved manufacturing operations excellence ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
UMC integrates real-time dispatching, full automation workflow, MES 300works® and more.
###### [By YY Chen](https://appliedsmartfactory.com/author/yy-chen/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
#### Popular
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Manufacturing discipline starts at the substrate: Why execution can’t wait for the fab ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
Front-end execution increasingly determines semiconductor outcomes
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Predict, don’t react ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
Why predictive monitoring is essential for maximizing uptime in semiconductor manufacturing
###### [By Yoram Barak, Global Product Manager](https://appliedsmartfactory.com/author/yoram-barak-phd/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Are you ready to achieve new levels of real-time decision intelligence in your factory? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
New SmartFactory message bus – critical to enable advanced automated manufacturing
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Applied pathway for faster automation – MES deployment in 90 days (Part 1/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
Deploy SmartFactory MES 300works® in 90 days: rely on experienced team and proven process
###### [By Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®](https://appliedsmartfactory.com/author/seong-hoon-lee/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Achieve critical factory KPIs with industry-proven turnkey CIM solution ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
Integrate automation capabilities across your entire factory domain with our SmartFactory CIM solution.
###### [By Bing Wang, Director of CIM Solution](https://appliedsmartfactory.com/author/bing-wang-2/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Using plug & play Spares and ERP modules with maintenance management lowers integration costs, reduces complexity, and improves OEE ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
The right parts at the right tool at the right time
###### [By John Robinson](https://appliedsmartfactory.com/author/john-robinson/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Bringing production reality closer to target ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
Driving the “S curve” to enable performance throughout your fab’s life cycle
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Ready to improve operations, increase yields and drive profits? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
Rely on our integrated solutions to prioritize quality and reliability across every stage of the manufacturing process.
###### [By Wei Xiaowei, ChinaAET.com](https://appliedsmartfactory.com/author/wei-xiaowei-chinaaet-com/)
[Download PDF](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Ready to optimize your packaging solutions? ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
Overview on ways we can help you to leverage the latest trends in solving packaging challenges.
###### [By SmartFactory Automation Solution Experts Team](https://appliedsmartfactory.com/author/smartfactory-automation-solution-experts-team/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ EngineeredWorks® increases speed-to-value for manufacturers and provides quicker deployment times ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
Gain continuous improvements in operations and construction of new factories.
###### [By David Hanny](https://appliedsmartfactory.com/author/david-hanny/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
###### [Semiconductor Use Cases ](https://appliedsmartfactory.com/semiconductor-blog-category/use-cases/)
#### [ UMC describes how they achieved manufacturing operations excellence ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
UMC integrates real-time dispatching, full automation workflow, MES 300works® and more.
###### [By YY Chen](https://appliedsmartfactory.com/author/yy-chen/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
#### Bingeworthy
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Beyond the MES: Crawl. Walk. Run. (Part 1/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
The MES provides a critical foundation for the semiconductor factory as needs change over time.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Beyond the MES: Fly. (Part 2/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
Advanced capabilities and MES provide the intelligence that is key to the ‘lights out’ factory
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
An aspirational view from the factory floor (Part 1/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
The MES is the operational backbone of the factory. But it should be so much more!
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
All about process configurations (Part 2/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
Taking a deep dive into MES configurations.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Lot tracking: the MES at run-time (Part 3/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
Keeping track of all the moving parts through lot tracking.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Data and metrics that drive the factory (Part 4/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
Key MES data and metrics…and how manufacturers use them.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Reporting and analytics for continuous improvement (Part 5/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
MES reporting and analysis | your tools to answer questions and solve problems.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Emerging Challenges (Part 1 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
Learn what matters most to experts as they address emerging challenges and complexities in semiconductor backend manufacturing.
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – SmartFactory Roadmap (Part 2 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
Roadmap to achieve full automation in semiconductor backend manufacturing.
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Overcoming Roadblocks (Part 3 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
Organization readiness, data, equipment, factory layout, material handling….do these roadblocks sound familiar? Watch this video (part 3 of 3) to get tips from...
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
[mv_grow_share url="https://appliedsmartfactory.com/series/mes/"]
---
### [Simulation AutoMod](https://appliedsmartfactory.com/supply-chain-solutions/simulation-automod/)
**Published:** October 4, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory Simulation AutoMod®
# Simulate reality
[ Global resellers ](/worldwide-automod-distributors/)
[ Academic license ](/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/)
[ Student version ](/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/#student-version)
After careful consideration, Applied Materials has made the business decision to discontinue sales and support for AutoMod after December 31, 2026. Our top priority is to ensure business continuity and success of our customers. Please [contact us](/connect/) if you have further questions.
## Are your simulation tools two dimensional or slow to run?
Not all simulation modeling tools are created equal. SmartFactory Simulation AutoMod is the leading graphical simulation software package for modeling, analyzing, and emulating complex manufacturing and material handling systems. With over 30 years of industry experience built into the product, AutoMod is the product of choice for top material handling providers and systems integrators worldwide, offering a superior level of detail in models to reflect reality.
## Why choose SmartFactory Simulation AutoMod?
### Reduced risk of costly design mistakes
### Reduced risk of operating bottlenecks
### Improved throughput and material flow
## What can you gain from our approach?
## Greater accuracy
- Incorporate a greater level of detail into models to accurately reflect reality
- Visualize a facility in action and view it from any angle
## Greater flexibility
- Simulate systems of any size or level of detail—from manual operations, works cells, and fork trucks to airline ticket counters and semiconductor fabs
- Use models as an emulator to emulate motors, sensors, and other equipment
## Greater profitability
- Optimize equipment, personnel, and resources
- Improve system integration by identifying and resolving capacity constraints and bottlenecks
- Reduce equipment requirements
[ Global resellers ](/worldwide-automod-distributors/)
[ Academic license ](/semiconductor/supply-chain-solutions/simulation-automod/for-students-and-academics/)
[ Student version ](#student-version)
---
### [MES Video Channel](https://appliedsmartfactory.com/?page_id=13485)
**Published:** February 20, 2024
**Author:** Applied Smartfactory
**Content:**
# [New MES video channel](/mes-channel/)
[  ](/mes-channel/)
[SmartFactory MES automation solutions](/mes-channel/)
[  ](/mes-channel/)
[ Learn more ](/semiconductor-mes-video-channel/)
[  ](/mes-channel/)
SmartFactory MES automation solutions
[  ](/mes-channel/)
[ Learn more ](/semiconductor-mes-video-channel/)
---
### [Blog Series](https://appliedsmartfactory.com/series/)
**Published:** May 31, 2022
**Author:** Applied Smartfactory
**Content:**
Insights Blog
# Special Series
[ Beyond the MES (Part 1-2) ](#beyond-the-MES)
[ What is an MES? (Part 1-5) ](#what-is-an-MES)
[ Assembly Test Series (Part 1-3) ](#assembly-test-series)
[ Common Data Models (Part 1-3) ](#common-data-models)
## Beyond the MES by Dan Meier
The MES provides a critical foundation for the semiconductor factory as needs change over time.
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Beyond the MES: Crawl. Walk. Run. (Part 1/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
The MES provides a critical foundation for the semiconductor factory as needs change over time.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ Beyond the MES: Fly. (Part 2/2) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
Advanced capabilities and MES provide the intelligence that is key to the ‘lights out’ factory
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
## What is an MES? by Dan Meier
The MES is the operational backbone of the factory. But it should be so much more!
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
An aspirational view from the factory floor (Part 1/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
The MES is the operational backbone of the factory. But it should be so much more!
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
All about process configurations (Part 2/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
Taking a deep dive into MES configurations.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Lot tracking: the MES at run-time (Part 3/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
Keeping track of all the moving parts through lot tracking.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Data and metrics that drive the factory (Part 4/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
Key MES data and metrics…and how manufacturers use them.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ What is an MES?
Reporting and analytics for continuous improvement (Part 5/5) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
MES reporting and analysis | your tools to answer questions and solve problems.
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
## Assembly Test Series by Joe Napiah
The Road to Full Auto in Semiconductor Assembly Test Manufacturing
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Emerging Challenges (Part 1 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
Learn what matters most to experts as they address emerging challenges and complexities in semiconductor backend manufacturing.
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – SmartFactory Roadmap (Part 2 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
Roadmap to achieve full automation in semiconductor backend manufacturing.
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Overcoming Roadblocks (Part 3 of 3) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
Organization readiness, data, equipment, factory layout, material handling….do these roadblocks sound familiar? Watch this video (part 3 of 3) to get tips from...
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
## Common Data Models by Madhav Kidambi
Common Data Model enables RAPID deployment for productivity solutions
###### [Semiconductor Productivity ](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
#### [ Common Data Model enables RAPID deployment for productivity solutions – Challenges (Part 1/3) ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
Data challenges for rapid deployment of factory productivity and supply chain solutions
###### [By Madhav Kidambi, Director, Technical Marketing, Automation Products Group](https://appliedsmartfactory.com/author/madhav-kidambi/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
###### [Semiconductor Productivity ](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
#### [ Common Data Model enables RAPID deployment for productivity solutions – Solutions (Part 2/3) ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
Common data framework for rapid deployment of factory productivity and supply chain solutions
###### [By Madhav Kidambi, Director, Technical Marketing, Automation Products Group](https://appliedsmartfactory.com/author/madhav-kidambi/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
###### [Semiconductor Productivity ](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
#### [ Common Data Model enables RAPID deployment for productivity solutions – Dispatching and Reporting (Part 3/3) ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
Improve cycle time by 10% in less than 6 months using SmartFactory Dispatching Solution
###### [By Madhav Kidambi, Director, Technical Marketing, Automation Products Group](https://appliedsmartfactory.com/author/madhav-kidambi/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
[mv_grow_share url="https://appliedsmartfactory.com/series/"]
---
### [Blog Series](https://appliedsmartfactory.com/series/)
**Published:** August 3, 2022
**Author:** Applied Smartfactory
**Content:**
洞察力博客
# 专题系列
## MES 系统是什么？作者：Dan Meier
MES 系统是工厂的运营骨干，但它的作用还远不止如此！
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ MES系统是什么？
来自工厂车间的高效管理视角 (第 1 篇，共 5 篇) ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
MES 系统是工厂的运营骨干，但它的作用还远不止如此！
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ MES系统是什么？
关于流程配置的一切（第 2 集，共 5 集） ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
深入了解 MES 系统的配置。
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ MES系统是什么？
批次追踪：运行时的 MES（第 3 集，共 5 集） ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
通过批次追踪实现所有生产部件的信息追踪。
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ MES系统是什么？
驱动工厂运行的数据和指标（第 4 集，共 5 集） ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
MES 系统的关键数据和指标，以及制造商如何使用它们。
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ MES系统是什么？
报表和分析实现持续改进（第 5 集，共 5 集） ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
MES 系统的报表和分析功能，帮助您回答问题和解决问题的工具。
###### [By Dan Meier, Director of MES Product Management](https://appliedsmartfactory.com/author/dan-meier/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
## 封测系列 作者：Joe Napiah
半导体封装测试的全自动化之路
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ 半导体封装测试的全自动化之路——新兴挑战（第1篇，共3篇） ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
了解专家在应对半导体后道制造的新兴挑战和复杂性时最关注的内容。
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ 半导体封装测试的全自动化之路——SmartFactory 路线图（第2篇，共3篇） ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
实现半导体后道制造全自动的路线图。
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
###### [Semiconductor Manufacturing Execution ](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
#### [ 半导体封装测试的全自动化之路——克服障碍（第3篇，共3篇） ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
公司准备工作、数据设备、工厂布局、物料搬运……这些障碍听起来熟悉吗？观看这个视频（第3篇，共3篇），从专家那里获得有关如何实现全自动的建议。
###### [By Joe Napiah](https://appliedsmartfactory.com/author/tim-reblitz/)
[Watch Video](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
## 通用数据模型 作者：Madhav Kidambi
通用数据模型支持快速部署生产效率解决方案
###### [Semiconductor Productivity ](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
#### [ 通用数据模型支持快速部署生产效率解决方案——挑战（第 1 部分，共3部分） ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
快速部署工厂生产效率和供应链解决方案面临的数据挑战
###### [By Madhav Kidambi, Director, Technical Marketing, Automation Products Group](https://appliedsmartfactory.com/author/madhav-kidambi/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
###### [Semiconductor Productivity ](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
#### [ 通用数据模型支持快速部署生产效率解决方案——解决方案（第 2 部分，共3部分） ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
通用数据框架支持快速部署工厂生产效率和供应链解决方案
###### [By Madhav Kidambi, Director, Technical Marketing, Automation Products Group](https://appliedsmartfactory.com/author/madhav-kidambi/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
###### [Semiconductor Productivity ](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
#### [ 通用数据模型支持快速部署生产效率解决方案 – 派工与报告（第 3 部分，共 3 部分） ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
[  ](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
借助 SmartFactory Dispatching解决方案，可在 6 个月内将生产周期缩短 10% 。
###### [By Madhav Kidambi, Director, Technical Marketing, Automation Products Group](https://appliedsmartfactory.com/author/madhav-kidambi/)
[Read More](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
[mv_grow_share url="https://appliedsmartfactory.com/series/"]
---
### [AutoMod 经销商](https://appliedsmartfactory.com/worldwide-automod-distributors/)
**Published:** September 20, 2022
**Author:** Applied Smartfactory
**Content:**
AutoMod 经销商
# 全球经销商联系方式
## 全球 AutoMod 经销商
并非所有的仿真建模工具都是一样的。 30年来，全球顶级物料搬运供应商和系统集成商一直依靠 SmartFactory Simulation AutoMod 来处理复杂的制造和搬运系统的建模、分析和仿真，以获得在其模型中能反映实际情况之所需高度细节及高质量水平。 准备好寻找您附近的销售、集成或服务的分销商吗？ 按地区查找我们的全球经销商。
亚洲
北美
欧洲
南美洲
澳大利亚和新西兰
亚洲
### 亚洲
中国
#### 曲立新
#### 北京亿特克科技有限公司
黄坪路19号龙旗广场E
座1001室中国北京市昌平区
邮编： 100096
[ qulx@etech.com.cn](mailto:qulx@etech.com.cn)
[ 86-10-88878250](tel:861088878250), [86-18601153747](tel:8618601153747%20)
[ www.etech.com.cn](http://www.etech.com.cn/)
日本
#### Applied Materials Japan, Inc.
AGS/Manufacturing Automation Services
Yokoso Rainbow Tower,
3-20-20, Kaigan, Minato, Tokyo, 108-8444, Japan
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
支持：[sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-6812-6866](tel:+8168126866)
支持：[+81-52-238-2801](tel:+81522382801)
[ www.brookssoftware.jp](https://www.brookssoftware.jp/)
印度
#### Vikram Ramnath
#### Larvik Engineering Consultants Pvt. Ltd.
705, B Wing, Great Eastern Summit,
Plot 66, Sector 15,
CBD Belapur, Navi Mumbai 400 614
[ info@larvik.co.in](mailto:info@larvik.co.in)
支持：
[ 91-22-2758-1054](tel:912227581054)
[ larvik.co.in](https://larvik.co.in/)
韩国
#### SCA Inc.
\#805,E&C DreamTower-5,197-13
Guro3-Dong,Guro-Gu,Seoul
Korea(ZIP:152-050)
[ admin@scacompany.co.kr](mailto:admin@scacompany.co.kr)
支持：
[ +82-2-3281-5222](tel:82232815222)
[ www.scacompany.co.kr](http://www.scacompany.co.kr/)
马来西亚，越南，泰国，印度尼西亚，菲律宾和新加坡
#### SCA Globals Co.,Ltd.
422 Nguyen Thi Thap, Tan Quy Ward, District 7,
Ho Chi Minh City, Vietnam
支持：[ support@scaglobals.com](mailto:support@scaglobals.com)
[ 8210-4743-5222](tel:821047435222)
[ www.scaglobals.com](https://www.scaglobals.com/)
北美
### 美国
所有地区
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
全球学术销售
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
加拿大
#### Vincent Santiguida
#### MultiCIM
16 Westminster Ave. N suite 306C
Montreal-West, Quebec H4X 1Z1
Canada
[ admin@multicim.com](mailto:admin@multicim.com)
支持：
[ 514-633-6401](tel:5146336401)
[ 514-633-6495](tel:5146336495)
[ www.multicim.com](http://www.multicim.com/)
欧洲
### 欧洲
比利时
#### SIMCORE Belgium
Bastion Tower, Floors 20&21
5 place du Champ de Mars
B-1050 BRUSSELS
[ info@simcore.be](mailto:info@simcore.be)
[ +32 2 550 37 69](tel:+3225503769)
[ +32 2 550 37 70](tel:+3225503770)
丹麦
#### Bent Aksel Jørgensen
Ivan Søndergaard Jensen
SIMCON A/S
Rugaardsvej 5
DK-8680 Ry
Denmark
[ info@simcon.dk](mailto:info@simcon.dk), [ automod@simcon.dk](mailto:automod@simcon.dk), [ simul8@simcon.dk](mailto:simul8@simcon.dk)
支持：, [ simul8support@simcon.dk](mailto:simul8support@simcon.dk)
[ +45-86-89-03-22](tel:+4586890322)
[ +45-86-89-03-99](tel:+4586890399)
支持：[ 45-86-89-03-42](tel:4586890342)
法国和瑞士的法语区
#### SIMCORE France
Parc Monier Immeuble Le Cassiopée
167 route de Lorient
F-35000 RENNES
[ info@simcore.fr](mailto:info@simcore.fr)
支持：[ support@simcore.fr](mailto:support@simcore.fr)
[ +33 2 99 14 88 50](tel:+33299148850)
[ +33 2 99 14 88 51](tel:+33299148851)
[ www.simcore.fr](https://www.simcore.fr/)
德国，荷兰，奥地利和瑞士和的德语区
#### Steffen Hertling
SimPlan AG
Niederlassung München
Manager: Steffen Hertling
Münchener Str. 13
85540 München-Haar
[ steffen.hertling@simplan.de](mailto:steffen.hertling@simplan.de)
支持：
[ +49 89 2189 7032 15](tel:+49892189703215)
[ +49 89 2189 7032 19](tel:+49892189703219)
支持：[+49 89 2189 7032 25](tel:+49892189703225)
意大利和瑞士的意大利语区
#### Andrea Trere
Prolog S.r.l.
Via Mengolina 31
48018 Faenza RA
[ +39 0546 46073](tel:+39054646073)
[ +39 0546 607191](tel:+390546607191)
热线：[+39 348 8706010](tel:+393488706010)
[ www.prolog.it](http://www.prolog.it/), [ www.automod.it](http://www.automod.it/)
西班牙
#### SIMCORE Spain
C/Génova, 7-3°-Izda
E-28004 MADRID
[ info@simcore.es](mailto:info@simcore.es)
[ +34 91 181 97 05](tel:+34911819705)
[ +34 91 102 28 93](tel:+34911022893)
瑞典
#### Pär Ström
ÅF Industry AB
Grafiska vägen 2
Box 1551
SE-401 51 Gothenburg
Sweden
[ par.strom@afconsult.com](mailto:par.strom@afconsult.com)
[ +46-10-505-3408](tel:+46105053408)
[ +46-10-505-3010](tel:+46105053010)
[ www.automod.se](http://www.automod.se/)
土耳其
#### SELCO Consulting
Haldun Çelik
Prof. Hıfzı Özcan Cad. TasarımKent, Blok D, No:4 34750 Ataşehir İSTANBULTurkey
[ info@selco.com.tr](mailto:info@selco.com.tr)
[ +90 216 5725001](tel:+902165725001), [ +90 533 360 0668](tel:+905333600668)
[ www.selco.com.tr](http://www.selco.com.tr)
英国
#### Graham Carter
Autologic Systems Ltd.
60 High Street
Tetsworth
Oxfordshire OX9 7AB
England
支持：[ support@autologic-systems.co.uk](mailto:support@autologic-systems.co.uk)
[ +44 (0) 1844 281380](tel:+4401844281380), [+44 (0) 7710 172577](tel:+4407710172577)
[ +44 (0) 1844 281874](tel:+4401844281874)
[ www.autologic-systems.co.uk](http://www.autologic-systems.co.uk/)
南美洲
### 南美洲
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
澳大利亚和新西兰
### 澳大利亚和新西兰
#### Applied Materials, Inc.
#### AutoMod Support, North America
5225 West Wiley Post Way Suite 275 Salt Lake City, UT 84116 [ automod\_support@amat.com](mailto:automod_support@amat.com)[ 801-736-3300](tel:8017363300)
## 全球 AutoMod 经销商
不是所有仿真软件都能完成您所期待的任务。 30年来，全球顶级物料搬运供应商和系统集成商一直依靠 SmartFactory Simulation AutoMod 来处理复杂的制造和搬运系统的建模、分析和仿真，以获得在其模型中能反映实际情况之所需高度细节及高质量水平。 准备好寻找您附近的销售、集成或服务的分销商吗？ 按地区查找我们的全球经销商。
亚洲
### 亚洲
中国
#### 曲立新
#### 北京亿特克科技有限公司
黄坪路19号龙旗广场E
座1001室中国北京市昌平区
邮编： 100096
[ qulx@etech.com.cn](mailto:qulx@etech.com.cn)
[ 86-10-88878250](tel:861088878250), [8618601153747](tel:8618601153747%20)
[ www.etech.com.cn](http://www.etech.com.cn/)
日本
#### Applied Materials Japan, Inc.
AGS/Manufacturing Automation Services
Yokoso Rainbow Tower,
3-20-20, Kaigan, Minato, Tokyo, 108-8444, Japan
[ mas\_japan\_sales@amat.com](mailto:mas_japan_sales@amat.com)
支持：[sim\_support\_jp@amat.com](mailto:sim_support_jp@amat.com)
[ +81-6812-6866](tel:+8168126866)
支持：[+81-52-238-2801](tel:+81522382801)
[ www.brookssoftware.jp](https://www.brookssoftware.jp/)
印度
#### Vikram Ramnath
#### Larvik Engineering Consultants Pvt. Ltd.
705, B Wing, Great Eastern Summit,
Plot 66, Sector 15,
CBD Belapur, Navi Mumbai 400 614
[ info@larvik.co.in](mailto:info@larvik.co.in)
支持：
[ 91-22-2758-1054](tel:912227581054)
[ larvik.co.in](https://larvik.co.in/)
韩国
#### SCA Inc.
\#805,E&C DreamTower-5,197-13
Guro3-Dong,Guro-Gu,Seoul
Korea(ZIP:152-050)
[ admin@scacompany.co.kr](mailto:admin@scacompany.co.kr)
支持：
[ +82-2-3281-5222](tel:82232815222)
[ www.scacompany.co.kr](http://www.scacompany.co.kr/)
马来西亚，越南，泰国，印度尼西亚，菲律宾和新加坡
#### SCA Globals Co.,Ltd.
422 Nguyen Thi Thap, Tan Quy Ward, District 7,
Ho Chi Minh City, Vietnam
支持：[ support@scaglobals.com](mailto:support@scaglobals.com)
[ 8210-4743-5222](tel:821047435222)
[ www.scaglobals.com](https://www.scaglobals.com/)
北美
### 美国
所有地区
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
全球学术销售
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
加拿大
#### Vincent Santiguida
#### MultiCIM
16 Westminster Ave. N suite 306C
Montreal-West, Quebec H4X 1Z1
Canada
[ admin@multicim.com](mailto:admin@multicim.com)
支持：
[ 514-633-6401](tel:5146336401)
[ 514-633-6495](tel:5146336495)
[ www.multicim.com](http://www.multicim.com/)
欧洲
### 欧洲
比利时
#### SIMCORE Belgium
Bastion Tower, Floors 20&21
5 place du Champ de Mars
B-1050 BRUSSELS
[ info@simcore.be](mailto:info@simcore.be)
[ +32 2 550 37 69](tel:+3225503769)
[ +32 2 550 37 70](tel:+3225503770)
丹麦
#### Bent Aksel Jørgensen
Ivan Søndergaard Jensen
SIMCON A/S
Rugaardsvej 5
DK-8680 Ry
Denmark
[ info@simcon.dk](mailto:info@simcon.dk), [ automod@simcon.dk](mailto:automod@simcon.dk), [ simul8@simcon.dk](mailto:simul8@simcon.dk)
支持：, [ simul8support@simcon.dk](mailto:simul8support@simcon.dk)
[ +45-86-89-03-22](tel:+4586890322)
[ +45-86-89-03-99](tel:+4586890399)
支持：[ 45-86-89-03-42](tel:4586890342)
法国和瑞士的法语区
#### SIMCORE France
Parc Monier Immeuble Le Cassiopée
167 route de Lorient
F-35000 RENNES
[ info@simcore.fr](mailto:info@simcore.fr)
支持：[ support@simcore.fr](mailto:support@simcore.fr)
[ +33 2 99 14 88 50](tel:+33299148850)
[ +33 2 99 14 88 51](tel:+33299148851)
[ www.simcore.fr](https://www.simcore.fr/)
德国，荷兰，奥地利和瑞士和的德语区
#### Steffen Hertling
SimPlan AG
Niederlassung München
Manager: Steffen Hertling
Münchener Str. 13
85540 München-Haar
[ steffen.hertling@simplan.de](mailto:steffen.hertling@simplan.de)
支持：
[ +49 89 2189 7032 15](tel:+49892189703215)
[ +49 89 2189 7032 19](tel:+49892189703219)
支持：[+49 89 2189 7032 25](tel:+49892189703225)
意大利和瑞士的意大利语区
#### Andrea Trere
Prolog S.r.l.
Via Mengolina 31
48018 Faenza RA
[ +39 0546 46073](tel:+39054646073)
[ +39 0546 607191](tel:+390546607191)
热线：[+39 348 8706010](tel:+393488706010)
[ www.prolog.it](http://www.prolog.it/), [ www.automod.it](http://www.automod.it/)
西班牙
#### SIMCORE Spain
C/Génova, 7-3°-Izda
E-28004 MADRID
[ info@simcore.es](mailto:info@simcore.es)
[ +34 91 181 97 05](tel:+34911819705)
[ +34 91 102 28 93](tel:+34911022893)
瑞典
#### Pär Ström
ÅF Industry AB
Grafiska vägen 2
Box 1551
SE-401 51 Gothenburg
Sweden
[ par.strom@afconsult.com](mailto:par.strom@afconsult.com)
[ +46-10-505-3408](tel:+46105053408)
[ +46-10-505-3010](tel:+46105053010)
[ www.automod.se](http://www.automod.se/)
土耳其
#### SELCO Consulting
Haldun Çelik
Prof. Hıfzı Özcan Cad. TasarımKent, Blok D, No:4 34750 Ataşehir İSTANBULTurkey
[ info@selco.com.tr](mailto:info@selco.com.tr)
[ +90 216 5725001](tel:+902165725001), [ +90 533 360 0668](tel:+905333600668)
[ www.selco.com.tr](http://www.selco.com.tr)
英国
#### Graham Carter
Autologic Systems Ltd.
60 High Street
Tetsworth
Oxfordshire OX9 7AB
England
支持：[ support@autologic-systems.co.uk](mailto:support@autologic-systems.co.uk)
[ +44 (0) 1844 281380](tel:+4401844281380), [+44 (0) 7710 172577](tel:+4407710172577)
[ +44 (0) 1844 281874](tel:+4401844281874)
[ www.autologic-systems.co.uk](http://www.autologic-systems.co.uk/)
南美洲
### 南美洲
#### Matthew Hobson-Rohrer
#### Roar Simulation
1338 South Foothill Drive #243
Salt Lake City, Utah 84108
[ automod@roarsimulation.com](mailto:automod@roarsimulation.com)
[ 801-831-5105](tel:8018315105)
澳大利亚和新西兰
### 澳大利亚和新西兰
#### Applied Materials, Inc.
#### AutoMod Support, North America
5225 West Wiley Post Way
Suite 275
Salt Lake City, UT 84116
[ automod\_support@amat.com](mailto:automod_support@amat.com)
[ 801-736-3300](tel:8017363300)
---
### [Symposium China](https://appliedsmartfactory.com/symposium-china/)
**Published:** April 7, 2023
**Author:** Applied Smartfactory
**Content:**
[ 简体中文 ](https://appliedsmartfactory.com/zh-hans/symposium-china/)
[ English (英语) ](#)
## 2023年 SmartFactory 智能工厂解决方案研讨会
**智能制造创新突破**
中国上海 | 2023年6月30日星期五
### 会议集锦
### 研讨会为期一天
### 多场技术分组会议
### 现场演示SmartFactory智能工厂解决方案
### 如有问题，请联系：
[Housman\_Chen@amat.com](mailto:Housman_Chen@amat.com)*应用材料中国*[Jardon\_Xiao@amat.com](mailto:Jardon_Xiao@amat.com)*应用材料中国*[James\_SC\_Chang@amat.com](mailto:James_SC_Chang@amat.com)*应用材料台湾地区*[Sean\_Yong@amat.com](mailto:Sean_Yong@amat.com)*应用材料东南亚*
### 查看时间表：
[ 查看完整议程 ](#)
---
### [支持](https://appliedsmartfactory.com/support/)
**Published:** December 9, 2021
**Author:** Applied Smartfactory
**Content:**
全球支持
# 软件入口
## 重要链接
[ ](https://amat.service-now.com/csm)
#### [ 登录 ](https://amat.service-now.com/csm)
[ ](https://partner.amat.com/identityiq/external/amat/resetPassword/rstPwdBaseForm.jsf)
#### [ 密码重置 ](https://partner.amat.com/identityiq/external/amat/resetPassword/rstPwdBaseForm.jsf)
[ ](https://appliedsmartfactory.com/zh-hans/support-contacts/)
#### [ 按地区查看支持中心联系方式 ](https://appliedsmartfactory.com/zh-hans/support-contacts/)
[ ](mailto:customer_portal@amat.com)
#### [ 登录需要帮助？ 联系我们 ](mailto:customer_portal@amat.com)
#### 购买维保服务的用户登录后可获取：
- 最新的GA版本和补丁
- 产品相关公告
- 软件支持专家的途径
#### 登录后，用户可以：
- 查看当前案例的状态
- 记录新案例
- 访问应用材料BOX云盘获取FTP选项
- 检查知识库材料
---
### [RTD](https://appliedsmartfactory.com/supply-chain-solutions/rtd/)
**Published:** November 9, 2021
**Author:** Applied Smartfactory
**Content:**
SmartFactory RTD
# 释放隐藏的产能
## 您的工厂如何达成按时交货的承诺？
SmartFactory RTD是一个实时的派工及报表解决方案，提供决策能力，以提高整个工厂的生产效率。 该解决方案使制造商能够制定派工策略，以满足客户交货时间，同时最大限度地提高瓶颈设备的生产能力。
## 为什么选择SmartFactory RTD？
### 每年增长300万-1200万美元的盈利
### 设备利用率提高10%
### 操作员一致性支持率高达99%
## 您能从我们的解决方案中获得什么？
## 智能决策
- 使用同样的设备和人员生产更多的产品——使制定的决策具备预测性和一致性
- 根据工厂的实时状态选择最优批次进行加工
## 基于规则的派工
- 通过增强改善瓶颈区域的生产流程来确保实现工厂目标
- 使用易用的、基于图标的规则开发环境部署派工规则
## 数据集成和存储
- 集成生产系统、物料控制系统和质量控制系统
- 从多个数据源收集数据，使用提取技术对相关数据进行复制，并将这些数据存储到一个高速、瞬时数据库
---
### [Posts](https://appliedsmartfactory.com/posts/)
**Published:** January 21, 2022
**Author:** Applied Smartfactory
---
## Semiconductor Blog
### [How a leading memory manufacturer transformed dry etch process control](https://appliedsmartfactory.com/semiconductor-blog/quality/transform-dry-etch-process-control/)
**Published:** August 25, 2026
**Author:** Hungyu Chen, Global Product Manager – Applied E3® Run-to-Run
**Excerpt:** Reducing false alarms and optimizing UVA specifications through data-driven intelligence
**Content:**
## What’s Inside
- [ The challenge: moving beyond experience-based spec settings ](#index1)
- [ The solution: SmartFactory AI™ Predictive Metrology with Safe Zone Simulator ](#index2)
- [ Advanced capabilities: process simulation and explainability ](#index3)
- [ Results: exceptional model performance ](#index4)
- [ The bigger picture: toward unified process control ](#index5)
- [ Predictive Metrology: an early proof point ](#index6)
- [ Key takeaways ](#index7)
- [ Looking ahead ](#index8)
## The challenge: moving beyond experience-based spec settings
For semiconductor manufacturers, maintaining tight process control while minimizing production disruptions is a constant balancing act. A leading memory IC manufacturer faced a common yet critical challenge in their dry etch operations: their univariate analysis (UVA) specifications were set based on expert experience and legacy configurations.
This approach led to significant operational pain points:
- Excessive false alarms: UVA specs frequently triggered alerts that didn’t correspond to actual quality issues, overwhelming module engineers with unnecessary alarm handling workload.
- Missed quality issues: Despite the abundance of alarms, real yield issues sometimes went undetected because UVA specifications couldn’t capture the actual process-to-quality relationships.
- Inefficient resource allocation: Engineers spent valuable time investigating false positives instead of focusing on genuine process improvements.
The customer needed a smarter approach—one that could leverage their wealth of historical data to establish scientifically-grounded process limits.
## The solution: SmartFactory AI™ Predictive Metrology with Safe Zone Simulator
Applied Materials Automation Products Group partnered with the customer to deploy the Safe Zone Simulator, a powerful feature within the SmartFactory AI Predictive Metrology solution. The approach centered on three core capabilities:
### **1. Data-driven model building**
The team collected comprehensive process data from the customer’s dry etch tools, including:
- UVA and trace data from the etch process.
- Lot quality control metrology measurements (depth/CD at 13 sites per wafer).
- Both production wafers and experimental lots from preventive maintenance (PM) periods.
A key insight emerged during the project: initial models built only on steady-state production wafers showed limited variation. By incorporating experimental wafers from the unstable post-PM period where module engineers actively tuned process parameters, the models could capture a much wider range of UVA-to-LQC relationships.
### **2. Intelligent Feature Ranking**
Using Partial Least Squares regression, the solution identified the most critical UVA parameters affecting metrology outcomes. The analysis revealed that a small set of equipment- and process-related parameters dominated the top key features, giving the team a clear, ranked shortlist of what to monitor.
This finding provided actionable intelligence for the dry etch engineering team, confirming which process parameters required the most careful monitoring and control.
### **3. Safe Zone Simulator**
The breakthrough capability: Given desired metrology control limits (Y specifications), the system could reverse-engineer optimal UVA specifications (X limits) that would keep the process within spec (see Figure 1).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/08/Figure-1-Mapping-safe-operating-zones—accurate-detection-minimal-false-alarms.webp) Figure 1: Mapping safe operating zones—accurate detection, minimal false alarms.
The system provides intuitive visualizations showing safe operating zones. This enables engineers to understand the complex interactions between multiple process parameters and their impact on metrology outcomes.
## Advanced capabilities: process simulation and explainability
Beyond spec recommendation, the solution delivered powerful simulation and diagnostic tools, including:
**Process simulator:** Engineers can now explore “what-if” scenarios by adjusting key feature values and instantly seeing predicted metrology outcomes. For example, adjusting a wafer’s top-ranked feature shows the predicted LQC shift in real-time—enabling proactive process optimization before running actual wafers.
**SHAP-based explainability:** Using Shapley Additive Explanations (SHAP), the system provides transparent explanations for model predictions. When engineers noticed two wafers with identical primary parameter values producing different metrology predictions, the SHAP analysis immediately identified differences in secondary parameters as the root cause.
This explainability builds trust in the AI recommendations and helps engineers deepen their process understanding.
## Results: exceptional model performance
The Virtual Metrology model achieved outstanding accuracy, validated by the customer’s process engineers as “very good”:
- 0.2% MAPE
- 901 wafers analyzed
- 6-month data period
This level of prediction accuracy enables confident decision-making for spec optimization, allowing engineers to trust the AI-recommended safe zones.
## The bigger picture: toward unified process control
For decades, the pillars of advanced process control have operated as separate systems: Fault Detection and Classification (FDC), Run-to-Run and Advanced Process Controls (R2R and APC), and Statistical Process Control (SPC). Each is powerful, but works largely in its own silo.
Applied Materials’ vision is to change that. Rather than adding yet another standalone tool, we are building a new generation of AI solutions on top of the FDC, R2R/APC, and SPC systems that fabs already rely on. These solutions draw on data from across all three domains and feed intelligence back into each—augmenting the existing investment rather than replacing it. The result is process control that behaves as one connected, continuously learning system instead of a set of disconnected point tools.
## Predictive Metrology: an early proof point
The Safe Zone Simulator story above is a clear example of the vision in action. The solution learned from fault-detection-domain data (UVA and trace signals), related it to downstream metrology outcomes, and produced data-driven control limits of the kind traditionally managed in SPC—all to protect yield in a way no single system could achieve on its own. It did not replace the fab’s existing FDC or SPC; it connected and elevated them with an AI layer on top.
That is the pattern we intend to repeat across the portfolio: AI that unifies fault detection, run-to-run control, and statistical process control into a single, continuously improving loop—turning years of siloed process-control data into predictive, actionable intelligence.
## Key takeaways
This collaboration demonstrates the power of data-driven process control:
1. **From experience to evidence:** UVA specifications can be scientifically determined rather than empirically guessed
2. **Multi-dimensional optimization:** Considering parameter interactions (2D+ analysis) significantly improves alarm effectiveness
3. **Continuous improvement:** The system requires periodic retraining with new data to maintain prediction accuracy—a sustainable approach to ever-improving process control
4. **Actionable intelligence:** Beyond recommendations, the solution provides simulation and explainability tools that empower engineers to understand and trust the AI
5. **Unified, not siloed:** The biggest gains come when AI draws on FDC, R2R/APC, and SPC together, augmenting every system rather than adding another standalone tool
## Looking ahead
As semiconductor manufacturing complexity continues to grow, AI-driven solutions like the Safe Zone Simulator represent the future of Advanced Process Control. By transforming historical data into predictive intelligence, fabs can achieve the dual goals of tighter quality control and reduced operational burden.
For this customer’s dry etch operations, the proof-of-concept has laid the groundwork for a new paradigm in process control excellence.
*This success story is based on a Proof-of-Concept project conducted by Applied Materials’ Automation Products Group in partnership with a leading memory semiconductor manufacturer.*
## FAQs
How can we reduce false alarms without missing real process problems?
AI-driven predictive metrology can help by using historical process and metrology data to set more accurate control limits. Instead of relying only on experience-based thresholds, the model identifies which process signals are most tied to quality outcomes, helping engineers reduce unnecessary alarms while still detecting conditions that could affect yield.
Can AI help us set better UVA specifications for dry etch tools?
Yes. By learning the relationship between equipment signals, process parameters, and downstream metrology results, an AI model can recommend UVA limits that are better aligned with actual quality requirements. This gives process teams a data-supported way to refine specifications and avoid overly broad or overly sensitive limits.
What is a “safe zone” in semiconductor process control?
A safe zone is the operating range where key process parameters are expected to keep wafer metrology results within target limits. With a simulator, engineers can visualize how one or more parameters interact, test different operating conditions, and identify the process window most likely to protect quality before wafers move further through production.
How do we know whether we can trust the AI model’s recommendations?
Trust comes from both model performance and explainability. Predictive accuracy shows whether the model can reliably estimate metrology outcomes, while explainability tools help engineers see which parameters influenced a prediction. This makes AI recommendations easier to validate, interpret, and use in day-to-day process decisions.
Can predictive metrology work with the process control systems we already use?
Predictive metrology is designed to complement existing FDC, APC/R2R, and SPC systems. It can use data from these systems to generate earlier quality predictions, improve control-limit decisions, and support a more connected approach to process control without requiring fabs to replace their established infrastructure.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [From data to decisions](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/from-data-to-decisions-ai-enabled-digital-twins-transform-semiconductor-manufacturing/)
**Published:** June 29, 2026
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** How AI-enabled digital twins are transforming semiconductor manufacturing
**Content:**
## What’s Inside
- [ Why data-rich factories make slow decisions ](#index1)
- [ A digital twin changes the question ](#index2)
- [ Closing the gap between observation and action ](#index3)
- [ Better timing is the real competitive advantage ](#index4)
- [ Building the foundation for AI-driven decisions ](#index5)
- [ Decision speed drives business value ](#index6)
- [ Where the industry stands today and what’s next ](#index7)
When people hear “digital twin,” they picture a virtual replica of a physical product—a jet engine or another complex piece of industrial equipment. While that definition is valid, it reflects only one perspective and overlooks a very different way to think about digital twins.
The real transformation is not just about modeling products. It is about modeling the factories that produce them and using that model to enable better, faster decisions that improve yield, cycle time, and overall factory performance.
That distinction matters in semiconductor manufacturing. A modern fab is an interconnected system, not just a set of isolated tools and recipes. Thousands of lots move across hundreds of process flows, interacting with hundreds of tools, and continuously generate large volumes of data. A maintenance event, process deviation, or scheduling change in one area can ripple through the factory, affecting output, cycle time, and delivery performance.
And yet, most fabs still manage that complexity reactively. Teams gather data from multiple systems, meet to compare findings, and work through the implications together. That process is necessary, but it is also slow. By the time the team has assembled, the problem is already growing. And by the time the issue is understood, yield or cycle time impacts are already spreading.
That is why digital twins are drawing so much attention. There is an opportunity to move toward a system-level representation of the fab that helps teams spot interactions earlier, evaluate trade-offs faster, and act before variability turns into missed targets.
### Why do data-rich factories make slow decisions?
Semiconductor fabs generate plenty of data, but that doesn’t always translate into clarity. Process, equipment, production, and planning teams each rely on their own dashboards and monitoring tools. The lack of shared content across factory domains slows decision making. And while dashboards are important, they rarely explain why something is happening across the broader factory.
This is where a digital twin becomes valuable; an integrated view of data from across the factory helps teams make faster, more confident decisions that protect yield, stabilize cycle time, and keep local issues from becoming factory-level problems.
### A digital twin changes the question
At its core, a digital twin shifts the conversation from fragmented visibility to system-level understanding. Instead of navigating disconnected dashboards and siloed metrics, teams work from a unified view of the factory and explore data in context.
That changes the questions teams can ask. Instead of asking why one dashboard turned red, they can ask what changed across the system, what is likely to happen next, and which action is most likely to improve the outcome.
As these capabilities mature, that unified view should make it easier to connect factory-level conditions to the process, equipment, or scheduling events behind them. Generative AI adds another layer by letting users ask specific questions across complex, multi-source factory data. That does not replace engineering judgment, but it can accelerate insight when timing and context determine whether an issue remains manageable or turns into a KPI problem.
### Closing the gap between observation and action
The next step in this evolution is moving from observation to prediction, recommendation, and action.
Many factories are good at explaining what happened yesterday. The larger opportunity is to see where performance is heading while there is still time to influence it. An AI-enabled digital twin becomes key here because it can improve both the quality and the timing of decisions.
Consider a common fab scenario: a critical tool or subsystem is nearing a lengthy maintenance event. Today, managing that event often requires several teams to coordinate capacity, scheduling, and downstream risk. The decision affects line balance, hot lots, delivery commitments, and utilization of other tools.
In a more mature digital twin environment, that same event could be handled more effectively. Maintenance actions could update capacity models. Simulations could evaluate trade-offs and recommend response options. Risks to cycle time, output, or delivery could be raised earlier, before the impact spreads through the fab. The benefit is clear: enabling faster actions leads to better manufacturing outcomes.
### Better timing is the real competitive advantage
The value of faster decisions comes down to timing. A proactive corrective action can have a very different economic impact than the same action taken after WIP has built up or ship dates have slipped.
If digital twins evolve as many manufacturers expect, operations could shift from meeting-driven coordination to a more continuous, data-guided response. People still make the decisions, but with earlier warning, better context, and a clearer sense of which actions are most likely to protect factory performance.
Parts of that vision already exist in targeted use cases. AI is being applied to scheduling, process control, fault detection, and predictive maintenance. Simulation tools already help manufacturers evaluate selected future-state scenarios. The broader vision is connecting those capabilities into a more coordinated decision-support layer for the entire factory.
### Building the foundation for AI-driven decisions
Delivering that vision requires real-time data integration across traditional manufacturing software systems, AI models that can interpret the data, and simulation capabilities that can test what-if scenarios quickly enough to support operations.
In practice, that means bringing together data from MES, material control, production scheduling, equipment automation, process control, and other factory domains into one unified environment. It also means solving basic problems of data quality, timing, and context so models can support real decisions.
Many of the technical building blocks are emerging, but making them work together in a way that improves factory-level performance is a work in progress.
### Decision speed drives business value
The business implications are substantial:
- Earlier identification of process issues could help reduce scrap.
- Better coordination around maintenance and capacity could improve utilization.
- More system-level understanding could support lower cycle time, better delivery performance, and improved cost per wafer.
Even small improvements in those metrics can have a meaningful financial impact in high-volume manufacturing. Manufacturers that make better, faster decisions are more equipped to respond to variability, recover from disruption, and operate with greater resilience under pressure.
### Where the industry stands today and what’s next
It is important to be clear about where the industry stands today. Fully integrated, AI-enabled digital twins that coordinate real-time data, predictive models, and system-wide recommendations across the factory are still emerging. Today’s reality is closer to a set of advancing capabilities than a finished end state.
That does not weaken the direction of travel. It makes the challenge clearer. The industry is moving from isolated optimization toward broader, connected decision support. Manufacturers that connect these pieces effectively will be better positioned to improve outcomes as manufacturing and business complexity continue to rise.
The future of semiconductor manufacturing won’t be defined simply by more data and more dashboards. It will be defined by how effectively manufacturers can turn data into insight and insight into timely action. That is the promise of AI-enabled digital twins: better timing, better decisions, and better factory performance.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [The power problem](https://appliedsmartfactory.com/semiconductor-blog/scheduling/the-power-problem-semiconductor-energy-management/)
**Published:** July 28, 2026
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** Why energy management is the next frontier for fab competitiveness
**Content:**
## What’s Inside
- [ The scale of the challenge ](#index1)
- [ Regulatory reckoning ](#index2)
- [ Customer pressure: Scope 3 comes home ](#index3)
- [ The three pillars of fab energy management ](#index4)
- [ Use case: smart sleep for equipment and sub-fab systems ](#index5)
- [ Use case: energy-aware scheduling ](#index6)
- [ Use case: simulation for energy analysis ](#index7)
- [ The integration imperative ](#index8)
- [ The investment case ](#index9)
- [ What are leading fabs doing? ](#index10)
- [ The path forward ](#index11)
- [ Energy as competitive advantage ](#index12)
Semiconductor manufacturing has always been energy intensive. Advanced fabs consume 100–200 megawatts continuously, making energy one of the largest operational inputs. But what was once a manageable cost is now a strategic constraint.
Energy prices are rising, regulatory requirements are tightening, and customers are demanding carbon transparency across the supply chain (see Figure 1). Meanwhile, the push to advanced nodes and higher volumes is increasing energy demand faster than efficiency gains can offset. Energy has moved from an operational cost to a core competitive factor. Fabs that address this challenge can strengthen margins, reduce regulatory risk, and improve customer alignment. Those that do not will face increasing exposure to cost pressure, compliance disruption, and customer attrition.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-1-2.jpg) Figure 1: The converging pressures on fab energy management: rising consumption, increasing costs, tightening regulations, and customer demands for supply chain transparency.
### The scale of the challenge
The magnitude of semiconductor energy consumption is significant and growing rapidly, as shown in Figure 2. Leading manufacturers consume tens of terawatt hours annually, and advanced nodes continue to drive higher energy intensity per wafer. Technologies such as EUV lithography add substantial, continuous power requirements at the tool level.
Across the industry, energy demand is expected to increase through the remainder of the decade, driven by capacity expansion and accelerating demand for AI and high-performance computing. This growth has direct financial implications because energy now represents a meaningful and rising portion of fab operating expenses. At the same time, power availability itself is becoming a constraint. Key regions such as Taiwan, Arizona, and Texas are experiencing grid pressure as fabs compete with data centers, electric vehicle production, and residential demand. Renewable energy adoption is critical, but it is not sufficient on its own to address these structural limitations.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-2.jpg) Figure 2: Illustrative growth trend for semiconductor industry energy consumption, driven by advanced node expansion and increasing chip demand. Actual figures vary by region and source.
### Regulatory reckoning
Regulatory requirements are also quickly evolving. Manufacturers increasingly must disclose energy and emissions data, report Scope 1, 2, and increasingly Scope 3 emissions, and meet efficiency requirements tied to incentives, financing, and reporting frameworks (see Figure 3).
The trajectory is clear: transparency today, efficiency mandates in the near term, and broader carbon pricing over time. Having energy management capabilities in place will help fabs avoid future compliance costs and operational disruption.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-3.jpg) Figure 3: Global regulatory requirements for fab energy and emissions—EU CSRD, US SEC climate rules, and emerging frameworks in Asia create a compliance imperative.
### Customer pressure: Scope 3 comes home
Regulation establishes the baseline, but customer expectations raise the bar. The ability to demonstrate low-carbon manufacturing is becoming a prerequisite for winning and retaining business. Major technology companies have committed to aggressive net-zero timelines across their supply chains, and semiconductor manufacturers are increasingly required to provide energy and carbon data at the product and lot level.
### The three pillars of fab energy management
Addressing energy consumption in semiconductor manufacturing requires a multi-layered approach built on three foundational pillars: equipment efficiency, operational optimization, and systemic intelligence (see Figure 4).
Equipment efficiency focuses on hardware-level improvements such as better components, integrated peripheral devices, and heat recovery systems. Operational optimization extracts more performance from existing assets through intelligent scheduling and predictive maintenance, and systemic intelligence integrates production systems, sub-fab infrastructure, and real-time energy data into a coordinated framework for real-time optimization.
While all three pillars are important, long-term advantages will come from systemic intelligence. Energy must be treated as a managed resource across the entire manufacturing system—not just at the tool level.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-4.jpg) Figure 4: The three pillars of fab energy management—equipment efficiency, operational optimization, and systemic intelligence. Each builds on the previous.
### Use case: smart sleep for equipment and sub-fab systems
The simplest energy-saving intervention is turning things off when they are not needed. But in a fab, “off” is complicated. Equipment cannot instantly switch from idle to production-ready and wake-up times range from seconds to more than 30 minutes, depending on the system. Additionally, sub-fab equipment—pumps, abatement systems, cooling—must coordinate with process tools. Turning something off at the wrong time risks yield excursions or safety events.
Smart sleep systems address this challenge by predicting idle time and transitioning equipment into lower-energy states when conditions allow. By integrating with MES data, they can anticipate production needs and ensure tools return to readiness in time to meet demand. Sleep modes can include pump speed reduction, N2 flow reduction, heater temperature setback, and other energy-saving configurations.
The energy savings are meaningful. Sub-fab equipment alone can represent 30–40% of fab energy consumption. Transitioning from always-on operation to intelligent sleep modes can reduce sub-fab energy by 15–25% without impacting production availability (see Figure 5).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-5.jpg) Figure 5: Smart Sleep integrates MES data with equipment control to predict idle duration and coordinate transitions between idle, sleep, and production-ready states.
### Use case: energy-aware scheduling
Traditional scheduling systems optimize for productivity metrics such as cycle time and throughput. Energy consumption is typically treated as a fixed cost rather than a variable that can be optimized.
Energy-aware scheduling introduces energy as a secondary objective without compromising primary goals. By incorporating consumption profiles, equipment efficiency, and time-of-use pricing, scheduling decisions can reduce energy costs while maintaining performance targets. Implementation requires granular energy modeling, rate-structure integration, and multi-objective optimization that balances productivity and energy objectives.
Even modest adjustments such as shifting high-energy processes to off-peak periods or selecting more efficient equipment can yield meaningful savings. Early implementations show potential for a 10–20% reduction in energy costs without measurable productivity impact, as shown in Figure 6. As a software solution, energy-aware scheduling does not require equipment modifications or capital investment; it extracts value from existing infrastructure through smarter decisions.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-6.jpg) Figure 6: Energy-aware scheduling shifts high-consumption recipes to low-cost periods while maintaining productivity KPIs. Potential savings: 10-20% of energy costs.
### Use case: simulation for energy analysis
You cannot optimize what you cannot measure. In many fabs, energy data is still aggregated at a high level, limiting the ability to understand and optimize consumption at a granular level.
As depicted in Figure 7, below, energy simulation extends existing fab models to include detailed energy profiles across process equipment, sub-fab systems, and facility infrastructure. Energy outputs can be viewed alongside productivity metrics and carbon footprint estimates based on grid emission factors.
The real value lies in predictive analysis. Simulation enables teams to evaluate the energy impact of changes in product mix, capacity, scheduling strategies, or equipment configuration before implementing them. It also supports compliance reporting by providing the data needed for emissions tracking and customer disclosures. This capability transforms energy from an unpredictable externality into a manageable variable for Operations, Finance, and Sustainability teams.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-7.jpg) Figure 7: Energy simulation provides visibility into consumption by area, equipment, product, and lot—enabling what-if analysis and compliance reporting.
### The integration imperative
While each approach delivers value independently, the greatest impact comes from integration like that seen in Figure 8. Coordinating scheduling with smart sleep strategies can create longer idle windows and unlock deeper savings. Integrating energy data with maintenance systems can identify inefficiencies before failure, while real-time pricing data can inform dispatching without disrupting production.
These cross-domain optimizations require connected systems and shared data models. As complexity increases, AI-enabled decision-making becomes critical. Intelligent systems can continuously evaluate trade-offs between productivity and energy objectives in ways that isolated tools or manual processes cannot.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-8.jpg) Figure 8: Integrated energy management connects scheduling, dispatch, equipment control, and sub-fab systems into a coordinated system that optimizes across domains.
### The investment case
Energy management investments compete with other capital priorities, so the case must be made in financial terms. The business value extends beyond direct savings: lower operating costs, avoided demand charges, stronger regulatory readiness, better customer alignment, and reduced exposure to energy-price volatility and grid constraints.
As supply-chain decarbonization accelerates, customer retention and acquisition may become the strategic prize. Fabs that can demonstrate low-carbon manufacturing will be better positioned to win preferred supplier status, and that value can exceed direct energy savings. The investment case varies by fab, region, and market position, but the trajectory is consistent: energy management capabilities are becoming more valuable over time, not less.
### What are leading fabs doing?
Leading semiconductor manufacturers are already prioritizing energy management as a core capability (see Figure 9). Investments are focused on granular monitoring, integration of energy data into production systems, optimization pilots, and renewable energy sourcing. Public net-zero commitments show that energy management is becoming part of the operating model for advanced fabs, not only a sustainability initiative. Early adopters are building capabilities that compound over time.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/image-9.jpg) Figure 9: Major semiconductor manufacturers have committed to aggressive net-zero timelines—TSMC and Samsung by 2050, Intel by 2040—driving industry-wide transformation.
### The path forward
Energy management maturity typically evolves through four stages: visibility, efficiency, optimization, and intelligence. Most fabs today are still building foundational visibility and implementing targeted efficiency improvements. Forward-looking organizations are moving toward integrated optimization and AI-driven systems.
This progression is not optional. Market dynamics, regulatory pressure, and customer expectations will continue to push the industry forward. The only question is how quickly each organization adapts.
### Energy as competitive advantage
The semiconductor industry’s relationship with energy is changing. What was once a background cost is now a strategic variable.
Fabs that invest in energy management will benefit from lower costs, stronger customer alignment, improved compliance, and greater operational resilience. Those that do not will face increasing constraints and competitive disadvantage. Energy management is not a distraction from fab competitiveness; it is fab competitiveness.
Applied Materials APG is developing comprehensive energy management solutions for semiconductor manufacturing—from smart sleep systems to energy-aware scheduling, to simulation-based analysis. [Learn how](/) we’re helping fabs reduce energy consumption while maintaining productivity.
## FAQs
#### How can a semiconductor fab cut energy costs without buying new equipment?
Many fabs can reduce energy costs by optimizing how existing equipment is used rather than immediately investing in new hardware. Approaches such as intelligent scheduling, automated idle-state management, and energy-aware production planning help reduce unnecessary power consumption while maintaining throughput, cycle time, and production commitments. In many cases, the fastest savings come from making better operational decisions with the assets already in place.
#### Why are customers asking semiconductor suppliers for energy and carbon data?
Many electronics manufacturers have public sustainability goals that extend beyond their own operations and into their supply chains. As a result, semiconductor suppliers are increasingly being asked to provide evidence of how products are manufactured, including energy usage and carbon impact. Fabs that can provide accurate, traceable data are often better positioned to meet customer requirements, support procurement decisions, and strengthen long-term supplier relationships.
#### What is the biggest obstacle to improving energy efficiency in a fab?
For many manufacturers, the biggest challenge is visibility. Energy consumption often exists in separate systems and is difficult to connect to specific products, tools, processes, or production decisions. Without detailed insight into where and when energy is being consumed, it becomes difficult to identify savings opportunities, evaluate tradeoffs, or measure the impact of improvement initiatives. Organizations typically achieve better results when energy information is integrated with production and operational data.
#### Can energy reduction initiatives hurt fab productivity or yield?
Not when they are designed correctly. Modern energy-management strategies focus on balancing manufacturing performance and energy objectives rather than sacrificing one for the other. By using production-aware controls, predictive analytics, and integrated decision-making, fabs can reduce unnecessary energy consumption while continuing to meet production targets, maintain equipment readiness, and protect yield. The goal is optimization, not restriction.
#### How should a fab start building an energy-management strategy?
A practical starting point is establishing a baseline of energy consumption and understanding where the largest opportunities exist. From there, fabs can prioritize improvements that deliver measurable business value, such as increased visibility, operational optimization, and cross-functional coordination between manufacturing, facilities, and sustainability teams. Organizations that treat energy as a business metric—rather than only a utility expense—are better positioned to improve resilience, manage risk, and support future growth.
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [End-to-End Quality Intelligence in Manufacturing](https://appliedsmartfactory.com/semiconductor-blog/quality/end-to-end-quality-intelligence-in-manufacturing/)
**Published:** July 27, 2026
**Author:** Yoram Barak, Global Product Manager
**Excerpt:** The next frontier is connected, contextualized intelligence from supplier to customer
**Content:**
## What’s Inside
- [ End-to-End Quality requires more than better inspection ](#index1)
- [ Quality starts before the fab ](#index2)
- [ The missing link: Integration and contextualization ](#index3)
- [ Why late detection is built into the process ](#index4)
- [ From reactive guardrails to learning systems ](#index5)
- [ AI needs better inputs, not just better algorithms ](#index6)
- [ Full automation raises the stakes ](#index7)
- [ The path forward: detection, prediction, prevention ](#index8)
- [ Conclusion ](#index9)
### End-to-End Quality requires more than better inspection
In semiconductor manufacturing, quality issues rarely begin where they are detected. A nonconformance may surface during metrology, inspection, yield analysis, or even after a customer return—but its root cause can originate much earlier: in product design, supplier manufacturing, inbound logistics, storage conditions, material handling, equipment configuration, or the way consumables and durables are introduced into production.
That is why end-to-end quality is becoming one of the most important conversations in advanced manufacturing. The industry has made enormous progress in equipment health monitoring, SPC, metrology, chamber matching, tool matching, and process control. Yet, many manufacturers still lack a fully connected view of quality from supplier to finished product. The result is a persistent gap between incoming quality, manufacturing quality, and outbound customer quality
(See Figure 1).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/figure-1.webp) Figure 1: Sources of non-conformance
### Quality starts before the fab
Manufacturing quality does not begin at the first process step. It starts with the specifications used to design and purchase materials, parts, chemicals, consumables, durables, and subassemblies. It continues through supplier manufacturing, certificates of conformance, freight conditions, receiving, sampling, storage, and ultimately the movement of materials into production.
Each point in that chain can introduce risk. Materials may meet its specifications at the supplier but be compromised during transit. A chemical may arrive with documentation but experience temperature excursions before use. A consumable may pass incoming quality sampling yet age out or degrade in storage. A gas bottle may feed multiple tools, making the source of a downstream issue difficult to isolate. By the time a defect is detected, the affected lots may already have moved far beyond the original point of failure.
### The missing link: Integration and contextualization
Most fabs have strong quality systems—but those systems were often designed around specific functions. Incoming quality teams work with suppliers and certificates of conformance (CoC). Manufacturing teams focus on equipment, processes, lot movement, and yield. Outbound quality teams manage customer returns, 8D investigations, and field issues. Each organization may have effective tools, but the data is often fragmented across systems and business processes.
The challenge, as shown in Figure 2, is not simply connecting systems through an interface. The real challenge is preserving context: what material was purchased, who supplied it, how it was manufactured, how it was transported, where it was stored, when it was moved into production, which tools it touched, which lots were exposed, and what quality outcomes followed. Without that context, quality teams may know that a problem occurred but lack the visibility needed to understand why.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/figure-2.jpg) Figure 2: Integration and contextualization
### Why late detection is built into the process
In high-volume semiconductor manufacturing, not every lot is inspected at every step. Sampling strategies are necessary for throughput, but they also mean that issues can propagate before detection. When a problem is finally identified at a metrology or inspection step, that location is often only the point of detection—not the point of origin. Root cause analysis then becomes a race against complexity. Which lots were exposed? Which tools processed them? Was the issue tied to a recipe, a chamber, a consumable, a supplier lot, a storage condition, or an upstream process step? Asking the “five whys” across one system is difficult enough. Asking them across supplier quality, manufacturing execution, equipment data, metrology, inspection, and customer quality systems is far more challenging.
### From reactive guardrails to learning systems
Traditional quality systems are often interrupt-driven. If a value exceeds a limit, a rule triggers. If a trend violates a control rule, the process stops. These guardrails are essential, but they primarily focus on what went wrong. They do not always capture what went right—or explain why certain combinations of supplier, material, equipment, process, and handling conditions consistently produce better outcomes.
This is where AI and agentic systems can change the quality paradigm. When granular, contextualized data is available, AI can help manufacturers move from reactive detection toward prediction, prevention, and continuous learning (see Figure 3). It can help identify hidden commonalities across lots, tools, materials, suppliers, and process windows. It can also help preserve institutional knowledge and uncover patterns that experienced engineers may not have had the full data context to see.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/figure-3.jpg) Figure 3: Driving performance through connected insights
### AI needs better inputs, not just better algorithms
AI can only be as effective as the information it can access. If supplier, material, and handling data are excluded from the quality model, the system has blind spots. If data is too coarse, disconnected, or missing context, AI may produce incomplete or misleading conclusions. Reliable AI for end-to-end quality, therefore, depends on three foundational capabilities: granular traceability, integrated data flows, and contextualized relationships across business and manufacturing systems.
For example, detecting that three tools experienced related quality excursions may not be enough. The key question is whether those tools shared a common consumable, gas source, supplier lot, maintenance event, or environmental exposure. Without contextualization, each excursion may look isolated. With contextualization, the common root cause becomes discoverable.
### Full automation raises the stakes
It is tempting to assume that fully automated fabs are less exposed to nonconformance risk than semi-automated or manual environments. In reality, automation can amplify both good and bad outcomes. If an error is introduced into a process flow, recipe, material handling step, or configuration, automation can repeat that error rapidly and consistently across many lots before detection.
This makes end-to-end quality even more critical in highly automated environments (see Figure 4). The faster a fab moves, the more important it becomes to identify abnormal patterns early, trace affected material quickly and understand common causes before quality issues scale into yield loss or customer impact.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/07/figure-4.jpg) Figure 4: End-to-End systems vision scenario
### The path forward: detection, prediction, prevention
The evolution of AI-enabled quality will likely follow a crawl-walk-run path. The first step is detection: helping engineers ask better “why” questions of their data and accelerate investigations. The next step is prediction: identifying risks earlier, such as lot yield, defect trends, cycle time, or shipment risk. The longer-term opportunity is prevention: creating agentic systems that monitor, reason, recommend, and eventually orchestrate actions across supplier, fab, equipment, process, and quality systems.
That future will not be built by AI alone. It will require manufacturing systems that expose the right data, business processes that capture the right events, and quality frameworks that connect the full product lifecycle from supplier to customer. AI becomes powerful when it is grounded in accurate, granular, and contextualized manufacturing truth.
### Conclusion
End-to-end quality is not just a supplier quality problem, a manufacturing problem, or a customer quality problem. It is a systems problem. The next generation of quality performance will come from connecting the dots across the entire lifecycle: design, sourcing, supplier manufacturing, logistics, receiving, storage, production, test, yield, and field performance.
Manufacturers that invest in integration, contextualization, and AI-ready traceability will be better positioned to detect issues earlier, reduce excursion scope, accelerate root cause analysis, improve yield, and build learning systems that get smarter over time. In an industry where complexity continues to rise, the ability to see quality from end-to-end may become one of the most important competitive advantages.
If you’re ready to rethink how your fab handles End-to-End Quality, [reach out](/manufacturing-execution-solutions/alarmmanagement/).
## FAQs
#### Why do quality problems often show up long after the actual issue occurred?
In semiconductor manufacturing, the event that reveals a problem is often not the event that caused it. A defect may become visible during inspection, testing, or yield analysis even though the contributing condition occurred much earlier in the product lifecycle. Without complete traceability across materials, suppliers, logistics, storage, equipment, and production processes, teams can struggle to identify where the issue originated and which products may have been affected.
#### How can manufacturers find the root cause of recurring quality excursions faster?
Faster root-cause analysis depends on connecting information that is typically stored in separate systems. When quality, manufacturing, equipment, supplier, and material data can be analyzed together, engineers gain the context needed to uncover relationships that would otherwise remain hidden. This helps determine whether multiple events share a common source and reduces the time spent investigating isolated symptoms.
#### What does end-to-end traceability actually mean in a semiconductor fab?
End-to-end traceability means being able to follow the history and impact of materials, parts, consumables, equipment interactions, process conditions, and production events throughout the manufacturing lifecycle. The goal is not simply to know what happened, but to understand how every step is connected so quality teams can assess risk, identify affected products, and make better decisions when issues arise.
#### Why isn't more AI alone enough to improve manufacturing quality?
AI can only generate meaningful insights when it has access to a high quality complete, connected, and contextualized information. If critical data sources are missing or relationships between events cannot be understood, even advanced analytics may produce incomplete conclusions. Successful quality initiatives depend on a strong data foundation that allows AI to evaluate the full manufacturing context rather than isolated data points.
#### How can highly automated fabs prevent quality issues from spreading quickly?
Automation increases speed and consistency, which means both successful processes and process errors can scale rapidly. To prevent isolated issues from becoming larger production problems, manufacturers need the ability to detect abnormal conditions early, understand their potential impact, and trace affected materials or lots before they move further through production. Combining traceability, contextual intelligence, and proactive monitoring helps reduce the risk of widespread quality excursions.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [SmartFactory SPC 助力提升良率、提高盈利能力、减少浪费](https://appliedsmartfactory.com/semiconductor-blog/quality/better-profitability-with-spc/)
**Published:** February 6, 2024
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** 自动化分析减少缺陷，优化持续改进
**Content:**
良率是制造商最关注的关键绩效指标之一，提升良率能够在减少浪费、提高生产力、盈利能力乃至客户满意度方面都产生积极影响。 然而，要实现良率的提升，必须识别并妥善解决生产过程不合格的根源、优化生产流程，形成持续改进文化，以长期保持良率提高。 为此，需要对来自不同工厂设备和系统的数据进行持续分析。 统计过程控制（SPC）系统可以及早发现问题、提供相应的纠正和预防措施，并为生产过程改进提供切实有效的线索，最大限度地减少过程不合格的情况。
[SmartFactory SPC](/zh-hans/semiconductor/process-quality-solutions/spc/) 可以实时处理参数、分析生产数据，以识别过程不合格项。 具体处理方式为验证规格是否在限制范围内，识别可疑的过程趋势，并在发现过程不合格时向员工发出警告。 您可以将其视为过程不合格项的“早期预警系统”，此系统不仅可以识别问题，还能够寻找机会提升品质、降低可变性。
SmartFactory SPC可以实时告诉您问题何时出现以及如何处理这些问题
此外，SmartFactory SPC 还能实时向生产人员反馈生产过程的重要信息，有助于培养持续改进的文化。
采用 SPC 系统可以使持续评估过程性能所需的复杂分析工作自动化，并为提升良率的工艺改进提出有效的建议。 最终，提升良率可以显著提高质量、减少浪费，提高盈利能力。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [How Advanced Packaging MES helps ATP facilities recover capacity](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/how-advanced-packaging-mes-helps-atp-facilities-recover-capacity/)
**Published:** July 12, 2026
**Author:** Christian Elggren, MES Global Product Manager
**Excerpt:** Legacy back-end MES systems are no longer enough
**Content:**
## What’s Inside
- [ Why is advanced test and packaging becoming more complex? ](#index1)
- [ The cost of white space ](#index2)
- [ Where does ATP capacity get lost? ](#index3)
- [ A structural transformation ](#index4)
- [ SmartFactory MES for ATP ](#index5)
- [ How does SmartFactory MES accelerate technology ramps? ](#index6)
- [ How does SmartFactory MES reduce quality and compliance risk? ](#index7)
- [ Production resilience: the factory that doesn't stop ](#index8)
- [ Conclusion: closing the complexity gap ](#index9)
Advanced test and packaging is no longer a simple back-end process. As chiplets, HBM, AI accelerators, and 2.5D/3D IC architectures increase complexity, ATP facilities now require front-end levels of control for tracking, traceability, recipe management, SPC, and dispatching. The facilities that modernize their MES foundation will be better positioned to recover capacity, reduce risk, and ramp new technologies faster.
### Why is advanced test and packaging becoming more complex?
Legacy back-end MES systems were designed for simpler operating models: large lot sizes, stable flows, limited package variation, and lot-level tracking. That model worked when the back end primarily supported wire bond, mold, test, and ship processes. It is not sufficient for modern advanced test and packaging.
The surge in AI accelerators, HBM, 2.5D/3D IC stacking, and chiplet architectures has transformed advanced test and packaging (ATP) into one of the most technically demanding disciplines in the semiconductor value chain. The operational gap between what ATP now requires and what legacy systems can deliver is real, growing, and expensive.
Among the factors impacting why legacy capabilities can’t meet today’s ATP needs:
- **Substrate-level tracking:** Hybrid bonding at sub-10µm pitch requires tracking every substrate position with the precision of a 300mm wafer fab. Lot-level tracking is structurally insufficient.
- **Single-die traceability:** JEDEC JESD31, IATF 16949, and hyperscaler contracts require full field-reconstructible die history. One automotive escape can cost $10–50M in total impact.
- **Automated SPC:** Process windows are shrinking every generation. The minimum viable capability is real-time rule detection, automatic equipment hold, and engineer notification within seconds.
- **Complex recipe management:** Version-controlled recipes with equipment-product compatibility enforcement are non-negotiable in multi-product mixed-technology environments.
### The cost of white space
White space in advanced test and packaging is the productive capacity a facility has already paid for but cannot use because of manual handling, poor dispatching, slow error recovery, and queue-time violations. In mature 300mm logic fabs, equipment utilization targets run 85–90%. In many ATP facilities running mixed advanced packaging technologies concurrently, measured utilization falls into the 60–70% range. The gap is mostly white space, and most of it is invisible because legacy systems lack the data resolution to see it.
### Where does ATP capacity get lost?
White space builds up in predictable ways across a modern ATP facility. In mixed-technology environments, manual material handling makes mis-routing a systemic risk rather than an occasional exception. On a line processing 10,000 substrate passes per month, even a 3% mis-route rate can erase 300 productive passes every month. Dispatching creates another hidden drain. When decisions rely on manual prioritization instead of intelligent, constraint-aware logic, facilities can leave 5–12 percentage points of equipment utilization on the table — equal to $25M of recoverable capacity on a $500M equipment base.
The same pattern appears in error recovery and queue-time control. A wrong recipe, carrier, or inspection program can trigger an unplanned stop, root-cause investigation, and MRB cycle, consuming equipment time that could have been protected through automated recipe dispatch and compatibility locks. Queue-time violations are equally costly in processes such as plasma-activated bonding, where working windows are measured in hours. Missing those windows can mean scrap or rework, while real-time tracking and automated exception management can reduce violations to near zero.
The cumulative cost of white space in a modern ATP facility is 10–20% of available productive capacity. This is not a quality program problem — it is a foundational operational systems problem.
### A structural transformation
SmartFactory SPC focuses on the ease with which such analytical models can be implemented. The platform provides the ecosystem for data preparation, model selection and implementation, which readily works with existing data. Among the key capabilities of this application are user experience and interpretation of results for easier implementation into factory systems. Web-based reporting helps ensure continuous monitoring and maintenance of the model’s performance. One of the advantages of this solution is that it helps shut down tools likely to produce bad products, as well as qualify new tools and validate preventative maintenance (PM) cycles. With many of our customers, we have seen smoothened tool performances for KPI improvements as well as process window gains for better line monitoring and scrap reduction.
### SmartFactory MES for ATP
As advanced packaging complexity increases, ATP facilities need more than incremental process improvement. They need an advanced packaging MES that connects material movement, recipe control, SPC, dispatching, traceability, and exception response in one operational system. This is where SmartFactory MES becomes a foundation for capacity recovery, risk reduction, and production resilience.
### How does SmartFactory MES accelerate technology ramps?
SmartFactory MES helps ATP facilities accelerate technology ramps by executing new processes against predefined MES configurations. Step sequences, recipe-equipment compatibility, and automated SPC monitoring are enforced from the first lot, reducing reliance on manual setup cycles, spreadsheet-based qualification tracking, and operator-dependent training.
When customer specifications change, SmartFactory MES propagates updates automatically. Recipe changes are version-controlled, pilot-qualified on affected lots, and deployed to equipment in hours, not days. Facilities running SmartFactory MES demonstrate new technology ramp times compressed by 30–40% compared to legacy systems.
### How does SmartFactory MES reduce quality and compliance risk?
SmartFactory MES also helps reduce quality and compliance risk by converting invisible process risks into actionable events. Automated SPC detects drift before a specification is breached. Die-level genealogy enables surgical containment in seconds rather than full-lot holds, and equipment-lot compatibility locks prevent the human errors that drive 40–60% of unplanned stops. The asymmetric value of risk mitigation is stark: a single automotive-grade packaging excursion that reaches the field can cost $10–50M in warranty, recall, and customer remediation. The operational systems investment that prevents it is a fraction of that exposure.
### Production resilience: the factory that doesn't stop
ATP facilities cannot afford downtime—and resilience means more than equipment reliability. It means knowing exactly where every lot is, what constraints apply, and what the optimal path forward is, even after a disruption.
It starts with real-time WIP visibility. Knowing the location, status, history, and priority of every unit of material allows teams to assess the impact of a disruption in minutes rather than hours.
With that visibility, production can adapt dynamically. Real-time dispatch decisions are continuously optimized based on WIP state, equipment availability, priorities, and queue-time constraints, allowing the factory to absorb disruptions without manual recalculation.
The response is reinforced through closed-loop process feedback. SPC violations trigger equipment holds, quality events automatically flag downstream inspection requirements, and excursion containment identifies affected lots in seconds before issues can spread.
Customers operating SmartFactory MES report on-time delivery improvements from approximately 85% to more than 95%—a meaningful advantage that strengthens customer retention, supports technology award decisions, and improves competitive positioning.
### Conclusion: closing the complexity gap
Advanced packaging has moved ATP beyond its historical role as a high-volume finishing step. Today’s facilities must operate with front-end discipline: substrate-level tracking, die-level traceability, recipe version control, automated SPC, and real-time exception management. Legacy back-end systems were not designed for this level of product mix, precision, or traceability.
The cost of that gap is measurable. In mixed advanced packaging environments, 10–20% of available ATP capacity can be lost to manual handling, poor dispatching, queue-time violations, and error recovery. At the same time, the market is accelerating; chiplet revenue is projected to reach $236B by 2030, AI accelerator packaging is scaling rapidly, and automotive traceability requirements are expanding as semiconductor content rises toward $1,500–2,000 per vehicle.
For ATP manufacturers, the strategic question is no longer whether complexity will increase. It will. The question is whether operational infrastructure can turn that complexity into faster ramps, lower risk, and more resilient production. SmartFactory MES addresses that challenge by helping facilities compress technology ramp time by 30–40%, reduce unplanned stops by 40–60%, prevent excursions with automated SPC and die-level containment, and improve on-time delivery from roughly 85% to 95%+.
The facilities that close the complexity gap first will not simply keep pace with advanced packaging demand — they will be better positioned to win the next generation of customers, programs, and capacity decisions.
## FAQs
#### Why is our packaging and test operation struggling to keep up even after investing in new equipment?
Adding equipment does not automatically increase output if production decisions, material movement, process controls, and traceability are still managed through disconnected systems. Many facilities discover that delays, misrouting, waiting time, rework, and manual interventions limit throughput long before equipment capacity is fully utilized. A modern MES helps identify and eliminate these bottlenecks so existing assets can produce more value.
#### How can we reduce production delays caused by routing mistakes and process errors?
The most effective approach is to automate process enforcement. When production systems verify the correct route, equipment, program, and process conditions before work can proceed, errors are prevented rather than corrected later. This reduces rework, minimizes unplanned interruptions, and helps keep material moving through the factory according to plan.
#### What capabilities are required to support advanced packaging technologies such as chiplets and 3D integration?
Advanced packaging requires more detailed operational control than traditional back-end manufacturing. Manufacturers typically need granular traceability, automated process monitoring, strict recipe governance, real-time production visibility, and intelligent scheduling. These capabilities help manage increasingly complex product flows while maintaining quality and cycle-time targets.
#### How can we introduce new packaging technologies without disrupting existing production?
Successful technology introductions rely on standardized process execution, controlled change management, and automated validation. When production rules, equipment requirements, and quality checks are built into the MES, new products can be introduced more consistently while reducing dependence on manual coordination, spreadsheets, and tribal knowledge.
#### What should manufacturers look for when evaluating an MES for advanced packaging and test?
An MES designed for advanced packaging should do more than track work in progress. Key capabilities include detailed traceability, automated process control, recipe management, production dispatching, exception handling, material tracking, and quality monitoring within a single operational framework. The goal is to improve throughput, reduce risk, and maintain control as product complexity increases.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Create your own competitive advantage with SmartFactory AI™ Productivity](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactoryai-competitive-advantage/)
**Published:** October 12, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Amplify productivity with pre-built AI/ML models
**Content:**
There is critical demand for semiconductor manufacturing, which can mean significant opportunities for fabs that are able to increase productivity and efficiency. However, existing tools and methods are limited in how much productivity can be achieved or by what magnitude KPIs can be improved. SmartFactory AI makes improvement possible. It enables fabs to create a unique competitive advantage by achieving end-to-end AI/ML model development and deployment that solves productivity and supply chain challenges using the next-generation approach of advanced and intelligent algorithms.
SmartFactory AI addresses two key types of challenges that affect a fab’s productivity and yield: those associated with the prediction model, such as lot cycle time, dynamic bottlenecks, and yield prediction; and problems associated with finding the best logic or parameter values to control production flow or equipment operations in an optimal way, considering real-time and future status. It is the only industrial AI/ML platform that can integrate with scheduling, dispatching, and full auto solutions in the current manufacturing environment.
### Key benefits
Among its key benefits is the elimination of manual model development for every step of production. Rather, the system uses a task automation tool and Solution UI to make it easier to develop an AI/ML system for the entire cycle, in as little as six months. This is roughly a quarter the time it would take to develop individual models for data preparation, ML model training and evaluation, deployment, and monitoring stages of production.
### Enhance your existing APF suite
The platform enhances the existing Applied APF (Advanced Productivity Family) suite by introducing special features to automate deployment and monitor AI/ML models. Through this integration, engineers can use pre-built ML models or configure key parameters that help focus the model on a fab’s particular challenges and ways of problem-solving. There is no need for users to learn additional environments or languages.
In production, SmartFactory AI collects data, trains a model, deploys it to the production environment, and monitors its performance in real-time to see how the model is performing. If there are fluctuations in the model’s accuracy, it can automatically be retrained.
By integrating SmartFactory AI with the production environment (e.g. APF and E3 platforms), semiconductor manufacturers can expect to achieve improved cycle times, utilization, throughput, and yield. No other platform achieves this in as little time or effort.
To learn more about how SmartFactory AI can help you meet your goals,
[ Contact Us ](/connect)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [SmartFactory AI™ Productivity tunes dispatching rule parameters automatically, in less time](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactory-ai-productivity/)
**Published:** August 11, 2023
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** Uncover the transformative power of smart manufacturing for semiconductor operations, enhancing productivity, efficiency, decision-making, and data security. Find optimal value in hours instead of days.
**Content:**
Both front end and assembly test and packaging semiconductor factories deploy global dispatching rules alongside local dispatching rules and schedulers to improve productivity. Typically, the global rule ensures the due dates are met and bottleneck tools utilization is optimized by deploying line balance algorithms. These line balance algorithms have different parameters which need to be adjusted based on factory state for a given product mix. Today, these parameters are tuned manually, or in some cases, [simulation modeling capabilities are used](/blog/dispatching-scheduling-algorithms-impact/). It’s difficult to compute the impact of these parameters for all the equipment and all products and process steps in a factory. Manually adjusting the parameters, therefore, could result in negative impact to factory KPIs, and it could take too much time to find an optimal set of parameters using simulation. This use case provides insight into how we tuned the dispatching rule parameters automatically and in significantly less time using SmartFactory Productivity AI.
Consider the example shown in figure 1, below. Per the global rule, there are four parameters for determining the bottleneck tool and the line balance thresholds to conclude if the tools are starved, sufficient or high, based on numbers of hours work in process (WIP). The tables show the possible range of values these parameters can take. One option for finding the optimal values of these parameters for a given factory state is to run a simulation model. With each simulation, we choose a different combination of parameter values and measure the resulting KPIs, an approach referred to as grid search in literature. Each run is a 90-day simulation and, for a simulation model to run for 90 days and measure KPIs for on time delivery percentage and cycle time, it will take days. This won’t be practical to use in day-to-day operations.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/line-balance-parameters.jpg) Figure 1: Line balance Parameters in Global Rule
To address this issue, we deployed SmartFactory AI Productivity and Evolutionary Optimization combined with Simulated Annealing method to find the optimal parameters for on time delivery and cycle time simultaneously. Figure 2 shows how this algorithm was deployed using SmartFactory AI Productivity, which includes the Simulation AutoSched and Fusion modules along with RTD and Activity Manager.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/algorithm.jpg) Figure 2: Algorithm Deployment
Using this approach, we were able to find the optimal parameter value in hours as compared to days. In each iteration we vary both the line balance parameter values and the combination of bottleneck station families. Where previously it took 300 iterations of grid search to find the best on time percentage of 86.90%, we were able to reach the on-time percentage of 98.83% after just 10 iterations of the model run, as shown in figure 3.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/modeling-1.jpg) Figure 3: Modeling for on-time percentage
When running iterations for the KPI of cycle time, the fourth iteration of the model run using our method reached a KPI of 886 hours; this is in comparison to a KPI of 992 hours by grid search, as shown in figure 4.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/cycle-time-1.jpg) Figure 4: Modeling for cycle time
Once the optimal settings are obtained, these can be integrated with existing dispatching rules and scheduling applications and the results can be integrated and recomputed in daily factory operations, as shown in figure 5.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/production.jpg) Figure 5: Production deployment
Running for the local KPI of total moves on bottleneck equipment, it took only four iterations to find the optimal bottleneck threshold and line balance thresholds to achieve 20,181 moves.
Simulation optimization is the first step in automating the dispatching and scheduling parameters; further improvements are planned to automate these parameters using reinforcement learning methods.
## What’s Inside
- [ Types of dispatching rules ](#index1)
- [ Using algorithms to optimize KPIs ](#index2)
- [ Limitations of manual tuning ](#index3)
- [ Deploying our AI solution ](#index4)
- [ Fast identification of best on-time percentage ](#index5)
- [ Modeling for cycle time ](#index6)
- [ Applying results to daily operations ](#index7)
- [ Bottleneck and line balance thresholds ](#index8)
- [ Conclusion ](#index9)
- [ FAQs ](#index10)
This use case provides insight into how we tuned the dispatching rule parameters automatically and in significantly less time using SmartFactory AI Productivity.
### Types of dispatching rules
Dispatching rules are implemented factory wide, typically as global and **local rules**. The **global rule** includes line balance logic that enables managing customer commits, and local rules that contain additional logic to optimize the throughput for a given area—like Litho. Both front end and assembly test and packaging semiconductor factories deploy global dispatching rules alongside local dispatching rules and schedulers to improve productivity.
### Using algorithms to optimize KPIs
Typically, the global rule ensures the due dates are met and bottleneck tools utilization is optimized by deploying line balance algorithms. These line balance algorithms have different parameters which need to be adjusted based on factory state for a given product mix.
Today, the line balance algorithm parameters are tuned manually, or in some cases, [simulation modeling capabilities are used](/semiconductor-blog/dispatching-scheduling-algorithms-impact/). It’s difficult to compute the impact of these parameters for all the equipment and all products and process steps in a factory. Manually adjusting the parameters, therefore, could result in negative impact to factory KPIs, and it could take too much time to find an optimal set of parameters using simulation.
### Limitations of manual tuning
Consider the example shown in figure 1, below. Per the global rule, there are four parameters for determining the bottleneck tool and the line balance thresholds to conclude if the tools are starved, sufficient or high, based on numbers of hours work in process (WIP).
The tables show the possible range of values these parameters can take. One option for finding the optimal values of these parameters for a given factory state is to run a simulation model. With each simulation, we choose a different combination of parameter values and measure the resulting KPIs, an approach referred to as grid search in literature. Each run is a 90-day simulation and, for a simulation model to run for 90 days and measure KPIs for on time delivery percentage and cycle time, it will take days. This won’t be practical to use in day-to-day operations.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/line-balance-parameters.jpg) Figure 1: Line balance Parameters in Global Rule
### Deploying our AI solution
To address this issue, we deployed SmartFactory AI Productivity and Evolutionary Optimization combined with Simulated Annealing method to find the optimal parameters for on time delivery and cycle time simultaneously.
Figure 2 shows how this algorithm was deployed using SmartFactory AI Productivity, which includes the Simulation AutoSched® and Fusion modules along with RTD and Activity Manager®.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/algorithm.jpg) Figure 2: Algorithm Deployment
### Fast identification of best on-time percentage
Using this approach, we were able to find the optimal parameter value in hours as compared to days. In each iteration we vary both the line balance parameter values and the combination of bottleneck station families. Where previously it took 300 iterations of grid search to find the best on time percentage of 86.90%, we were able to reach the on-time percentage of 98.83% after just 10 iterations of the model run, as shown in figure 3.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/modeling-1.jpg) Figure 3: Modeling for on-time percentage
### Modeling for cycle time
When running iterations for the KPI of cycle time, the fourth iteration of the model run using our method reached a KPI of 886 hours; this is in comparison to a KPI of 992 hours by grid search, as shown in figure 4.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/cycle-time-1.jpg) Figure 4: Modeling for cycle time
### Applying results to daily operations
Once the optimal settings are obtained, these can be integrated with existing dispatching rules and scheduling applications and the results can be integrated and recomputed in daily factory operations, as shown in figure 5.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/production.jpg) Figure 5: Production deployment
### Bottleneck and line balance thresholds
Running for the local KPI of total moves on bottleneck equipment, it took only four iterations to find the optimal bottleneck threshold and line balance thresholds to achieve 20,181 moves.
### Conclusion
Simulations allow manufacturers to run multiple combinations of parameter values and measure the resulting KPIs without interfering with production. However, finding optimal values can still be time consuming and not suited to daily operations. Deploying SmartFactory AI Productivity and Evolutionary Optimization combined with Simulated Annealing method makes it possible to find optimal settings in a timeframe more realistic for daily operations.
Simulation optimization is the first step in automating the dispatching and scheduling parameters; further improvements are planned to automate these parameters using reinforcement learning methods.
## FAQs
#### What is dispatching in a semiconductor fab?
Dispatching refers to the sequence of lots to process at specific equipment in real-time.
#### What is the advantage of using dispatching rules?
Dispatching rules can quickly find solutions and prioritize lots to send to tools to optimize productivity.
#### Do you need both a scheduling solution and dispatching?
Yes. Schedules are generated every 5 to 10 minutes in a factory, as changes are occurring in real-time on the factory floor. These changes can result in schedules that present unclear or inconsistent decisions. A dispatching solution can help overcome some of the schedule’s challenges to maintain or improve productivity. For more about dispatching, read our blog, [ “Improve throughput by 5-10% using SmartFactory dispatching solutions.”](/semiconductor-blog/smartfactory-dispatching-solutions/)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [SmartFactory AI™ Overview](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactory-ai-overview/)
**Published:** November 27, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Discover how SmartFactory AI solutions drive innovation, optimize performance, and enhance real-time data accessibility for seamless manufacturing operations.
**Content:**
#### Transcript
Welcome to the future of manufacturing with AI.
Our SmartFactory Solutions team is driving innovation and enhancing the value of our customers’ business operations. Our AI-driven solutions unify understanding, making data accessible in real-time and optimizing performance like never before.
Now, let’s see how AI is transforming manufacturing. Imagine AI acting on large datasets, providing immediate insights for faster, more accurate decisions. This isn’t just about productivity, it’s about transforming the entire manufacturing landscape.
Why? Because your competition doesn’t rest. To understand this transformation, let’s look at some key capabilities of AI systems. Recognizing the environment, interpreting inputs, learning from past results, and prescribing corrective actions.
These capabilities bring significant benefits to manufacturers. Proper use of AI can increase yield, accelerate output, and reduce costs. AI-powered systems can increase equipment uptime, prescribe equipment maintenance, and optimize supply chains, leading to fewer disruptions and higher efficiency.
By combining data from sensors, machines, and people, AI enhances decision precision with a larger volume of data and accelerates decision-making. Let’s explore some real-world applications of AI in manufacturing. AI predicts equipment failures, reducing downtime and costs.
It increases utilization of production lines by optimizing workflows and ensuring precise quality control with real-time defect detection. Additionally, AI optimizes planning decision-making, improves safety by identifying potential environmental risks, and enhances collaboration between humans and machines with systems such as Cobots. While AI offers many benefits, it also presents challenges.
Security and data quality issues are at the top of the list and can hinder AI implementation. Other known challenges include solution explainability, data scarcity, and disparate technologies. Finally, it’s crucial to identify the AI use case business value.
Meeting these challenges, the future of AI in manufacturing is promising. Join us in shaping this future and stay ahead with SmartFactory AI.
Visit us at [AppliedSmartfactory.com](/).
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Enhance semiconductor business operations with AI-powered solutions](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/semiconductor-business-enhancement-with-ai/)
**Published:** March 10, 2025
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** Benefits to quality and productivity help manufacturers stay ahead of demand
**Content:**
## What’s Inside
- [ Capabilities of AI systems ](#index1)
- [ How AI benefits manufacturing ](#index2)
- [ Increasing productivity and quality ](#index3)
- [ Enhancing operational efficiency ](#index4)
- [ Real-world applications of AI in manufacturing ](#index5)
- [ The future of AI in manufacturing ](#index6)
Artificial Intelligence (AI) is the process of programming a computer system or machine to ingest data and perform decisions based on that data. With enough data, computational power, and context, AI can make decisions that have not been seen before by human intelligence. This capability allows AI to provide innovative solutions and insights that can significantly enhance business operations and productivity.
### Capabilities of AI systems
AI systems generally incorporate four fundamental capabilities. They can: - Sense the world around them using cameras, microphones, or sensors
- Comprehend by extracting information from these inputs through pattern detection and context recognition
- Act based on that information
- Learn by refining future actions based on the evaluation of past actions
### How AI benefits manufacturing
The manufacturing sector can benefit from AI in many ways. This includes increased yield and production speed, reduced operational costs, and improved product quality. Additionally, AI-powered systems can predict equipment failures, schedule maintenance, and optimize supply chains, leading to fewer disruptions and higher efficiency. They combine data from sensors, machines, and people to help manufacturers become more data-driven, optimizing production and maintenance processes, improving product quality, and addressing sustainability concerns.
For example, AI-powered automation software solutions like our SmartFactory portfolio are designed to co-optimize yield and cycle time and empower manufacturing operations.
### Increasing productivity and quality
AI-driven automation enhances productivity by allowing machines to perform tasks faster and more accurately than humans, leading to higher output. AI can also monitor production lines in real-time, detecting defects and ensuring that only high-quality products reach the market.
AI also can help manufacturing operations provide intelligent and real-time orchestration and optimization of their processes, not just inside the four walls of an individual manufacturing facility but across the entire supply chain. This includes improving quality assurance and quality control (QA/QC) testing and inspection processes, rationalizing the number of QA/QC tests conducted, and providing better insight into the root causes of failures.
### Enhancing operational efficiency
AI solutions can significantly improve operational efficiency by automating routine tasks and optimizing workflows. For example, AI can analyze production data to identify bottlenecks and suggest improvements, ensuring that manufacturing processes run smoothly and efficiently.
AI-driven manufacturing enhances product safety and reliability by producing precise components, boosting performance, and system safety. It also helps in minimizing production errors, improving product design, and accelerating time-to-market
### Real-world applications of AI in manufacturing
In the real world, AI is being used in various ways to improve manufacturing. For instance, AI-powered predictive maintenance systems can forecast when equipment is likely to fail, allowing for timely repairs and reducing downtime. AI is also used in quality control, where it can inspect products for defects with greater accuracy than human inspectors.
Our SmartFactory AI™ solutions offer integrated automation software designed to maximize efficiency and empower manufacturing operations. These solutions include productivity enhancement, process quality improvement, MES integration, and supply chain management, covering everything from enterprise planning to production control.
### The future of AI in manufacturing
The future of AI in manufacturing looks promising, with continuous advancements in technology leading to even greater efficiencies and innovations. As AI continues to evolve, it will play an increasingly vital role in helping manufacturers stay competitive and meet the growing demands of the market.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Achieve accurate lot cycle time predictions for more on-time deliveries](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/achieve-accurate-lot-time/)
**Published:** January 6, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Improve the accuracy of lot fab out predictions with AI/ML
**Content:**
The current statistical method of predicting lot cycle time is, on average, only 70 percent accurate—not a reliable level of accuracy for a busy fab looking to increase productivity. Ultimately, fab teams spend a significant amount of time each day reviewing prediction data and developing new, accurate predictions because the statistical model cannot represent real-time dynamics in the fab. This points to a need for a faster, easier, and more accurate solution for predicting lot cycle time in 14-day increments. In a recent customer application, SmartFactory AI™ Productivity and Engineered Works® were proven to improve fab out prediction accuracy to 85 percent.
Through some experimental studies, we determined the most appropriate ML model for this customer’s needs was a gradient boosted tree-based machine learning model, particularly the Light Gradient Boosted Machine implementation. Widely used in the industry, this was particularly suitable because this framework is used to make predictions in tabular data, has strong generalization property on unseen data, and is robust against noise.
Using SmartFactory AI Productivity, the ML model was trained on the previous 24 months’ fab out data. For the feature calculation, we defined several features that can represent the lot flow and fab behavior, such as station statistics and WIP (work in process) features which are calculated daily by lot priority and by the steps of each route or part. A Clickhouse database was used to store feature data.
The ML model was built and located on top of the current working systems, so the ML module and the current RTD or scheduling solution collaborate and communicate with each other. The ML model has been trained to run based on schedules including hourly, daily or by shift, and has learned the lot flow and current fab behavior from any one step to the final. It will create one model per step to predict cycle time at the final step. For example, if there is a lot at step A and 12 steps are remaining until fab out, then 12 models will be generated, one model per step pair to predict the cycle time until the final step. Each model will be trained on the historical feature data, WIP profile from the current step to the final step, utilization, tool availability, and lot priority. These models are saved to pickle files on disk, and all are aggregated into one main pickle file for Formatter. These can be deployed to production.
You can see the details of deployment and the results in Figure 1.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/01/figure-1-shows-details-of-deployment-and-results.jpg) Figure 1: Shows details of deployment and results
When the current RTD or scheduling solution system needs a certain prediction, it will refer to those the ML module has made. The ML model automatically retrains based on conditions not covered in its past training data and the predictions are modified and become more accurate as a result.
With an accurate fab out prediction model, fabs can better determine reasons for late lots and improve order to delivery, for example by changing dispatching rule parameters to expedite the late lots.
The ML model developed for the customer was evaluated based on test data set after the training was completed. Metrics defined for model evaluation and accuracy included as key performance indicators: Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). We defined the accuracy metric as 1-Mean Absolute percentage error, meaning the average of each lot’s prediction accuracy. Our accuracy comparison showed the ML model had 5 to 13% better results than baseline model. This approximately 10% accuracy increase could lead to a 2% on time delivery (OTD) increase and 2% inventory maintenance cost reductions.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Solve lot cycle time prediction challenges with greater speed and accuracy](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/prediction-accuracy/)
**Published:** March 28, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Built on our advanced APF platform, this AI-powered approach boosts model accuracy from 75% to 95%—while making deployment faster and easier.
**Content:**
### Transcript
Maintain your leading edge by resolving lot cycle time prediction problems. With SmartFactory AI™ Productivity, our customers are achieving more accurate predictions and improving their order-to-delivery rates. SmartFactory AI Productivity will help with visibility of up-and-downstream productivity and supply chain management challenges.
With statistical and simulation models, constant monitoring is required and cannot represent real-time dynamics, resulting in diminished accuracy. Our prediction ML model will train on factory and data history and run based on schedules, including hourly, daily, or by shift, and learn lot flow and current fab behavior of the entire production cycle. With ML Automatic Retraining, model accuracy can improve from 70-75% to 85-95%.
This level of accuracy will be maintained without human intervention. And the approximate 10% accuracy improvement includes a 2% on-time delivery rate increase and 2% inventory maintenance cost reduction. Built easily on top of your current APF platform, Applied SmartFactory AI Productivity is not only a faster, easier, and more accurate solution for all prediction challenges, but a game changer for the industry.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Innovations that will help semiconductor manufacturers increase efficiency in real-time](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/increase-efficiency-real-time/)
**Published:** November 28, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Semiconductor growth is anticipated and there are many tools to help drive it
**Content:**
The global semiconductor industry has experienced many challenges over the past several years amidst a growth in demand for semiconductors in products from earbuds to automobiles. Analysts are now optimistic the industry has begun recovery that will continue into 2024. World Semiconductor Trade Statistics (WSTS) predicts growth of 11.8% in 2024. In the area of AI semiconductor revenue, Gartner anticipates double-digit growth of more than 25%, to $67.1 billion.
Among the many factors that will contribute to the growth will be the ability of semiconductor manufacturers to make the most of several key innovations: - **Artificial Intelligence:** as much as AI is placing demands on chip manufacturers for AI-ready hardware, the semiconductor companies themselves have embraced the [potential of AI](/ai/) to improve process quality, optimize production, and increase efficiency in their fabs.
- **Internet of Things:** has spurred demand for semiconductors while also being employed by the industry to help keep up with that demand. IoT devices have found their way into the production environment for real-time data capture and monitoring of tools, equipment, and processes. Armed with the right automation solution, these devices facilitate continuous process improvement.
- **Simulated Fabrication:** developing new recipes and processes is costly and time consuming. Simulation, or virtual modeling, with AI and ML models enables manufacturers to [simulate the process flow](/blog/semiconductor-manufacturing/). They can generate a high volume of data in days instead of in the weeks or months it would take to produce enough wafers to gather this data. The models can quickly provide insights into bottlenecks, [cycle time](/blog/mes-strategy/) and output, as well as predict problems that may impact products—all without having to interrupt current production.
- **Innovative Technologies:** increasingly smaller chips necessitate greater accuracy in placement of both patterns and wiring. Manufacturers have turned to advances in fabrication technology such as robotic wafer handling and unique fabrication techniques such as additive manufacturing.
- **Innovative Materials:** semiconductor companies have looked to materials such as gallium nitride (GaN) and silicon carbide (SiC), to achieve higher operating temperatures, high voltage resistance, a smaller form factor, and faster switching. Manufacturers’ continued ingenuity in working with innovative materials will help them overcome chip size limitations.
Semiconductor manufacturers who are willing to leverage the power of innovations that can improve their process, productivity, and quality in factories of any size will be best positioned to meet customer requirements and stay relevant in this dynamic marketplace.
## What’s Inside
- [ Artificial intelligence ](#index2)
- [ Internet of things ](#index3)
- [ Simulated fabrication ](#index4)
- [ Innovative technologies ](#index5)
- [ Innovative materials ](#index6)
- [ Conclusion ](#index7)
The global semiconductor industry has experienced many challenges over the past several years amidst a growth in demand for semiconductors in products from earbuds to automobiles. Analysts are now optimistic that the industry has begun recovery that will continue into 2024. World Semiconductor Trade Statistics (WSTS) predicts growth of 11.8% in 2024. In the area of AI semiconductor revenue, Gartner anticipates double-digit growth of more than 25%, to $67.1 billion.
Among the many factors that will contribute to the growth will be the ability of semiconductor manufacturers to make the most of several key innovations.
**Artificial Intelligence:** as much as AI is placing demands on chip manufacturers for AI-ready hardware, the semiconductor companies themselves have embraced the potential of AI to improve process quality, optimize production, and increase efficiency in their fabs.
**Internet of Things:** has spurred demand for semiconductors while also being employed by the industry to help keep up with that demand. IoT devices have found their way into the production environment for real-time data capture and monitoring of tools, equipment, and processes. Armed with the right automation solution, these devices facilitate continuous process improvement in smart manufacturing in the semiconductor industry.
**Simulated Fabrication:** developing new recipes and processes is costly and time-consuming. Simulation, or virtual modeling, with AI and ML models enables manufacturers to simulate the process flow. They can generate a high volume of data in days instead of in the weeks or months it would take to produce enough wafers to gather this data. The models can quickly provide insights into bottlenecks, cycle time, and output, as well as predict problems that may impact products—all without having to interrupt current production.
**Innovative Technologies:** increasingly smaller chips necessitate greater accuracy in placement of both patterns and wiring. Manufacturers have turned to advances in fabrication technology such as robotic wafer handling and unique fabrication techniques such as additive manufacturing.
**Innovative Materials:** semiconductor companies have looked to materials such as gallium nitride (GaN) and silicon carbide (SiC), to achieve higher operating temperatures, high voltage resistance, a smaller form factor, and faster switching. Manufacturers’ continued ingenuity in working with innovative materials will help them overcome chip size limitations.
### Conclusion
Semiconductor manufacturers who are willing to leverage the power of **innovative semiconductor solutions** that can improve their process, productivity, and quality in factories of any size will be best positioned to meet customer requirements and stay relevant in this dynamic marketplace.
## FAQs
#### Why is data preparation for AI considered a challenge in semiconductor manufacturing?
Data preparation for AI can be expensive in terms of time and resources, making it a barrier, especially for smaller companies. Historical data may also be insufficient due to evolving environments.
#### How does simulation help overcome data collection challenges for AI deployment?
Simulation allows for the creation of synthetic data, eliminating the need for extensive data cleaning. It provides an efficient way to generate diverse and high-quality data for AI training.
#### What are some practical benefits of using simulation in AI deployment?
Simulation enables the exploration of AI in essential use cases without resource limitations. It accelerates projects, reduces costs, and quantifies the impact of changes before implementation, reducing risks.
#### What role does simulation play in scenarios like Reinforcement Learning (RL) and Machine Learning (ML) in semiconductor manufacturing?
Simulation plays a crucial role in RL by providing a detailed environment for agents to learn and make decisions. In ML, it allows models to be trained on rich datasets, leading to operational efficiency gains and KPI comparisons.
Accelerate the value AI can bring to your factory’s operations with simulation! Simulation addresses insurmountable data preparation tasks when deploying AI in a production environment. Deploying AI in production is no small feat; there are many steps to a successful implementation. An [AI lifecycle](/blog/improve-productivity/) consists of design, development, and deployment components (as shown in figure 1). While each phase has its own challenges, preparing the substantial, high-quality data required for an accurate model during the first stage often is enough to discourage companies from continuing the process toward deploying AI.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/end-to-end-lifecycle.png) Figure 1: AI end-to-end lifecycle.
Collecting and formatting diverse data required for deep learning is often expensive in both time and money, which is sometimes infeasible for smaller companies. Even if a manufacturer has the resources required to collect large amounts of data, historical data is often inadequate due to an evolving environment. For example, tools and process steps are constantly adapting to uncertainties found in supply chains, labor limitations, or change in part types. Evolving scenarios (i.e., adding more time constraint steps) in semiconductor manufacturing are especially common as technology nodes progress. Consequently, these rapid changes do not allow time for a diverse, historical dataset to develop to train models.
However, what if there was a way to get more quality data? What if AI could be explored on business essential use cases without the resource limitations of technology advancements? With simulation, you can answer these ‘what-ifs’! You can model various scenarios and generate synthetic data to use in AI training. Projects can be accelerated without the cost of cleaning raw datasets and in significantly less time than it takes to collect a sufficient amount of data. Quantifying the impact of changes in a simulated environment prior to production implementation is also key to avoiding unnecessary, costly risks. Furthermore, training models on rich datasets develop more robust, resilient models. Evaluating on-edge cases or other diverse scenarios that seldom occur in historical data increases generalization abilities of models, which improves accuracy overall.
### Requirements for an acceptable simulation model
Simulation requires many details for an accurate semiconductor manufacturing replication. Not only must simulations replicate various scenarios in a semiconductor factory environment, but they also need to have the ability to replicate dispatching and scheduling rule behavior found in a production system. Quick, scalable run times and flexibility to accommodate various planning horizons are also necessary. From simulating a short-term planning situation (i.e., two-day run to illustrate a tool down scenario) to a larger simulation model to represent a long-term planning example (i.e., one year run to demonstrate the impact of adding new equipment), end users will always want a reasonable run time with results in minutes.
### Use cases: where simulation can support AI in smart manufacturing
There are multiple scenarios where simulation plays a key role. For starters, [Reinforcement](/blog/deep-reinforcement-learning/) Learning (RL) is growing in popularity and simulation can play a vital role in this architecture. RL involves an agent, a computer program or an intelligent system, attempting to take actions in an environment to change its state for maximum manufacturing and productivity. Here, an accurate, very detailed simulation model can act as the environment where the agent’s actions can be observed and changed. For example, a simulated environment can support an agent in learning when to release lots in a queue-time constraint scenario. Figure 2 below shows an RL framework that includes a simulator environment.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/architecture-with-simulation.jpg) Figure 2: RL architecture with simulation.
Another great example is utilizing simulation in a machine learning (ML) framework, such as predicting [cycle time](/blog/achieve-accurate-lot-time/). Simulation allows models to be trained on a rich, multi-year dataset, which aids prediction accuracy. Operational efficiency gains are then possible as planners are given the opportunity, in a non-production, simulated environment, to test and validate changes such as updating dispatching and scheduling parameters required for late lot predictions. Just as in the RL example above, simulation can find key performance indicator (KPI) differences by evaluating ML or RL models versus existing dispatching rules or scheduling models. This provides the powerful opportunity to compare those differences.
Together, simulation and AI can create a [productivity solution](/blog/smartfactoryai-competitive-advantage/) that enables real operational efficiency gains. A fast, flexible, scalable, and very accurate simulation aspect provides the opportunity to support AI solutions for current dispatching and scheduling dilemmas. From predicting lot cycle time to optimizing dispatching parameter values and scheduling constraints, SmartFactory AI Productivity is rapidly accelerating AI innovations into a reality!
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Minding the Gap with AI and ML Processes](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/minding-the-gap-with-ai-and-ml-processes/)
**Published:** December 10, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Experience a smarter way of controlling manufacturing using the SmartFactory Productivity AI/ML platform.
**Content:**
In the UK, the term “mind the gap” refers to **watching out for the space between the train and the platform.** The automated warning is heard thousands of times each day at every stop in the underground. In a general sense, the term means to look after, watch for something, explore what’s missing or what’s not there.
For semiconductor fab managers who are considering artificial intelligence (AI) and machine learning (ML) technologies, here’s some questions to consider: are you mindful of gaps in your fab data? Are you aware of them? What’s missing with your manufacturing operations or preventing you from moving on to smart manufacturing? Do gaps exist between what’s required with your operations and what can be achieved?
The article highlights issues associated with moving to smart manufacturing and looks at the value of making changes to current fab systems using productivity AI and ML processes, focusing on prediction model problems and equipment control through optimization. A use case is provided to illustrate how to use an AI/ML platform to predict lot cycle time.
### Self-knowledge, Restrictions, and Latency
In the current productivity system and control environment of fabs, three key limitations exist that prevent manufacturers from moving on to smart manufacturing (see Figure 1):
1. **Manual adjustments.** For multiple area scheduler and dispatching rules, manufacturers rely heavily on their current skill set and knowledge, which often falls short and is time consuming.
2. **Model restrictions.** From the perspective of model run time and accuracy, clear limits exist with the current simulation models being used for predicting dynamics in the factory.
3. **Latency.** For scheduling, dispatching, equipment and process health controls, latency delays still prevail in setting configuration values due to lack of integration and prediction speed and accuracy.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/figure1-current-fab-challenges.png) Figure 1. The three key limitations preventing manufacturers from moving on to smart manufacturing and our approach to address these limitations
### A Smarter Way
If manufacturers can make some essential changes to their current system using productivity AI and ML processes, they can achieve improvement and a smarter way of controlling manufacturing. More specifically, by effectively using AI and ML models and algorithms, you can establish a foundation of solving two types of manufacturing problems (see Figure 2): 1. The first relates with **prediction model problems**—that is, problems associated with lot cycle time prediction, dynamic bottleneck prediction, and yield prediction. Using the proper ML algorithm for each of these problems offers a good solution.
2. The **second** relates with **finding the best logic or parameter values** to control the production flow or equipment operations in an optimal way, considering real-time and future status. A reinforcement learning (RL) model could be a good solution to find and learn the optimal logic and parameter setting based on an intensive training process.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/figure2-problems-and-solutions.png) Figure 2. Two key fab problems addressed with AI and ML processes and specific solutions to these problems
### Minding the Gap
To help with this effort, our SmartFactory Productivity AI/ML Platform provides a toolbox for (1) building custom algorithms for solving a wider range of problems, (2) powering automated processes, and (3) making manufacturing equipment and processes **more efficient** and **profitable**. Using this toolbox can reduce the time required for developing and deploying a total ML solution by more than **30%**.
The platform consists of the following— 1. Predefined **feature factors** for solving common productivity problems. Feature factors are a type of statics value like mean cycle time at a step or the average number of lots at a step. Each feature factor represents a certain feature of a lot, equipment, or step. With the AI/ML platform, manufacturers can reuse or modify APF Formatter reports, specifically created for feature calculation of predefined feature factors. By using APF Formatter, manufacturers can easily manage feature factors and feature calculations.
2. Ready-to-use **ML models** for solving common factory productivity and supply chain problems. These models serve as “baseline” solutions that you can freely modify and reuse as needed. You can build and deploy ML models by using the current APF platform in all stages of the ML model development lifecycle—from data preparation to deployment and monitoring. If you are familiar with the current APF platform, you can build your own ML model more easily.
3. Ready-to-use **algorithms** for automatically setting scheduling and dispatching parameters. These algorithms are RL model-based and built around simulation-based optimization.
4. Pre-built **solution UIs** for evaluation and monitoring. These UIs expedite the total process of building and deploying new ML models
Figure 3 contrasts current systems of manual control with AI/ML embedded systems for automated control. In addition to its feature factors, the AI/ML platform is unique in several ways: 1. The platform provides a **data-driven approach** with **ML/RL algorithms,** so you can automatically configure or adjust dispatching and scheduling parameters—eliminating the need for manual adjustments. Example dispatching and scheduling parameters include Hot\_lot\_factor, Prefer\_tool\_factor, and Step\_move\_target\_factor.
2. The platform also provides an **ML prediction model** capable of executing quick runs, enabling the scheduler and dispatcher to use the results in real-time, improving accuracy. This model even **incorporates training automatically** with time-based or condition-based patterns, giving you better visibility and quicker response to needs.
3. Based on the improved ability of the prediction model, you can more effectively **integrate real time and predicted data,** eliminating latency delays associated with controlling key configurable parameters.
4. The APF Formatter has a **Python block** that can run a ML model coded by Python, so if you’re using the APF platform for the current scheduling and dispatching rule development environment, deploying ML models will almost be similar with the current rule deployment process. This is a great benefit of the Applied AI/ML platform for current APF users because they can develop and deploy AI/ML models without changing their current development and deployment environment.
5. Finally, after deploying a model to production, you must monitor model performance and periodically retrain the model based on performance. In the Applied AI/ML platform, **Activity Manager®** automatically manages this workflow process.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/figure3-current-vs-ai-platform.png) Figure 3. The differences between current systems of manual control and AI/ML embedded systems for automated control
### Predicting Lot Cycle Time Using Smarter AI/ML Controls
To illustrate the use of the AI/ML platform, we can look at the challenge of predicting lot cycle time as an example. Lot cycle time prediction refers to predicting the completion time of each lot at a step. With an accurate lot completion time prediction, fab managers can check if their daily fab-out plan meets the schedule, so it plays an important role in a successful on-time delivery.
Figure 4 shows how to build an ML model for lot cycle time prediction (steps 1–5). For a lot at a step, if 12 steps are remaining until fab out, then 12 models will be generated, one model per step pair, and each model will be trained. And aggregated model files will be deployed to production.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/figure4-use-case-1a-build.png) Figure 4. Building an ML model to predict lot cycle time
Figure 5 shows the deployment of the lot cycle time prediction model and the results (steps 1–4). To train and test the model, you can use historical lot transaction data and various future simulation data as your input data. To test and evaluate the model, you can use a basic metric-like precision matrix test. For the deployment, you can use APF Formatter to make a completion time prediction for each lot. To obtain the lot cycle time prediction, import the feature data and the trained ML model to a Python block, and the result of this Python block is the lot cycle time prediction.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/figure5-use-case1b-predict.png) Figure 5. Deploying the lot cycle time prediction model
### Conclusion
Are you mindful of gaps in your factory data? How well do you manage predictions for lot fab-out events, lot step arrivals, and tool down events? The productivity AI/ML platform is a set of tools for problem solving issues associated with such events. It powers automated processes and makes manufacturing equipment and processes more efficient and profitable. These tools support the general AI/ML model development and deployment lifecycle by supporting efficient feature calculation and management. And the platform enables manufacturers to easily deploy an ML model with their current scheduling and dispatching rule development environment. After deploying a model to production, manufacturers can monitor model performance and retrain the model based on performance and significant fluctuations in the fab.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Infineon Technologies describes how they optimize productivity](https://appliedsmartfactory.com/semiconductor-blog/use-cases/infineon-technologies-describes-how-they-optimize-productivity/)
**Published:** October 18, 2021
**Author:** Michael Förster
**Excerpt:** Enable dispatching, planning, and scheduling solutions integrated with real-time data to boost factory productivity.
**Content:**
Infineon Technologies, one of the 10th largest semiconductor manufacturers worldwide, has deployed our SmartFactory Advanced Productivity Family (APF) to enable automated decision making and optimize existing automation solutions. Because Infineon was relying on Excel to make assembly and test decisions manually, they needed a shoulder-to-shoulder automation solution where man and robot worked in parallel. Additionally, they wanted to reduce the effort it took to use real-time data from systems with different levels of data quality and high complexity.
Watch the video to see how they used APF for scheduling to achieve a **5 to 15% capacity improvement** across multiple work centers at their front-end sites, and to support fully automated decision making at their back-end sites.
#### Transcript
Infinite Technologies has 35,000 employees. It’s running 19 production facilities and 34 research and development locations around the world. Our business environment is not really different from that of any other semiconductor company and our competitors.
In order to stay in business, we need a certain percentage productivity increase every year for our 6, 8 and 12 inch factories. Infineon transitions from the classical semiconductor production flow, which is running a fab, you test, you have an assembly and the final test, to more and more complex production networks across multiple sites, including subcons. Also, we are faced with an increasing product mix.
So, this is adding to complexity significantly. So, we are producing more different things at the same time. Obviously, we need to reduce manual planning effort and we need to provide more accurate delivery forecasts and early warnings.
And last but not least, there is a huge pressure to standardize and harmonize IT and automation solutions for existing factories. The key requirement is really, you have to get to automated decisions and you have to optimize existing automation concepts and solutions, which have been developed in the past years. Let me give you some examples.
In assembly and test, there are lots of manual decisions. To plan setup corridors, lot starts or to do forecasts for the supply chain. Some of them are still based on Excel. Another example is coming from the front-end manufacturing sites.
We have to go for full automation in parallel to manual processes. So, we call it the shoulder-to-shoulder situation, where man and, well, the operator in the factory and the robot have to work in parallel. And factories have a very different degree of automation.
So, we have already pretty highly automated factories, but we also have on the other side factories, which just started the automation projects. For all this, we must reduce the effort to integrate real-time data coming from different systems, having various levels of data quality. Many of these systems are site-specific, have been implemented over many years and the complexity is really huge.
So, the market requires improved, optimized and real-time feedback into the supply chain. APF stands for the Applied Materials Product Advanced Productivity Family and is really a great tool when it comes to integrating with real-time data sources, when it comes down to integrating with many, many different data sources. Out of the APF suite, we are using the dispatching component, which is the Real-Time Dispatcher, RTD.
We also use the reporting capabilities and we use Activity Manager®. And as no real programming experience is required to build those APF rules, IT can shift automation, reporting and diagnostic responsibilities back to business users in line control or in automation groups and in industrial engineering. And you can imagine just by pushing back the responsibility of the people who actually came up with the requirements and who understand their business better than IT, you speed up projects significantly.
And at the end of the day, you have very short learning cycles and a good strategy for rapid prototyping. In front-end sites, we are using APF and a commercial solver to implement scheduling. Results exceeded our expectations.
We saw a 5-15% capacity improvement across multiple work centers. Those work centers were furnaces, wet benches, Azure, Sputter tools and also lithography. In back-end sites, we started to use APF and that commercial solver to support full automated decision-making for lot starts, equipment setup planning and lot sequencing.
A very important thing we achieved is now that the end-users can validate data, they can check for data consistency and sanity checks, etc., which also speeds up our project significantly. Within 18 months, we rolled out RTD to three different sites with very heterogeneous data sources and site-specific business processes in order to support the ongoing large and ambitious automation projects. In terms of IT, RTD or APF is very important as a building block, as a baseline.
It helps to harmonize and to standardize solutions and it really has become a building block for all the automation projects, the running ones as well as the ambitious upcoming ones.
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Semi
---
### [Mitigating cybersecurity challenges for the semiconductor industry](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mitigating-cybersecurity-challenges-in-semiconductor-industry/)
**Published:** August 27, 2025
**Author:** Brian Korn, CIM Solution Architect
**Excerpt:** The industry is a significant target of cyber-attacks, but there are ways to reduce the risk
**Content:**
## What’s Inside
- [ Rising threats ](#index1)
- [ Global impacts ](#index2)
- [ Preventive measures ](#index3)
- [ The industry’s response ](#index4)
- [ SmartFactory’s role in prevention ](#index5)
- [ Conclusion ](#index6)
The semiconductor industry has seen a robust increase in demand due to the world’s dependence on technology. Given its role as the foundation of innovation in industries ranging from consumer electronics to defense, it has also become a high value target for cyberattacks. The industry is a principal objective for nation-state actors, financially motivated attackers, and supply chain disruptions. In fact, there has been a 72% increase in data breaches since 2021 and an 81% rise in financial losses due to cybersecurity complaints in 2023.[1](#references) There is an urgent need for improved cybersecurity measures.
### Rising threats
There are several factors that make the semiconductor industry particularly vulnerable, including its valuable intellectual property in the form of proprietary designs and fabrication processes. Its highly interconnected global supply chain and reliance on cutting-edge science and engineering compound its cybersecurity challenges. Reports by cybersecurity companies detail attacks on the industry with far-reaching consequences ranging from halted production to financial losses from compromised intellectual property. Among these, Cyble last year reported a surge in cyber threats targeting semiconductor firms. These ranged from ransomware and supply chain breaches to sophisticated espionage campaigns.[2](#references) A separate report by Critical Start revealed that, in the first half of 2024 alone, the manufacturing and industrial sectors (led by semiconductor firms) suffered 377 confirmed ransomware and data leak incidents.[3](#references)
One of the most high-profile incidents was the ransomware attack on Advantech in 2020, where hackers demanded 750 bitcoins (valued at the time at $13.8 million).[4](#references) In May 2023, Lacroix, a major electronics manufacturer, was forced to shut down three of its eight global sites for a week due to a cyberattack that crippled its virtual infrastructure.[5](#references)
### Global impacts
Cyber-attack disruptions to the semiconductor industry cause immediate financial damage to the company at the center of the attack, but also have a ripple effect through the global supply chain. This includes delayed product launches and impacts to industries reliant on timely chip deliveries.
Despite the high stakes, many semiconductor firms remain underprepared. More than 60% of manufacturing companies have experienced cyberattacks, and the average cost of a breach in this sector is around $1 million.[6](#references)
### Preventive measures
While daunting, it’s possible to prevent many forms of these attacks. In some cases, it’s a matter of tightening training and protocols. For example, 70% of breaches are due to human error[7](#references) such as phishing attacks or poor password hygiene – both issues that should be addressed in ongoing staff training.
Other methods for reinforcing defenses against cyber threats include:
- **Zero trust architecture:** a policy whereby no user or device is trusted by default. This minimizes lateral movement in the case of a breach.
- **Supply chain risk management:** identification of weak links in the supply chain to enforce cybersecurity standards.
- **Advanced threat detection:** deployment of managed detection and response (MDR) and 24/7 security operations centers (SOC).
- **Employee training:** informing and empowering employees to protect against phishing and social engineering attacks.
- **Regulatory compliance:** aligning with global standards such as ISO/IEC 27001 and the NIST Cybersecurity Framework.
### The industry’s response
Understanding the need for an industry-wide strategy, SEMI launched the SEMI Manufacturing Cybersecurity Consortium (SMCC), a key initiative to address threats via a unified approach. SMCC brings together global stakeholders to develop standards, share threat intelligence, and align with regulations. This includes representatives from fabs, equipment manufacturers, software vendors, and academia. By taking a practical, standards-based and collaborative approach, the aim is to enhance security while streamlining compliance.
Collaborative working groups focus on factory-level security, supply chain readiness, regulatory alignment (including the EU Cyber Resilience Act), and educational outreach. Through these, the SMCC has developed standards such as SEMI E191 for equipment compliance, frameworks for supply chain security, and mechanisms for cross-industry threat sharing—even among competitors.
Among the initiatives the SMCC has undertaken since its inception at SEMICON West in July 2023, are:
- Partnering with NIST to develop a tailored cybersecurity profile for semiconductor manufacturing.
- Publishing SEMI E191 and E191.1 standards for cybersecurity status reporting.
- Forming a dedicated group to interpret and align with the EU Cyber Resilience Act.
### SmartFactory’s role in prevention
SmartFactory solutions play a significant role in improving supply chain security within the semiconductor manufacturing industry by embedding cybersecurity into the core of smart manufacturing operations. There are many preventive measures inherent to the SmartFactory platform, including:
**Secure data integration and flow:** The integration of data across equipment, processes and systems is designed with secure data protocols and access controls. This reduces the risk of unauthorized access or data tampering.
**AI-driven anomaly detection:** [AI and machine learning](/semiconductor-blog-category/ai-ml/) are leveraged to detect unusual patterns in equipment behavior or process data—often early indicators of cyber intrusions or system manipulation.
**Role-based access and authentication:** Only authorized personnel can access sensitive systems or make changes to production parameters to limit the attack surface and help prevent insider threats.
**Real-time monitoring:** Integration with factory systems and [real-time monitoring](/semiconductor-blog/manufacturing-execution/manufacturing-software-systems/) of factory operations that include cybersecurity-related metrics means any deviations from expected performance can trigger alerts. This enables an early and rapid response to threats.
**Supply chain and equipment compliance:** Manufacturers can more easily align with industry-wide best practices and a reduction in vulnerabilities introduced by third-party tools because SmartFactory solutions are often used as part of standards such as SEMI E187 and E191.
**Integration with broader cybersecurity frameworks:** Integration with enterprise cybersecurity tools aids in centralized threat detection and response.
**Secure data exchange between fabs and suppliers:** Only authenticated and authorized systems can interact with factory networks, reducing the risk of the supply chain-originated breaches. These currently account for more than 65% of incidents in semiconductor factories.
**Support for standardized assessments of supplier cybersecurity maturity:** Alignment with initiatives such as SMCC’s WG3 helps fabs evaluate and onboard vendors based on consistent security criteria.
### Conclusion
The world already relies heavily on semiconductors and demand is only expected to grow. As manufacturers work to meet those demands, they cannot afford the delays and ensuing costs incurred from a cyberattack. From basic employee training to collaboration with supply chain partners and choosing automation solutions with inherent security elements, it is possible—and critical—to reduce these threats.
### References
\[1\] “Cybersecurity Framework Profile for Semiconductor Manufacturing,” NIST, 4 February 2025. \[Online\]. Available: .
\[2\] “Semiconductor Threat Report 2024 | Cyble Industry Insights,” Cyble. \[Online\].
Available: .
\[3\] ”Manufacturing and Industrial Sectors: Top Targets for Cyberattacks in 2024,” Critical Start. \[Online\] Available: .
\[4\] “Manufacturing Cybersecurity: Stats, Risks & DataGuard Solutions 2024,” DataGuard. \[Online\].
Available: .
\[5\] Ibid.
\[6\] Ibid.
\[7\] Ibid.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Featured, Semi
---
### [Avalign Technologies improved planner productivity by approximately 75% using SmartFactory Production Control](https://appliedsmartfactory.com/semiconductor-blog/use-cases/avalign-technologies-case-study/)
**Published:** October 27, 2023
**Author:** Madhu Mamillapalli, Global Product Manager, Planning Solutions
**Excerpt:** Production Control simulation identifies roadblocks and overcomes challenges
**Content:**
[SmartFactory Production Control](/semiconductor/productivity-solutions/production-control/) is a capacity planning system for simulating manufacturing and planning operations. By replicating production activities in a simulation environment, the system identifies opportunities for improving work in process (WIP) movement, capacity utilization and throughput —all without disrupting factory operations. Avalign Technologies, one of the largest contract manufacturing organizations dedicated to the global orthopedics industry, solved some key challenges using the SmartFactory Production Control Solution. Among these were improvements in production schedule, on-time deliveries, and utilization of bottleneck work centers.
### Production control challenges
Avalign was experiencing challenges inherent to a high capex, made-to-order manufacturer, including customer dissatisfaction, equipment productivity issues, cycle-time increases, line imbalances, and increases in manufacturing costs.
- Lack of a robust finite and optimal production schedule
- No comprehensive mid-term and long-term capacity planning
- Limited “what-if” analysis capabilities to support continuous improvement
- Long time required to re-plan and re-schedule in coordination with pull-in and push-out requests
- Non-standard data across multiple sites that requires long data mining processes
### Improving KPIs with SmartFactory Production Control Solution
To overcome these challenges, Avalign implemented the SmartFactory Production Control Solution, which enabled Avalign to simulate the factory operations and foresee the roadblocks in the production schedule.
They were also able to integrate output from Production Control Solution with dispatching and scheduling solutions to generate a finite production plan. This allowed them to move from weekly planning, taking two to three days, to scheduling that takes less than one hour daily. This improved planner productivity by approximately 75%, allowing them to focus on multiple what-if scenarios and other planner activities.
Additionally, a high-speed Production Control simulation run with detailed modeling provided quicker and more accurate customer open order updates and a new delivery schedule. This reduced the customer order fulfillment response time from two to three days to a couple of hours with higher accuracy and improved on-time-delivery by approximately 5%.
Easy modeling simulation runs enabled scenario-based scheduling that improved machine utilization and line balancing. Avalign’s utilization of bottleneck work centers improved by 5-10 %.
Detailed reports and graphs helped identify bottlenecks and inefficiencies to optimize the plan before execution. This enabled them to achieve a more efficient work in process management and work order releasing mechanism. Whereas work orders previously were released in a fixed cadence, the process is now more dynamic and as needed with a more balanced WIP level.
They also achieved detailed mid- to long-term capacity planning by implementing Production Control solution, which uses AutoSched®, a robust simulation tool designed for complex planning.
Other significant improvements Avalign realized by using SmartFactory Production Control Solution are shown in figure 1, below.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/production-control-solution.png) Figure 1: Table of problems resolved by implementing SmartFactory Production Control Solution
### A move toward continuous improvement
Using SmartFactory solutions, Avalign was able to leverage a single platform for factory production and planning efficiency. They were able to focus on data integration, availability, and accuracy, as well as on business process change associated with automated solutions and to develop a continuous improvement mindset.
## What’s Inside
- [ Production control challenges ](#index2)
- [ Improving KPIs with SmartFactory Production Control Solution ](#index3)
- [ Added benefits ](#index4)
- [ A move toward continuous improvement ](#index5)
- [ FAQs ](#index6)
[SmartFactory Production Control](/semiconductor/productivity-solutions/production-control/) is a capacity planning system for simulating manufacturing and planning operations. By replicating production activities in a simulation environment, the system identifies opportunities for improving work in process (WIP) movement, capacity utilization and throughput —all without disrupting factory operations. Avalign Technologies, one of the largest contract manufacturing organizations dedicated to the global orthopedics industry, solved some key challenges using the SmartFactory Production Control Solution. Among these were improvements in production schedule, on-time deliveries, and utilization of bottleneck work centers.
### Production control challenges
Avalign was experiencing some challenges inherent to a high capex, made-to-order manufacturer: - Lack of a robust finite and optimal production schedule
- No comprehensive mid-term and long-term capacity planning
- Limited “what-if” analysis capabilities to support continuous improvement
- Long time required to re-plan and re-schedule in coordination with pull-in and push-out requests
- Non-standard data across multiple sites that requires long data mining processes
The challenges listed above increased levels of customer dissatisfaction, decreased equipment productivity, increased cycle time, line imbalance, and manufacturing costs.
### Improving KPIs with SmartFactory Production Control Solution
To overcome these challenges, Avalign implemented the SmartFactory Production Control Solution, which enabled Avalign to simulate the factory operations and foresee the roadblocks in the production schedule.
They were also able to integrate output from Production Control Solution with dispatching and scheduling solutions to generate a finite production plan. This allowed them to move from weekly planning, taking two to three days, to scheduling that takes less than one hour daily. This improved planner productivity by approximately 75%, allowing them to focus on multiple what-if scenarios and other planner activities.
*This improved planner productivity by approximately 75% enabling Avalign to focus on multiple what-if scenarios and other planner activities.*
Additionally, a high-speed Production Control simulation run with detailed modeling provided quicker and more accurate customer open order updates and a new delivery schedule. This reduced the customer order fulfillment response time from two to three days to a couple of hours with higher accuracy and improved on-time-delivery by approximately 5%.
*This reduced the customer order fulfillment response time from 2-3 days to a few hours---improving on-time delivery by 5%.*
Easy modeling simulation runs enabled scenario-based scheduling that improved machine utilization and line balancing. Avalign’s utilization of bottleneck work centers improved by 5-10%.
*Avalign's utilization of bottleneck work centers improved by 5-10%.*
Detailed reports and graphs helped identify bottlenecks and inefficiencies to optimize the plan before execution. This enabled them to achieve a more efficient work in process management and work order releasing mechanism. Whereas work orders previously were released in a fixed cadence, the process is now more dynamic and as needed with a more balanced WIP level. They also achieved detailed mid- to long-term capacity planning by implementing Production Control solution, which uses AutoSched®, a robust simulation tool designed for complex planning.
### Added benefits
Other significant improvements Avalign realized by using SmartFactory Production Control Solution are shown in figure 1, below.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/production-control-solution.png) Figure 1: Table of problems resolved by implementing SmartFactory Production Control Solution
### A move toward continuous improvement
Using SmartFactory solutions, Avalign was able to leverage a single platform for factory production and planning efficiency. They were able to focus on data integration, availability, and accuracy, as well as on business process change associated with automated solutions and to develop a continuous improvement mindset.
## FAQs
#### How did Avalign Technologies benefit from using SmartFactory Production Control?
Avalign Technologies improved planner productivity by approximately 75%, enhanced production scheduling, increased on-time deliveries, and improved utilization of bottleneck work centers.
#### What improvements in customer service did Avalign experience with SmartFactory Production Control?
Avalign saw a reduction in customer order fulfillment response time from two to three days to a couple of hours with higher accuracy, and an improvement in on-time delivery by approximately 5%.
#### How does SmartFactory Production Control aid in machine utilization and line balancing?
Through easy modeling simulation runs, it enables scenario-based scheduling that improves machine utilization and line balancing, with a 5-10% improvement in the utilization of bottleneck work centers.
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Semi
---
### [Enhance manufacturing efficiency with SmartFactory Unified Process Control](https://appliedsmartfactory.com/semiconductor-blog/quality/manufacturing-operations/)
**Published:** October 9, 2023
**Author:** Vishali Ragam, Global Product Manager, SPC
**Excerpt:** Explore AI-driven process quality improvement with SmartFactory’s UPC solution in this engaging article by Applied SmartFactory.
**Content:**
Chip manufacturing information is rich and complex, and bringing this information together has substantial benefits. Data variety, sources, quality, and volume are some of the characteristics which make this task challenging. SmartFactory has built a unified process control (UPC) solution that brings together in one platform the different principles of process quality, specifically pertaining to monitoring product. The unified platform takes data from multiple sources that speak a different language and, for the first time, transports them into composite data to have more insights into the factory.
We chose to build the solution on the Applied E3® equipment and process control platform, which has all the [ core capabilities](/blog/cim-solution/) and is something most customers already use. The resulting ecosystem provides models and linkages to E3 that make it possible to move to automated decision making (AI-enabled decisions) for process quality.
The UPC derives artifacts from many pieces of equipment rather than looking at data in a silo. This is key, since there are implications for process quality coming from each of those different artifacts, and looking at them holistically provides deeper insights. The solution brings together relevant data from multiple sources, looks at it in a combined fashion and interprets what happened, what needs to be done and how. Its interpretive vision identifies an accident as well as the specific, combined effects that led to the problem, then tells you what to fix and how.
SmartFactory’s unified platform was designed with only the required resources to provide insights, carefully filtering noise that wouldn’t have an impact on process quality. Importantly, the solution does not take a cookie-cutter approach. Because the models must be reliable and relatable to the individual semiconductor factory, they are designed one-by-one. The user can input information specific to the factory, as well as identify protocol for managing situations.
Take for example, a factory where many alarms have come from the same source in a short period of time. Each is fixed in turn, but the source continues to trigger alarms. In the fast-paced environment, manufacturers can’t afford to stop production to analyze this extensively. Fixing each alarm’s perceived cause is a band aid approach to get back to production, but it clearly isn’t working. In this case, the UPC does the work without interrupting production. It looks at the history of that source over several different shifts to see that it’s a recurring problem. The model gathers and interprets data across several shifts, looking at multiple factors that may impact process quality. It integrates the artifacts, reads relationships between them, and finds the root cause of the alarms, finally proposing a remedy.
In this way, manufacturers can make business decisions faster. Additionally, the model becomes a continuous improvement tool. Once it has identified the solution to one problem, it can move on to other process quality concerns to analyze combined data toward another solution.
This connectivity via a unified platform can help you unleash the full potential of your fab by harnessing the synergy of integrated tools and data to simplify operations and empower your teams.
## What’s Inside
- [ Our solution ](#index1)
- [ How does Unified Process Control work? ](#index2)
- [ AI-ready ecosystem ](#index3)
- [ Breaking down silos ](#index4)
- [ Solutions unique to each factory ](#index5)
- [ Fixing without interrupting ](#index6)
- [ Bigger picture ](#index7)
- [ Conclusion ](#index8)
- [ FAQs ](#index9)
Information created in the process of chip manufacturing is rich and complex, derived from several sources in the factory. Bringing this information together has substantial benefits. Data variety, sources, quality, and volume are some of the characteristics that make this task challenging. Here, we’ll look at how SmartFactory can help overcome that challenge.
### Our solution
SmartFactory has built a unified process control (UPC) solution that brings together in one platform the different principles of process quality, specifically those pertaining to monitoring product.
### How does Unified Process Control work?
The unified platform takes data from multiple sources that speak a different language and, for the first time, transports them into composite data to have more insights into the semiconductor factory. This integration at a core level across all process control systems requires:
- A standardized data structure, which is critical for advanced analysis and AI/ML applications
- Shared tools to help standardize our action and reaction to events
- A consistent UI which provides the same look and feel across applications
- Universal management to streamline the administration of the applications
- A standardized knowledge base that enables us to reuse expertise and lower the overall investment
- Architecture designed to scale as factories grow
(For more about the requirements and benefits of unifying process control, see our [blog](/semiconductor-blog/unifying-process-control/) on the topic.)
### AI-ready ecosystem
We chose to build our solution on the Applied E3® equipment and process control platform, which has all the [core capabilities](/semiconductor-blog/cim-solution/) and is something most customers already use. The resulting ecosystem provides models and linkages to E3 that make it possible to move to automated decision making (AI-enabled decisions) for process quality.
### Breaking down silos
The UPC derives artifacts from many pieces of equipment rather than looking at data in a silo. This is key, since there are implications for process quality coming from each of those different artifacts, and looking at them holistically provides deeper insights. The solution brings together relevant data from multiple sources, looks at it in a combined fashion and interprets what happened, what needs to be done and how.
Its interpretive vision identifies an accident and the specific, combined effects that led to the problem. It then tells you what to fix and how.
### Solutions unique to each factory
SmartFactory’s unified platform was designed with only the required resources to provide insights, carefully filtering noise that wouldn’t have an impact on process quality.
Importantly, the solution does not take a cookie-cutter approach. Because the models must be reliable and relatable to the individual semiconductor factory, they are designed one-by-one. The user can input information specific to the factory, as well as identify protocols for managing situations.
### Fixing without interrupting
Take for example, a factory where many alarms have come from the same source in a short period of time. Each is fixed in turn, but the source continues to trigger alarms. In the fast-paced environment, manufacturers can’t afford to stop production to analyze this extensively. Fixing each alarm’s perceived cause is a band aid approach to get back to production, but it clearly isn’t working.
In this case, the UPC does the work without interrupting production. It looks at the history of that source over several different shifts to see that it’s a recurring problem. The model gathers and interprets data across several shifts, looking at multiple factors that may impact process quality. It integrates the artifacts, reads relationships between them, and finds the root cause of the alarms, finally proposing a remedy. In this way, manufacturers can make business decisions faster.
### Bigger picture
The model becomes a continuous improvement tool. Once it has identified the solution to one problem, it can move on to other process quality concerns to analyze combined data toward another solution.
### Conclusion
This connectivity via a unified platform can help you unleash the full potential of your fab by harnessing the synergy of integrated tools and data to simplify operations and empower your teams.
## FAQs
#### What is Applied E3?
This advanced equipment and process control solution is a comprehensive factory automation software package designed to improve productivity and reduce costs in semiconductor manufacturing. Utilizing proprietary algorithms, the Applied E3 system can boost process capability by greater than 30%, reduce unscheduled down time, and shorten cycle time to achieve up to a 20% increase in overall equipment effectiveness. The Applied E3 system uniquely integrates all critical equipment automation and process control components to deliver the most flexible, user-friendly and powerful fab-wide Equipment Engineering System solution on the market today.
#### Where can Unified Process Control get its data from?
The UPC can bring together data from all process control domains, including Run-to-Run, Recipe Management, and Yield and Defect Management, among others.
#### How does Unified Process Control impact my team?
The UPC can provide shared access across team members, improving communication and collaboration. For example, engineers responsible for different aspects of production can more easily review combined data, rather than just data specific to their purview. This enables collaboration between different teams to develop a solution to an event.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Performance Pioneers: Factory Innovations](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Chris Reeves shares transformative strategies for boosting quality and performance in factories. Gain valuable knowledge from the forefront of manufacturing innovation.
**Content:**
#### Transcript
I’m Chris Reeves. I’m a Product Manager for Applied E3® Process Control Platform. E3 is a technology that really focuses on providing a fundamental connectivity layer for our process quality suite, which includes products such as fault detection, run-to-run, SPC, and an OCAP module known as Knowledge Advisor.
Applied SmartFactory represents a solution of softwares that are designed at improving our customers’ connectivity, improving our customers’ capabilities through automation. One of the key things I see about the Applied SmartFactory is the approach to have the same look, the same feel, and the same integration across all of our products. You know, one of the key features I see about the E3 platform is our interconnectivity of our process control modules and our extendability beyond just those modules.
One thing that we’ve noticed when talking with customers is a key requirement is the ability to share data and information, whether it originates in fault detection or SPC or run-to-run control. And being able to have and leverage that data across those modules really helps facilitate detection, it facilitates reaction, it really helps our customers to be much more efficient and take their process control environments to the next level. In terms of measuring the value, where our customers are truly focused on is how well their factories are performing.
And that’s manifesting itself through the throughput, the amount of material they can run through their equipment, the amount of scrap or excursions that are occurring, and essentially the overall cost of running a factory. And by having the E3 platform and the integrated solutions, they’re able to expedite their ability to detect things quicker, they’re able to make better decisions when reacting to those detection, and that, at the end of the day, helps them to reduce their costs and improve their factory performance.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi
---
### [Analyze impact of dispatching and scheduling Algorithms on factory KPI’s](https://appliedsmartfactory.com/semiconductor-blog/scheduling/dispatching-scheduling-algorithms-impact/)
**Published:** May 3, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** Use APF Fusion® to integrate dispatching and scheduling algorithms.
**Content:**
Typically, semiconductor manufacturing facilities implement 8 to 10 area-specific dispatching rules and 4 to 5 area-specific schedulers to improve equipment bottlenecks. The algorithms tend to have 5 to 10 parameters each, which can be configured for optimizing the performance of the system. The users tend to change these parameters several times per week.
Because it’s difficult to recreate complex logic in an offline environment, manufacturers conduct soft runs in the production environment to analyze the impact of dispatching and scheduling algorithms. Running this analyses in production, can result in downtime or negatively impact the factory moves for the duration of the testing period.
Companies use dynamic simulation capabilities to forecast weekly output from factories, identify bottlenecks, plan for equipment downtime, and set move target goals for areas. They are using simple basic dispatching rules, instead of the rules used in production and this results in generating several gaps between the production and simulation outputs. Figure 1\[1\] below summarizes the typical gaps observed in the online simulation at the lot-level. In this case, a gap represents the delta between an actual lot’s step count and a simulated lot’s step count, and that delta is greater than an allowable threshold over a period.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig1-min.jpg) Figure 1: Lot-by-lot gap comparison of simulation vs. production
To address these challenges, Applied’s APF Fusion module integrates dispatching and scheduling algorithms developed using Applied’ s APF Real-Time Dispatcher® (RTD) rules in production within our SmartFactory AutoSched® simulation model.
Our APF Fusion module enables manufacturers to reuse the production dispatching rules without requiring the engineers to use customizations in the AutoSched simulation module. Figure 2 shows the high-level architecture for APF Fusion capabilities.
The Fusion engine acts as a dispatcher for AutoSched. The key difference between Fusion and an APF dispatcher is that Fusion has been designed to use Autosched’s factory data in memory rather than data from a repository.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig2.jpg) Figure 2: Fusion Architecture
To create the dispatching rules for simulation and production, the following steps are required and are shown below in Figure 3. - You need to create separate “branches” of blocks that read input data from the appropriate data source. Then, use a Switch-in block to toggle and identify the branch of input data to execute when the rule runs. The branch that reads from the AutoSched model (if the rule is running in simulation) or the MES (if the rule is running in production)
- Because the AutoSched model schema is different than the MES data schema, the rule uses a function block to rename data elements from the AutoSched model and performs type conversions (if necessary) so that their names and types match corresponding data elements from the MES. The rule’s logic then performs the same operations, using the same input parameters, regardless of the data’s source.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig3.jpg) Figure 3: Creating rules with APF Fusion
The benefit of using the integrated dispatching and simulation solution is it allows manufacturers to proactively work within the production system environment with actual data as part of a continuous improvement activity.
### Benefits of our SmartFactory Integrated Dispatching and Simulation Solution
- Evaluate dispatch rule /scheduling policy changes without impacting production
- Determine the impact of KPI due to line down and other scenarios
- Increased confidence and reduced risk to production due to new changes
- Improve cost of ownership
- No need to use C++ extensions to model dispatching and scheduling policies
- Share rules between production and simulation
- Share KPI reports between production and simulation
- Reduce rule complexity by eliminating non-essential logic
- Get RTD training resources online, enabling manufacturers to experiment in a safe sandbox
**REFERENCE**
Figure 1 – \[1\] [Proceedings of the 2013 Winter Simulation Conference, AN INTEGRATED APPROACH TO REAL TIME DISPATCHING RULES ANALYSIS AT SEAGATE TECHNOLOGY, Gowling, Peterson, O’Donnell, Kidambi, Muller](https://dl.acm.org/doi/10.5555/2675983.2675864)
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [Common Data Model enables RAPID deployment for productivity solutions – Solutions (Part 2/3)](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
**Published:** February 6, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** Common data framework for rapid deployment of factory productivity and supply chain solutions
**Content:**
[ Part 1: Challenges ](/blog/rapid-deployment-part-1/)
[ Part 3: Dispatching and Reporting ](/blog/rapid-deployment-part-3/)
In today’s semiconductor factories, it’s become increasingly difficult and time-consuming to generate valid data for factory productivity solutions.
To address this gap, Applied Materials is developing a common data model using the Extract, Transform and Map (ETL) capabilities modules from Applied’s APF (Advanced Productivity Platform) software environment.
Figure 1 below shows steps involved in building the common data model schema
### Smartfactory productivity solutions components
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/step-involved-in-building-the-common-data-model-schema.jpg) Common framework from dispaching to automation — Built on Smartfactory Platform ETM, Common Data Model (CDM), EngineeredWorks®, Solution UI > Open Box Solutions
Applied solution leverages out of box APF adapters to integrate the data from various sources such as MES, MCS and other applications in the CIM solution.
Figure 2 shows the data intercepted from various solutions in APF repository
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/the-data-intercepted-from-various-solutions-in-APF-repository-.jpg)
Once the data is replicated in APF repository then it is mapped to the common data model schema using APF macros as shown in figure 3
### Extract, Transpose, and MAP(ETM)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/extract-transpose-map.jpg)
Once the data is transformed in the common data model format then it is ready to get used in various factory productivity solutions.
Figure 4 shows some of the snapshot of various tables
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/the-some-of-the-snapshot-of-various-tables-2.jpg)
Recently, Applied Materials has been using this approach to rapidly deploy Factory Productivity solutions within 6 months.
[ Part 1: Challenges ](/blog/rapid-deployment-part-1/)
[ Part 3: Dispatching and Reporting ](/blog/rapid-deployment-part-3/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Common Data Models, Semi
---
### [The potential to transform reporting with FactoryView and AI (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
**Published:** June 25, 2025
**Author:** Samantha Duchscherer and Michael Frenna
**Excerpt:** Transform factory operations with an advanced decision support system
**Content:**
[ Part 2: FactoryView and AI ](/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
## What's Inside
- [ Defining FactoryView ](#index1)
- [ Real time monitoring ](#index2)
- [ New reports without the need to code ](#index3)
- [ Access to best known methods ](#index4)
- [ Change management ](#index5)
- [ Deployment and integration ](#index6)
In this blog, Sam sits down with Michael to explore how FactoryView transforms factory operations through real-time monitoring, standardized reporting, and actionable insights. From simplifying decision-making to preparing for seamless integration with existing APF products and solutions, this conversation highlights why FactoryView is more than just a reporting tool—it’s a catalyst for smarter, faster, and more aligned manufacturing operations.
Sam: As always, I want to talk about AI. However, let’s just begin the discussion by explaining what FactoryView is and how it benefits manufacturers.
Michael: Sure. FactoryView is part of our SmartFactory Reporting Solution. It’s a real-time visualization of factory operations and KPIs, used to monitor important metrics that the manufacturing organization is concerned about and align planning and scheduling goals across the organization.
Ideally, this should be a decision support system for daily operations to make sure that they are effectively utilizing their resources and addressing areas that are impacting the fab, as well as identifying bottlenecks.
Sam: I see; so is it a preset reporting solution, or do users define what they’re viewing?
Michael: We have a preset definition of what they’re viewing. However, the customer defines which areas are most important to address in each shift based on some predetermined logic of where their bottleneck is in the factory. Different factories have different methods for identifying this condition.
The reporting then has a user focus. The high-level view is meant more for the manufacturing manager or director and then each of the module areas are for the section managers.
Sam: And could you define what exactly “real-time” means in the context of this application?
Michael: Real time just means that as transactions are happening in the factory’s MES those transactions are being replicated and displayed in the FactoryView application. The KPIs that are tied to those factory transactions also are changing as the transactions are occurring in the MES. For example, the movement of a lot from one step to the next would be considered a transaction; the logging of a tool of an equipment down would be a transaction, so would the logging of an equipment back up.
Any of the reports that have to do with real time status of tools as well as factory metrics having to do with movement of material in the factory would be impacted by the real time nature of this application.
Sam: Everything you’ve shared sounds incredibly useful. But let’s be honest—how is this really different from what manufacturers or industrial engineers (IEs) are already doing with custom reports in other software?
Michael: That’s a great question! It’s key to understand that this doesn’t require an industrial engineer, IT, or developer to create the actual dashboard and maintain it. FactoryView comes already developed, so the industrial engineer or IT can use it more as a tool to make decisions and help align the manufacturing organization. It takes the reporting aspect out of the IT and IE role to enable them to focus more on using that information to make better decisions for the factory.
I will also say, most customers do have something in terms of factory reporting; they all need to understand at a high level what’s going on in their factory and are driving towards a goal. But creating these reports is cumbersome for the staff who do it—it takes a long time for them to develop and maintain them. Oftentimes, these reports also are siloed across various organizations and there are gaps. For operational reporting, there might be several reports that have the same factory KPIs but are calculated differently. Ultimately, there are certain reports that factories don’t have that FactoryView does, and there’s an advantage in having that single source of truth for factory operational reports.
Sam: So we’re standardizing, scaling and giving them reports they didn’t have before. However, let’s dig a little deeper—what do teams really gain with FactoryView that they wouldn’t get from their existing tools or custom-built dashboards?
Michael: Our solution is built on years of experience deploying custom reporting solutions for customers, so we’ve been able to gain a lot of semiconductor-specific requirements. Often, what we’ve seen when we put this in front of customers is that they gain new insights, such as factory KPIs they didn’t think to track that may have come from a best known method (BKM) from another manufacturer in the industry. When they’re part of the roadmap for this reporting solution, they can pick up on the kind of industry BKMs for reporting instead of relying solely on the metrics they’ve been using.
Sam: Well, you’ve definitely won me over on FactoryView. Let’s now talk about the real-world side of things—what’s the most challenging part of getting ready for an implementation like this? What should manufacturers be thinking about ahead of time to set themselves up for success?
Michael: I’d recommend engaging in some change management. There’s a certain way that the manufacturing organization has been looking at key metrics in their factory for many years, and this might change that view. Their daily stand-up meeting may change a little bit and may incorporate this report, and that will take some learning on how to use the application. There’s definitely an early change management cycle that goes on because of this.
In addition to change management, I would also say an important early step is to verify the metrics. With every deployment, you need to gather all the MES data and make sure the application works for the customer, ensuring that each of the metrics aligns with the way that the customers have defined them.
Sam: And to wrap things up—would you say that one of the biggest enablers of successful change management is how easily this solution integrates with existing systems?
Michael: Yes, since it’s built on the same common data model as all our EngineeredWorks® solutions, many of the inputs and the factory KPIs that we are producing in this solution would be shared across the other solutions. For instance, we would be calculating the same throughput statistic for scheduling as we would in FactoryView. When a tool is up in FactoryView, it would also be considered up in the scheduling solution and we would be considering the same tool list as the scheduling solution.
When you do a deployment of the reporting solution, it actually sets you up quite nicely for a scheduling solution deployment because many of the key pieces of data that you need for the reporting solution are also needed in scheduling. It cuts down on deployment time.
### Up next
In the next article, Sam and Michael discuss how AI technology can bring added advantages to FactoryView.
## About the Authors
Samantha Duchscherer, Global Product Manager
Samantha is the Global Product Manager overseeing SmartFactory AI™ Productivity, Simulation AutoSched® and Simulation AutoMod®. Prior to joining Applied Materials Automation Product Group Samantha was Manager of Industry 4.0 at Bosch, where she also was previously a Data Scientist. She also has experience as a Research Associate for the Geographic Information Science and Technology Group of Oak Ridge National Laboratory. She holds a M.S. in Mathematics from the University of Tennessee, Knoxville, and a B.S. in Mathematics from University of North Georgia, Dahlonega.
Michael Frenna, Global Product Manager, Workflow Automation and Factory Analytics
In his current role, Michael drives road map initiatives for Workflow Automation and Factory Analytics offerings to meet the growing needs of Semiconductor customers worldwide. Prior to his current role, Michael honed his expertise as an Industrial Engineer in the semiconductor industry, where he helped drive digital transformation and I4.0 initiatives for a 150mm/200mm front-end fab. With a passion for technology and a commitment to driving innovation, Michael continues to work with customers from around the world in advancing manufacturing capabilities and operational efficiencies.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [2023 PROMIS® User Group](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/2023-promis-user-group/)
**Published:** November 17, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Introducing the new PROMIS on Linux!
**Content:**
#### Watch Webinar
### Watch a replay of the user group
Please complete the form to watch the user group replay. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [UMC describes how they achieved manufacturing operations excellence](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
**Published:** October 18, 2021
**Author:** YY Chen
**Excerpt:** UMC integrates real-time dispatching, full automation workflow, MES 300works® and more.
**Content:**
UMC, a leading global semiconductor foundry company, needed to build a collaborative MES system for their multi-fab operations. The decision was made to deploy SmartFactory MES 300works to achieve numerous operations advancements, including productivity and product quality improvements plus an increase in yield and throughput, and a reduction in cycle time.
The video discusses how UMC used SmartFactory automation products and solutions to build, run, and manage their manufacturing operations efficiently, enabling the company to achieve a fast ramp to high-volume manufacturing by resolving quality issues sooner.
#### Transcript
I am Y Y, Director of CIM at UMC. As one of the leading semiconductor manufacturers of advanced IC, UMC has 11 manufacturer fabs, including 12x in Xiamen, China. Our business operation environment is facing similar challenges that other semiconductor manufacturers have.
With dynamic requirements, UMC needs to manufacture quality products at reduced cost and meet customer commitments in a timely manner. At UMC, we use a price 300works MES, which has helped us to achieve the number of manufacturer operation excellence through improved productivity, product quality, yield, throughput, cycle time, on-time delivery meeting customer commitments, rapid expansion of manufacturing capacity to meet customer demand. We all know that companies would like to get cost advantages by achieving economy of scale.
So every company continues to expand their fab capacity by building up new fab modules and produce quality wafer at reduced cost per unit. To run multiple fabs efficiently, the challenge we have is how we build a collaborative MES system for multi-fab operation.
1\. We need a collaborative MES solution enabling visibility and information consistency across multiple fabs.
2\. These multi-fabs should be interconnected by MES system so lead load can be seamlessly transferred between fabs. At UMC 12A site, two FABs P1-4 and P5-6 have all these features so that they can operate together seamlessly as one fab. Apply 300works is a flexible solution that offers application module to support multiple fab operation requirements.
If we want to transfer load between multiple fabs seamlessly, all MES system should have the same process flow information across all of the fabs. Central Modeling Repository enables product flow consistency across multiple fabs. This solution can guarantee load to run at correct step across all fabs simultaneously.
With 300works, we created cross-fab transaction to handle load and data transfer between multiple fabs enabling web status visibility across the board. With Applied 300works MES, all 12A P1-4, P5-6 FABs successfully achieve collaborative cross-fab operations because it enables visibility to load status across multiple fabs. We achieve efficient and seamless cross-fab manufacturing operation through real-time visibility, efficient integrated dispatching, tracking and optimization of cross-fab manufacturing.
With interconnected fabs and cross-fab MES function, distance transportation can be predicted and managed easily. This has helped us minimize manufacturing cycle time and increase wafer output. We use Applied Material automation product and solution to build, run and manage our manufacturing operation efficiently.
UMC-CIM solution consisting of 300works MES, APFRTD, AMA and WINSEX are capability that enables UMC to reduce time to first silicon, fast RAM to high volume by resolving quality issue in a timely manner and running high volume operation with excellence with applied integrated CIM solution. With applied commitment to continue software improvement in line with technology and industry trend such as Big Data, Industry 4.0, positions both of us for success.
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Newly Released, Popular, Semi
---
### [Applied pathway for faster automation – full-auto readiness (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation-part-2/)
**Published:** July 5, 2022
**Author:** Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®
**Excerpt:** Driving MES 300works® deployments to achieve a fully automated CIM system
**Content:**
For semiconductor frontend manufacturers, having a goal of achieving full automation is a critical factor for leading and supporting a successful fab with required automation capabilities.
However, the path to reach this goal varies and depends on numerous factors. Several risks prevail in this process, depending on customer management and whether the right partnerships are developed for journeying on the path together.
When customers successfully achieve their first MES deployment with basic automation and can run wafer processes, then it’s time to establish a vision focused on increasing factory automation capabilities with the goal of closing in on full automation in a timely manner.
### What Is Full Automation?
*Full automation*, also known as full-auto or lights out manufacturing, enables factories to process products automatically with minimum human interaction1. Full automation enables fabs to optimally use data and computer systems to enhance productivity.
The following diagram illustrates the concept of full automation, showing the flow or relationship among making decisions, transporting material, learning, and reacting to exceptions.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/07/figure-1-full-automation.png) Figure 1. The concept of full automation
We believe it’s critical for manufacturers to have a vision of achieving full automation—and as early in the process as possible. Why? So manufacturers can work in parallel to (1) deploy various factory applications to increase product quality and (2) maximize throughput with better integration of these applications. To achieve full automation in the appropriate time, manufacturers must progress through the following activities (summarized in Figure 2): 1. **Design automation scenarios.** Factories have different needs and conditions that they must manage, such as factory space constraints and tools with limited online capabilities. Such conditions require that factories carefully consider and design automation scenarios, so they work with multiple applications like dispatching, run-to-run control, fault detection and classification, alarm management, recipe management, and others depending on factory automation scope.
2. **Refine operation capabilities.** The timeline for implementing full automation involves refining MES execution scenarios based on processes and equipment that are continuously being added in the factory. Factories will continuously change to increase production output, so it’s inevitable to change manufacturing scenarios, including equipment form factors, integration with the automated material handling system, and so forth. Change is constant in a fab, particularly after deployment because customers are continuously looking to improve operational efficiency.
3. **Deploy automated capabilities.** Following design and refinement, factories can start deploying automation capabilities with full automation scenarios to implement no or minimum human intervention.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/07/figure-2-automation-path.png) Figure 2. Activities for achieving full automation
### Use Case: Common Challenges with Advanced Automation
Part 1 of this blog highlighted a use case of a frontend manufacturer who accomplished basic automation in 90 days. This same manufacturer wanted to achieve advanced automation as soon as possible, but even after improving their automation capabilities during this time, they were still concerned about avoiding countless errors if they overlooked an integration point in some area. Other challenges faced by this manufacturer included: - Building a company-wide view of *full automation*
- Lacking or not having enough automation knowledge, particularly with integration
- No expertise on how to improve
- Limited view on how to prioritize automation tasks
### Partnering for Advanced Automation
Applied can be a valuable partner for consulting on automation concerns, particularly on matters related with execution, which integration to implement first, which processes to prioritize to avoid setbacks, and so forth. With Applied, what value can customers expect? - Complete full-auto readiness in 6–9 months
- Production ramp from basic automation to semi automation to increase yield and output
- On time readiness for full automation
Figure 3 shows how Applied SmartFactory automation capabilities align with various levels of automation with the target to achieve full automation capabilities.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/07/figure-3-automation-journey.png) Figure 3. Capabilities for journeying from manual to level 2 automation
Deploying an MES, together with automation applications following a systematic and experienced approach, is provided through Applied’s proven solution. This solution is built on expertise gained through many deployments over the years. Applied SmartFactory MES 300works is market-proven for achieving fast MES deployment in 90 days. The solution enables customers to execute in their factory with fully automated capabilities within a year.
**REFERENCES**
\[1\] Krishnaswamy, S., Hanny, D., & Napiah, J. (n.d.). Challenges and strategies to achieve full automation in semiconductor assembly and test. Semi.org. Retrieved June 29, 2022, from
[ Part 1: MES deployment ](/blog/faster-automation/)
Ready to contact us to learn more about our MES deployment methodology?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Applied pathway for faster automation – MES deployment in 90 days (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
**Published:** July 5, 2022
**Author:** Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®
**Excerpt:** Deploy SmartFactory MES 300works® in 90 days: rely on experienced team and proven process
**Content:**
For new semiconductor fabs, traversing the path of factory automation is complex in even the best of circumstances. For example, configuring an MES and modeling complex processes can be overwhelming. This complication is compounded if manufacturers rely on IT-centric companies with little or no semiconductor experience for implementation. In addition, fabs frequently fall behind their startup timelines because they don’t commit the experienced resources required to install and configure automation software systems early enough in the process.
If you’re responsible for deploying an MES for a greenfield fab, are you experiencing similar challenges? Are you meeting required milestones for achieving first wafer production? To help new 300mm fabs on their journey to increasing factory automation, this blog highlights the path to achieving a successful MES deployment. It focuses on the first steps in this process—setup and basic readiness—to support first wafer production within 90 days.
### Meeting Milestones to Stay Competitive
For new semiconductor manufacturers, it’s critical to choose a proven automation software solution that (1) meets the demanding technical requirements of launching a new fab and (2) achieves key production milestones, such as first silicon and production ramp. No room exists for missing milestones in a successful production ramp. Because of this constraint, it’s critical to carefully manage every automation software system deployment so it supports production ramp requirements. As shown in Figure 1, among the most important milestones on a new fab’s path to competitiveness with automation are: 1. **Getting up and running**. This is accomplished by setting up and validating the minimum factory automation capabilities not requiring automation.
2. **Basic readiness**. To support first wafer production, fabs must implement basic automation to run automated data collection with statistical process control (SPC), manual dispatching and tracking, and equipment automation.
3. **Increased yield, quality, and throughput**. To realize these KPIs, fabs must increase their factory automation capabilities by further integration with advanced process control (APC), fault detection and classification (FDC), dispatching, and material control systems.
4. **Maximized value**. To maximize value, fabs must continually refine these automation capabilities (for example, by tuning dispatching scenarios based on scheduling inputs and automating MES scenarios).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/automation-competitiveness-milestone.png) Figure 1. How to achieve automation competitiveness milestones
### Getting Up and Running
Among the key tasks in getting the automation software up and running for first wafer production are: - Installing and configuring the MES
- Automating equipment
- Integrating with SPC
- Configuring equipment maintenance
Figure 2 highlights the key software systems that must be configured and integrated to achieve a successful ramp.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/key-automation-software-systems.png) Figure 2. Key automation software systems requiring configuration and integration for a successful ramp
### How Can SmartFactory MES 300works Help?
With [SmartFactory 300works](/semiconductor/manufacturing-execution-solutions/300works-full-auto/), it’s possible to get up and running with basic automation, which enables operators to control when wafer processing starts, eliminating the need for manual track in and track out. And you can enable support for initial wafer starts in only 90 days.
How is this accomplished? It’s done with our proven deployment plan and systematic, step-by-step deployment methodology. With over 30 years of “hardened” experience in semiconductor factories, our deployment teams are adept at getting fabs up and running on schedule while minimizing deployment risk using the following (see also Figure 3):
- Battle-tested **deployment methodology** and **resources**. With SmartFactory 300works, fabs can tap into a deployment team with knowledge on what works and what doesn’t work—some equipment, for example, may not be automation ready and require special or unique scenarios. In such cases, the team can consult with customers on making the equipment ready for automation.
- Pre-defined process **modeling templates**. These templates provide a knowledge base of lot and carrier naming rules, equipment processes, and so forth.
- Proven deployment templates based on standard **manufacturing scenarios**. This enables fabs, for example, to access resources about different equipment types and operating scenarios.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/formula-for-successful-mes-deployment.png) Figure 3. Keys to rapid MES deployment
### A Case in Point
To illustrate the value of a proven deployment methodology, a new semiconductor frontend manufacturer faced many of the challenges discussed earlier. In the beginning of their automation project, the company kicked off their effort with only a few experienced resources. As such, it was hard knowing what automation capabilities needed completion, when they were needed, and during which phase of the fab life cycle (see also [Bringing production reality closer to target](< /blog/bringing-production-reality-closer-to-target/?hilite=bringing+production+reality>)). As the level of automation increased—from basic to advanced—concern increased. Specifically, the process of continual tool installation required automation and testing with manufacturing scenarios, along with a way to encompass diverse automation integration. This challenge was overwhelming to the manufacturer. To help with these issues, an Applied Materials service team provided a solution with pre-defined modeling templates and an experienced deployment method. The solution included deployment of [MES](/semiconductor/manufacturing-execution-solutions/300works-full-auto/), [maintenance management](/semiconductor/manufacturing-execution-solutions/maintenance-management/), [dispatching](/semiconductor/productivity-solutions/dispatching-and-reporting/), [FullAuto ](/semiconductor/productivity-solutions/fullauto/)with [Activity Manager](/semiconductor/productivity-solutions/activity-manager/)®, [material control](/semiconductor/manufacturing-execution-solutions/material-control/), [run-to-run control](/semiconductor/process-quality-solutions/run-to-run-control/), [fault detection](/semiconductor/process-quality-solutions/fault-detection/), and [recipe management](/semiconductor/process-quality-solutions/recipe-management/). The Applied team completed basic readiness in 3 months and advanced automation in 1 year, followed by a couple of months of post tuning for optimization. As a result of this deployment effort, the customer was on the path of meeting their high-volume production targets.
### Next Steps
Successfully deploying automation software systems to support manual operation and first wafer production is only the first step in the journey to moving to a fully automated fab. But this journey can be worth the effort with the help of an experienced team to provide proven deployment and modeling templates, as well as the right methodology. In our next blog, we’ll discuss the next steps on this journey, identifying priorities to achieve advanced automation readiness.
[ Part 2: Full-auto readiness ](/blog/faster-automation-part-2/)
Ready to contact us to learn more about our MES deployment methodology?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular, Semi
---
### [Using plug & play Spares and ERP modules with maintenance management lowers integration costs, reduces complexity, and improves OEE](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
**Published:** March 7, 2022
**Author:** John Robinson
**Excerpt:** The right parts at the right tool at the right time
**Content:**
Today, a typical semiconductor 300mm front end fab may require thousands of process and metrology tools to build up a wafer die into an impressive and flexible device component. Each of these tools is incredibly complex and very specific in nature and each of these together must be orchestrated carefully to ensure overall equipment effectiveness (OEE).
### Millions of Parts
To illustrate the maintenance & spare parts complexity, consider the photolithography process. At the photomask disposition step, masks used to expose film at Litho must be carefully inspected for defects under scanner-like conditions. The Zeiss AIMS Inspection tool is one example of this. For this specific tool, there are over 4,500 subsystems and 64,000 individual parts from 134 different suppliers. This is an incredible array of parts and a monumental management challenge—not only with the supply chain but also with the maintenance and effort involved with associating parts and part numbers (P/Ns).
### The Right Part at the Right Time
To manage this complexity, fabs must ensure parts availability. For all the thousands of tools and millions of spare parts, many of the most needed or replaced parts are available in-house, either within the fab or at a short distance nearby where parts are housed and ready for use in a local “Stores” warehouse. Other longer lead time parts are shipped and ordered as needed from OEM and 3rd party suppliers.
All this part complexity contributes to the OEE of an individual tool because parts and P/Ns must be associated with maintenance work done on the tool. When a maintenance work order is planned or triggered for a tool in a fab, the required spare parts must be available and associated with that work order. Given the risk of not having the right part at the right time for maintenance, a need exists to efficiently manage the association of P/Ns to maintenance work orders in a way that reduces complexity and ensures the right part at the right tool.
### The Exchange of Part Information
To illustrate this part association process, figure 1 shows the flow of parts during staging and maintenance phases, divided into physical and logical systems. With physical systems, shown at the bottom, parts move from actual suppliers, to warehouses, and then to tools. To facilitate the automation management of spare parts to maintenance work orders we show the necessary logical flow as well, in which a massive volume of spare parts inventory, typically maintained by an ERP system, must exchange P/N information with the maintenance management system. This overlap and exchange of data between these two systems requires careful coordination and system integration to ensure the right part at the right tool for maintenance.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/the-flow-of-parts-through-various-lifecycle-phases.png) Figure 1: The flow of parts through various lifecycle phases, divided into logical and physical systems (from suppliers and tools to ERP and maintenance management applications)
Applied Materials has a well-known maintenance management capability that is built on Xsite® technology, which is used to efficiently automate maintenance schedules and track tool maintenance performance based on SEMI E10 states. This tracking ability provides a means of measuring OEE in terms of MTBF and MTTR metrics, which are captured automatically during maintenance when using the Xsite technology.
### What Customers Have Told Us
To enhance this maintenance management capability, we’ve worked closely with our customers to identify the key challenges which arise from the integration of spare parts to maintenance.
1. Automating and managing **spare parts association** to maintenance work orders
2. Reduce system complexity by allowing the P/N to move between these two systems
3. Providing **faster-out-of-box integration** with the ERP system
With these three customer priorities in mind, we have released two optional modules, Spares and ERP, both of which are available today with maintenance management. Figure 2 highlights both these modules in the Xsite technology framework.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/the-new-spares-and-erp-modules.png) Figure 2: The new Spares and ERP modules, shown in orange, are available with other optional modules, all of which plug and play with the Xsite technology core
### What Do These Modules Do?
The Spares module is based on the well-known INV module and does the following: 1. Associates work orders to P/Ns (both serialized and consumable parts)
2. Consumes spares during PMs
The ERP module: 1. Standardizes the data dictionary and Server-Side Rules (SSRs) for fast out-of-box integration with ERP
2. Allows P/N tracking history and queries
3. Ensures P/N consumption and returns to ERP
### What are the Benefits in a Semiconductor Fab?
Essential benefits of these modules for manufacturers include:
1. **Data traceability** (P/N association and usage counts)
2. **Improved MTTR** by providing the right part at the right time through P/N to work order association, which reduces maintenance down time
3. **Lower ERP integration cost** by providing standard touch points and simple SSR configuration
4. **Reduced complexity** — P/Ns move between systems and do not need to exist in both places
5. **Improved OEE**—spares outliers can be identified because P/Ns can be queried and associated to out-of-bounds MTBF metrics
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular
---
### [The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Overcoming Roadblocks (Part 3 of 3)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
**Published:** February 15, 2022
**Author:** Joe Napiah
**Excerpt:** Organization readiness, data, equipment, factory layout, material handling….do these roadblocks sound familiar? Watch this video (part 3 of 3) to get tips from the experts on how to move forward in your journey to full automation.
**Content:**
[ Part 2: SmartFactory Roadmap ](/blog/assembly-test-part-2)
Learn strategies for mitigating roadblocks in this video series, featuring The Road to Full Auto in Semiconductor Assembly Test Manufacturing (part 3 of 3).
## Transcript
Welcome to the third video in our series on Full Auto and semiconductor assembly tests. In this video we will discuss the roadblocks to achieving Full Auto and strategies to mitigate them. So what are the roadblocks to achieving Full Auto? First, the organization itself can be a roadblock if it lacks a Full Auto vision and executive buy-in.
Next, data can be a roadblock. This could mean not enough data or too much data.
Third, legacy equipment can be a roadblock.
We discussed this briefly in our first video. Next, the factory layout can be too complex or ill-suited for Full Auto. And finally, material handling challenges.
Let’s dive a little deeper into each of these roadblocks now. Your organization needs to have a vision for what it needs and expects with lights out Full Auto manufacturing and how it can be implemented. What processes could be handled via automated execution and which really need a human touch? How can your equipment know what lot is which and how will you manage the equipment recipes? Have you defined control limits for your equipments and corrective actions for when KPIs go out of those limits? Consider how you can improve your supply chain systems in a lights out Full Auto context.
If you use or implement a digital twin, consider how its usage may be changed or improved. Consider how lights out manufacturing and the right data could enable self-learning. These are just a few examples of what your organization could consider in its Full Auto vision.
But a vision without executive buy-in might never see the light of day. It is critical that your organization’s executives have buy-in and budget for lights out Full Auto. What about roadblocks with respect to data? Smart manufacturing is enabled with data, the right data.
What data do you need to automate your equipments and processes? What is the right data to measure your KPIs? Does any legacy equipment need to be retrofitted to enable integration, perhaps by adding sensors and small computers like Raspberry Pis? What data is needed to integrate all your enterprise applications and can your network infrastructure handle all this data and if not, what needs to be upgraded? Consider the trade-offs between low-cost storage like an on-prem or off-prem cloud and high performance such as a solid state SAN where appropriate. Again, decide what data is critical to automate and measure your processes, how to capture it, and how you can store it, balancing cost and performance. We mentioned in prior videos that legacy equipment presents its own challenges for assembly test facilities.
We want to integrate to equipment not only to capture valuable data but also to automate a lot of processing activities such as recipe selection, tracking in and out lots, and running those jobs. In an ideal scenario, all factory equipment would be compatible with the SECS/GEM standard protocol, but we are not in an ideal world. You may have critical factory equipment that has to connect via OPC/UA, TCP/IP, or web services and SmartFactory Equipment Automation or EA is your solution.
EA has various adapters allowing us to integrate to this legacy equipment, enabling your factory to realize higher levels of automation. Factory layout. Simulating a factory layout can have a lot of benefit, especially when building a new factory.
Using SmartFactory simulation, your organization can plan for maximum factory productivity before you even break ground. Optimize layout of new factories, explore what-if scenarios, understand and visualize dependencies between components, determine effects of variability and unforeseen events, determine system requirements, and identify constraints. So measure twice and cut once, and when in doubt, simulate.
We’ve mentioned in prior videos that non-standardization is a big roadblock to automation and assembly test. The Semi-Industry Association has a task force to work on that problem. Semi-ABFI is the Semi-Advanced Backend Factory Integration Task Force.
That group’s mission is to create new standards for assembly test facilities to help enable a path towards Full Auto. Google Semi-Smart Manufacturing Standards and Semi-ABFI to learn more. Material handling is arguably the last and highest hurdle in the road to Full Automation and assembly test.
In 300 millimeter wafer fabs, we benefit from standardized FOUPs and FOSBs for handling the wafers. In the top left, we see some carriers used in a wafer fab and bumping facility. In semiconductor backend, there is much less standardization.
In the midterm and long term, the Semi-ABFI task force should be aligning on standards to mitigate such problems. In the short term, your facility should determine, as best as possible, standard magazines, trays, and boards to be used across all sites. The more you standardize, the lower your automation hurdle will be.
Now, how do you move those standard trays from point A to point B? That’s where automated transports and an Automated Material Handling System, or AMHS, comes in. This could come in the form of Automated Guided Vehicles, AGV, Rail Guided Vehicles, RGV, and Overhead Hoist Transport, OHT. Each of these options has their own pros and cons.
An OHT is generally fastest and does not take up floor space, provided your factory has the height to accommodate them. AGVs and RGVs may be a good alternative, but of course will take up valuable floor space. The potential return on investment might compel your organization to implement automated transport.
Consider the potential increase in factory output and yield, and reduction in labor cost and human errors. Finally, to manage all these automated transport systems and material types, like trays and magazines, use Applied SmartFactory Material Control, also known as Class MCS-5®. This solution will integrate multiple AMHS providers into a single solution, and once implemented, does not require factory downtime to implement changes.
That brings us to the end of our three-part series on Full Auto and semiconductor assembly test. In the first video, we discussed today’s manufacturing challenges. In the second video, we defined Full Auto and its role in addressing those challenges.
And finally, in this video, we discuss roadblocks to Full Auto and how to mitigate them. Let’s wrap up. Full auto is required to stay competitive in assembly/test, and some leading edge assembly/test companies have realized this and have made strides towards Full Auto. Smart capital investments can mitigate roadblocks and gaps for Full Auto. Formal industry standards and cooperation can lower costs and accelerate the path to Full Auto. Lastly, it’s time to make the jump, so contact us to learn more about how Applied SmartFactory can solve your high-value problems. Thanks for tuning in.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, The Road to Full Auto in Semiconductor Assembly Test Manufacturing
---
### [Improving operational efficiency through better data visualization](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
**Published:** September 5, 2022
**Author:** John Robinson
**Excerpt:** Make easy, consistent, and visually appealing charts for data-driven decisions using SmartFactory Material Control and APF Reporter
**Content:**
In my former roles as AMHS Manager and Automation Technology Development Leader, I’ve sat through fab “Ops Review” meetings where each module owner is responsible for highlighting relevant issues impacting fab operations. In those meetings, while working at three different semiconductor companies, I found a common link between these different fabs—a link pertaining to *the consistency of data visualization.* Several commonalities exist, including a fab dashboard for 30 days showing moves per hour (MPH), delivery time, alarm Paretos over time, and storage utilization ordered by bay.
In this blog I focus on the 30-day AMHS dashboard report. The idea is on a single chart—30 days’ worth of trends, commonalities, and irregularities are communicated at-a-glance. Figure 1 shows the typical dashboard I’ve observed at most fabs.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure1-30-day-dashboard.jpg) Figure 1. A typical 30-day trend dashboard showing daily delivery time and move counts
The dashboard in Figure 1 consists of x, right, and left axes, explained next.
- The bottom **x-axis** shows the time under review, in this case a 30-day trend of 24-hour movement statistics.
- The **right axis** shows the average and 95th percentile delivery times achieved by eliminating the outliers (the top 5% times). This is represented in the two-line charts and is the bread-and-butter KPI metric for AMHS optimization. It is a lagging indicator of how efficient the storage optimization and move dispatching capability may be in the factory. Naturally, the focus is drawn to the outliers where delivery time is trending higher. These trends usually require an explanation to management in an Ops Review. Outliers are sometimes tied to a new tool or AMHS bay coming online and usually indicate the need for better organization of up-stream storage locations or improved scheduling logic to ensure material is stored closer to the tool, which leads to shorter delivery times.
- The **left axis** shows the total moves per 24 hours (MP24) using a stacked chart representing three move types: stocker-to-stocker, stocker-to-tool, and tool-to-tool. The stack total represents total moves within a 24-hour period. The stacked chart is interesting data to visualize because this is where we can glean clues of move type trends over time. For example, some days a rush to storage is evident, while on other days there is a greater emphasis on tool moves. These trends are typically aligned with factory-specific milestones that can be highlighted as required.
It’s important enough to explain these chart elements—MP24, average DT per day, and trends over 30 days—because then can we realize the value of it. A fab manager, for example, might wonder why on the **19-Sep** mark that the average DT spiked compared to other days, and here you can answer your Ops team with specific reasons, such as a new product introduction (NPI), a run-on at Wafer Starts with new test wafers, or a new bay coming online. Often the gap between the 95th percentile and the average delivery time can also indicate that on that specific day, a bottleneck likely occurred, or some odd disruption triggered this event, which is seen in the day-over-day trend.
If we can agree this chart has value and is common in most Ops Reviews, I will next show how we create this chart in CLASS MCS 5® and then visualize it using APF Reporter.
### Step 1 – Analysis of a Move
We need to first define what a move is and have a clear understanding of all the elements that contribute to a move from the AMHS perspective. Figure 2 shows a breakdown of the anatomy of a move in a 300mm semiconductor factory—from first requested to transfer complete.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure-2-move-anatomy.png) Figure 2. Anatomy of a move and event triggers
In Figure 2 the **Delivery Time** is the amalgamation of several events occurring, most notably the sum of assign-wait, retrieve, and delivery times. The other key point here is the definition of a move. A move begins with the MES move **Requested** and ends with the overhead transport (OHT) event of **Transfer Complete**. It’s important here to point out that a stocker-to-tool move will consist of one macro-**Transfer Complete** move (from the MES perspective), which simultaneously means that we will have two micro device complete moves (one from the stocker, one from the OHT). Distinguishing between MES moves and device moves is key to how we store this information in MCS statistics tables.
### Step 2 – Data Organization
Here then is the secret sauce to all of this—the data organization. The CLASS MCS 5 data storage structure, illustrated in the anatomy-of-a-move in Figure 2, is all inclusive into one single table called **SCARMOVE\_SUMMARY**. This table represents the infusion and feedback from our customer user groups, where we achieved alignment on a single storage organization strategy. The table looks something like the one shown in Figure 3.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure3-scarmove.png) Figure 3. Sample SCARMOVE SUMMARY table
This table identifies all the relevant elements of a move: the MES request time, vehicle assign time, arrival time, delivery time, command ID, and so on. Factory data analysts who need to build this type of chart will quickly realize the value. A single table to represent all data in the anatomy of a move is a unique accomplishment of SmartFactory Material Control (CLASS MCS 5).
### Step 3 – Data Visualization
And now the sleek part—taking the data visualization to its completion. With all the elements of the move properly defined, categorized, and stored in a single database table, we can now leverage the APF Reporter tool using the MCS Delivery Time Report template, available with CLASS MCS 5.14. The APF Reporter template has been designed with our users in mind, considering the Ops Review meetings they’ll need to attend. Figure 4 shows a sample chart created using APF.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure-4-delivery-time-report.png) Figure 4. MCS Delivery Time Report created using the APF Reporter tool
Our current customers have been asking for this reporting capability for several years, and now the APF template used to create this chart will be available with MCS 5.14 in March 2023.
Ready to contact us to learn more about this or other charts to improve productivity?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released, Semi
---
### [Synergizing Fault Detection and SPC: smarter manufacturing solution for cost reduction](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
**Published:** March 22, 2024
**Author:** Vishali Ragam, Global Product Manager, SPC
**Excerpt:** Integrating the functions of Statistical Process Control (SPC) and Fault Detection (FD) helps semiconductor manufacturers achieve higher quality, reliability, and efficiency
**Content:**
## What’s Inside
- [ Understanding SPC-FD systems integration ](#index1)
- [ Correlating equipment data with inline measurements ](#index2)
- [ The Pearson Correlation Coefficient ](#index3)
- [ Implementing SPC with correlation analysis ](#index4)
- [ Conclusion ](#index5)
In the intricate world of semiconductor manufacturing, precision is not just a preference; it is an absolute necessity. The smallest deviation can lead to significant defects impacting the final product’s quality and yield. To meet the demands of ever-shrinking device sizes and increasing complexity, manufacturers rely on advanced tools and methodologies. Two such essential tools are Statistical Process Control (SPC) and Fault Detection (FD) systems. While both offer distinct advantages on their own, integrating them into a unified platform provides a range of benefits that can significantly enhance semiconductor manufacturing process techniques. SmartFactory SPC is increasingly sophisticated at building models, especially when correlating fault detection data with inline measurements.
### Understanding SPC - FD systems integration
Having SPC and FD systems integrated into one platform provides a comprehensive view of the entire manufacturing process. Operators and engineers can monitor the process variables controlled by SPC and detect any faults or anomalies identified by the FD system. When SPC and FD data are integrated, it becomes easier to correlate process variations with potential faults and gain a deeper understanding of these relationships. This holistic view leads to more informed decision-making.
Such integration also streamlines data management, providing a centralized repository for all process-related information. By minimizing defects, optimizing processes, and reducing downtime, the integrated SPC-FD system leads to significant cost savings. Improved yield means more usable chips per production run, translating to higher revenues.
### Correlating equipment data with inline measurements
One of the advanced applications of SPC in semiconductor manufacturing involves correlating equipment data with inline measurements. This correlation provides insights into how equipment performance impacts product quality. It examines how anomalies detected by the FD system correspond to specific process parameters monitored by the SPC system. For example, a spike in voltage fluctuations (detected by FD) correlates with a specific tool’s running parameters (monitored by SPC), indicating a potential equipment issue. Figure 1 shows another example, the relationships between chamber temperature and metrology.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/03/Interrelationship-between-equipment-temperature-and-the-inline-measurements-showing-inverse-correlation.jpg) Figure 1: Interrelationship between equipment temperature and the inline measurements showing inverse correlation.
There are many types of correlations that detect deviations from expected behavior early in the manufacturing process. Such connections optimize processes by adjusting parameters to reduce defects and improve efficiency. One such example is the Pearson Correlation Coefficient, which is a valuable tool for quantifying the strength and direction of this relationship.
### The Pearson Correlation Coefficient
The Pearson Correlation Coefficient, often denoted as ‘r’, measures the linear relationship between two variables, X and Y. It ranges from -1 to 1, where:
- 1 indicates a perfect positive linear relationship.
- -1 indicates a perfect negative linear relationship.
- 0 indicates no linear relationship.
Figure 2 shows the behavior of different equipment sensors when measured in terms of immediate product measurements. As noticed, Sensor 1 shows a linear relationship and tells us there is significant effect on product dimensions. A coefficient of 0.99 indicates a positive correlation and it can guide us with root cause analysis when unexpected behaviors surface.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/03/Fault-Detection-sensors-correlations-with-SPC-inline-measurements-with-calculated-Pearson-Coefficient.jpg) Figure 2: Fault Detection sensors correlations with SPC inline measurements with calculated Pearson Coefficient
### Implementing SPC with correlation analysis
SmartFactory SPC focuses on the ease with which such analytical models can be implemented. The platform provides the ecosystem for data preparation, model selection and implementation, which readily works with existing data. Among the key capabilities of this application are user experience and interpretation of results for easier implementation into factory systems. Web-based reporting helps ensure continuous monitoring and maintenance of the model’s performance. One of the advantages of this solution is that it helps shut down tools likely to produce bad products, as well as qualify new tools and validate preventative maintenance (PM) cycles. With many of our customers, we have seen smoothened tool performances for KPI improvements as well as process window gains for better line monitoring and scrap reduction.
### Conclusion
In the competitive landscape of semiconductor production, where precision and efficiency are critical, having SPC and FD capabilities in one place provides a comprehensive approach to process management. It is not just about producing chips; it is about producing them with the highest quality, reliability, and efficiency possible.
As semiconductor technologies continue to advance, the role of SPC and correlation analysis will only grow in importance. Manufacturers embracing this integrated approach are poised to stay ahead of the curve, meeting the demands of today’s semiconductor market with confidence and agility. Applied SmartFactory is committed to delivering best in class practices to semiconductor manufacturers to help them achieve their standards for quality and efficiency.
## FAQs
#### What is Statistical Process Control (SPC)?
SPC is the process by which various data points are collected for each step of the manufacturing process, making it possible to determine whether a given step was completed correctly.
#### What is a Fault Detection (FD) system?
Fault detection collects and analyzes equipment parameters to provide rapid feedback on process performance issues and avoid unexpected failures that decrease productivity.
#### How can integrating SPC and FD systems benefit my semiconductor factory?
Integrating SPC and FD so they are in one place streamlines data management and provides a centralized repository for all process-related information. The integrated system minimizes defects, optimizes processes, and reduces downtime, which leads to significant cost savings.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Improve yield for better profitability, less waste with SmartFactory SPC](https://appliedsmartfactory.com/semiconductor-blog/quality/better-profitability-with-spc/)
**Published:** September 7, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Automating analytics reduces defects, optimizing continuous improvement
**Content:**
Yield is one of the most significant KPIs manufacturers focus on because improving yield has such a positive impact on waste reduction, productivity, profitability, and even customer satisfaction. To improve yield, however, it’s necessary to identify and appropriately address the source of process nonconformities, optimize production processes, and adopt a culture of continuous improvement to sustain yield improvements over time. This requires continuous analysis of data from different factory tools and systems. A Statistical Process Control (SPC) system can help minimize process nonconformities by identifying problems early, recommending corrective and preventive actions, and providing tangible clues for process improvement.
[SmartFactory SPC](/semiconductor/process-quality-solutions/spc/) processes parameters in real-time and analyzes production data to identify process nonconformities. It does so by validating whether specifications are within limits, identifying suspect processing trends, and warns the staff when a process nonconformity is identified. You can think of this as an “early warning system” for process nonconformities that not only identifies problems, but also identifies opportunities to improve quality and reduce variability.
SmartFactory SPC can tell you when problems arise and what to do about them in real-time
Additionally, SmartFactory SPC helps foster a culture of continuous improvement by providing vital feedback about production processes to the manufacturing staff in real-time.
Adopting an SPC system can automate the arduous analysis required to continuously evaluate process performance and make recommendations for process improvements that increase yield. Ultimately, improving yield can bring significant improvements in quality, waste reduction, and profitability.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Smarter alarm management: The hidden cost of alarm fatigue](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/smarter-alarm-management-and-hidden-cost-of-alarm-fatigue/)
**Published:** October 10, 2025
**Author:** Yoram Barak, Global Product Manager
**Excerpt:** The right alarms at the right time, to the right people
**Content:**
## What’s Inside
- [ Why does Alarm Fatigue matter ](#index1)
- [ Economic impact in semiconductor fabs ](#index2)
- [ The solution: SmartFactory Alarm Management ](#index3)
- [ The payoff: quality, efficiency, and peace of mind ](#index4)
- [ Conclusion ](#index5)
In our previous blog [Alarm Management: from chaos to control](/semiconductor-blog/manufacturing-execution/smart-alarm-management-for-semiconductor-industry/), we outlined the challenges with mismanaged alarms in manufacturing. When mismanaged, they flood operators with noise and obscure critical issues, as well as contribute to costly downtime and scrap. One of these challenges is a silent productivity and yield killer in semiconductor manufacturing that often goes unnoticed: alarm fatigue. Alarm fatigue arises when operators are overwhelmed by frequent, often non-critical alerts from process control and other systems. This desensitization can lead to delayed responses or missed alarms, increasing the risk of equipment failure, yield loss, and safety incidents. Economically, alarm fatigue can result in significant downtime, reduced throughput, and higher operational costs due to inefficient troubleshooting and maintenance. Over time, these consequences can erode profitability and competitiveness, especially in high-volume, precision-driven fabs where even minor disruptions have outsized financial impacts. In this article, we will explore the economic burden of alarm fatigue and ways to resolve it using the best-in-class Alarm Management system.
### Why does Alarm fatigue matter?
Alarm fatigue is a real problem across many segments. In the healthcare space for example, in intensive care units, patients may trigger more than 900 alarms per day, with 72–99% being false or non-actionable. This leads to clinicians ignoring alarms, resulting in missed critical alerts and patient harm, including delayed treatment and increased mortality. Alarm fatigue has been linked to serious patient safety incidents, prompting alarm management to become a National Patient Safety Goal since 2014.
An alarm fatigue example from pharma manufacturing is often associated with batch-level deviations and compliance risks. Excessive alarms in cleanroom environments or during sterile processing can lead to operator desensitization, risking product contamination or regulatory non-compliance. An example of a personalized medicine partnership between the Applied SmartFactory Rx team and Moderna to address major alert to action issues in pharma manufacturing can be found [here](https://www.linkedin.com/posts/amy-doucette-1ba53316_pharmamanufacturing-alarmmanagement-activity-7353828721096572928-ccRn/).
In the oil and gas industry, a relevant example is a case faced by an oil producer, the Pipeline Monitoring (Emerson Zedi Case). Most of the alarms in this case were false, leading to ignoring real leak alarms, risking environmental damage and regulatory fines. AI-based alarm filtering reduced false positives and improved leak detection accuracy. There is also no shortage of examples in the chemical and process industries (Houda Briwa, 2022),[1](#references) where alarm flood resulting in operators’ fatigue caused severe injuries and fatalities, as well as major economic damage.
Alarm fatigue in semiconductor fabs, where a single deviation can trigger a cascade of alerts, is a growing problem. A study at STMicroelectronics[2](#references) found that more than 95% of alarms were low-priority and only 4% triggered any action. Even more striking, just 100 alarms out of 5,000 accounted for 70% of all alarm activity.
This flood of irrelevant alerts leads to:
- Delayed responses to critical issues.
- Missed alarms due to operator desensitization.
- Increased scrap rates and reduced yield.
- Higher maintenance costs and unplanned downtime.
### Economic impact in semiconductor fabs
Let’s calculate the economic impact of the alarm fatigue for 300mm and 200mm fabs with 20,000 wafer starts per month (WSPM). The assumption base is shown in Table 1, below:
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/10/alarm-fatigue-table.webp) Table 1: Assumptions for 300mm and 200mm fabs.
Based on these assumptions for 300mm fabs, the potential economic consequence of alarm fatigue, as shown in Figure 1, is:
- **Lost yield:** Up to $28.8M/year
- **Downtime cost:** ~$2M/year
- **Total cost of alarm fatigue:** ~$30M+ annually
For a 200mm fab with the same volume:
- **Lost yield:** ~$7.2M/year
- **Downtime cost:** ~$900K/year
- **Total cost:** ~$8M+ annually
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/10/alarm-fatigue-fig.webp) Figure 1: Outlines the economic burden of alarm fatigue. Per the above assumptions table for: 20,000 WSPM; 300mm: the output will be 600 chips/wafer, and the depicted bar is for $20/chip. In the case of 200mm: the output will be 300 chips/wafer, and the depicted bar is for estimated $10/chip. Additional assumptions are 1% yield loss; Downtime: 20 hrs @ $100K/hr (300mm), 15 hrs @ $60K/hr (200mm).
Smart alarm management software can reduce nuisance alarms by 60 to 80%, leading to millions in recovered value and significant ROI.
### The solution: SmartFactory Alarm Management
SmartFactory Alarm Management addresses these challenges by offering a centralized, automated, and integrated approach to alarm handling:
- **Automated filtering and prioritization:** Only meaningful alarms are forwarded, with duplicates and false alarms suppressed.
- **Configurable notifications:** Alerts are sent only to relevant staff, via email or SMS, with escalation paths if unacknowledged.
- **Action automation:** Alarms can trigger predefined actions like putting a lot on hold or logging a tool down across MES, equipment automation, and other systems.
- **Comprehensive dashboarding:** A real-time, factory-wide view of active alarms, plus historical analysis for root cause investigation.
- **Integration:** Integrated with other SmartFactory Computerized Integrated Manufacturing such as Manufacturing Execution System (MES), Equipment Automation (EA), Material Control System (MCS), Run-to-Run (R2R), Activity Manager (AMA), Fault Detection (FD), Recipe Management System (RMS), Knowledge Advisor (KA) etc.; this automatically triggers actions for faster response time.
### The payoff: quality, efficiency, and peace of mind
By integrating alarm management into the broader SmartFactory ecosystem, manufacturers can:
- **Reduce downtime** by accelerating response to critical alarms and minimizing alarm fatigue.
- **Improve yield** by catching quality-impacting issues earlier.
- **Empower operators** with actionable, relevant alerts.
- **Streamline compliance** with ISA and EEMUA standards.
### Conclusion
Alarm fatigue can be mitigated by a smarter alarm management system with tight integration into other automation systems. This approach will result in less noise, which means more control, better quality, and higher profitability. The benefits the SmartFactory Alarm Management system can bring to your factory are unparalleled. If you’re ready to rethink how your fab handles alarms, [reach out](/connect/?page_source=https://appliedsmartfactory.com/semiconductor/manufacturing-execution-solutions/alarmmanagement/).
### References
\[1\] Briwa Houda, 2022 – Alarm Management for huma performance. Are we getting better? Proceedings of the 32nd European Safety and Reliability Conference (ESREL 2022).
\[2\] Al-Kharaz et al., 2019 – Evaluation of Alarm System Performance and Management in Semiconductor Manufacturing. 6th International Conference on Control, Decision and Information Technologies (CoDIT’19).
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Removing barriers to achieve higher levels of automation in the semiconductor industry](https://appliedsmartfactory.com/semiconductor-blog/productivity/removing-barriers-in-semiconductor-industry/)
**Published:** October 9, 2024
**Author:** Michael Frenna, Global Product Manager, Workflow Automation and Factory Analytics
**Excerpt:** Advancements are helping legacy fabs deploy automation solutions
**Content:**
## What’s Inside
- [ What’s driving demand for automation? ](#index1)
- [ Barriers for legacy fabs ](#index2)
- [ Strategic and technological solutions ](#index3)
- [ Robotics ](#index4)
- [ MES advancements ](#index5)
- [ Conclusion ](#index6)
Applied Materials Automation Products Group provides automation software solutions to customers worldwide. In our experience deploying these solutions, we’ve found there is a significant gap in automation maturity between legacy fabs—typically 150 mm/200 mm front-end fabs utilizing more manual processes—and the newer 300 mm fabs that are running fully automated “lights out” operations. This is primarily due to significant barriers legacy manufacturers have historically faced in achieving higher levels of automation. In this article, we’ll look at how times are changing, and how these barriers are currently being addressed by the industry.
### What’s driving demand for automation?
Every year, there is an increased demand for new technologies that require higher performance chips. As a result, semiconductor manufacturers have seen their unit volumes increase, while at the same time introducing more complex manufacturing processes. The additional steps and labor required to produce these higher performance chips are putting a significant strain on direct labor productivity, specifically in legacy factories that are running manual processes. Manufacturers understand that this increased demand and complexity in their manufacturing process will require automation because simply using additional labor to address the problem becomes too costly.
### Barriers for legacy fabs
There are three primary areas we’ve identified as significant barriers to legacy factories seeking to implement automation. The first of these is cost of ownership. Legacy manufacturers are often smaller manufacturers with smaller budgets than bigger players in the industry, so significant infrastructure changes are too costly for them. Most of their facilities were built in the ’80s and early ’90s, before 300 mm manufacturing came along, so they weren’t built with overhead transport systems. They have lower ceilings and their tool spacing is inadequate for automated material handling to take place, putting them at a disadvantage. Conversely, in the 300 mm segment, facilities were constructed with automated material handling systems to compensate for the larger front opening unified pods (FOUPs) which are used to transport larger 300mm carriers. Consequently, these manufacturers were put in a better position to adopt higher levels of automation.
Retrofitting an existing legacy factory that wasn’t built with automated material handling from initial construction can be extremely costly. Reconfiguring existing facilities involves moving high cost processing machinery, undertaking large scale construction projects, and re-training existing operations— all while not disrupting on-going production. Also falling into the cost-prohibitive category are the high upfront costs of high-powered servers required to run software solutions in semiconductor manufacturing solutions.
Another factor that plagues legacy factories’ ability to achieve higher levels of automation is access to talent that can maintain these robust systems. Large IT teams are required to integrate and maintain automation systems. Often, legacy factories have smaller budgets and much smaller IT teams, so it becomes infeasible for them to maintain automation systems in addition to maintaining Manufacturing Execution Systems (MES) and other critical IT infrastructure.
Finally, legacy systems, which are typically comprised of siloed point solutions, lack functional integration that is essential for a fully automated factory. Many legacy factories have multiple home-grown solutions and/or commercial solutions from different vendors throughout their automation stack that don’t fully integrate with each other without significant development work. This lack of integration is depicted below in Figure 1. Manufacturers understand they need to integrate these systems to achieve a fully automated factory, but there’s significant development effort required to do so, making this an immense challenge for manufacturers with smaller IT teams.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/integration-pyramid.png) Figure 1: Manufacturers struggle to automate data exchange from the enterprise level to the production floor
### Strategic partnerships and out of box solutions
Despite the financial and logistical barriers legacy manufacturers face, solutions now exist to ease the transition towards a more highly automated manufacturing environment. Commercial vendors have begun forming strategic partnerships to co-develop lower cost “out of box” or pre-integrated automation solutions for customers. These offerings are significantly reducing the cost of ownership for customers as they reduce the amount of IT overhead required to develop and maintain.
Additionally, hardware and software providers are starting to deliver modular solutions that can coexist with existing systems in running fabs. Examples of this are MES-agnostic solutions that do not require a specific MES, but rather work with any type of MES solution, even ones which are developed by the customers themselves.
### Robotics
Advancements in mobile robotics (such as ARVs, AGVs and co-bots) are meeting the unique needs of legacy factories without requiring them to completely refactor their facility. An existing factory already has an infrastructure and systems in place which are not often well suited to add traditional Automated Material Handling Systems (AMHS) such as Overhead Hoist Transport Systems (OHT). OHT’s require specific ceiling heights and multi-year construction projects to install and configure the guided rail systems in a fab, which not only is costly, but disruptive to an on-going fab operation. Mobile robotics on the other hand, can be rolled out on the floor in specific areas rather than requiring a semiconductor manufacturer to remodel or deploy a robotics solution all at once. Legacy factories are finding success in deploying mobile robotics in areas with tight spacing and low ceilings without major disruptions to production.
### MES advancements
The Manufacturing Execution System, or MES, is critical software that is responsible for monitoring and controlling manufacturing operations. Often, customers have an MES that is either a commercial MES that is decades old, or a homegrown MES that was developed potentially 10 or more years ago that hasn’t grown with the complexity of their current manufacturing process. To bridge the gap as requirements are added to the production process, organizations build point solutions around the MES that lead to the integration problem noted earlier.
Advancements in manufacturing execution systems that have made them ready to handle the complex semiconductor processes that are run today have also reduced the barriers to automation. Low-code and no code developer tools have helped improve developer productivity and reduced the need for IT resources. Manufacturers have a tool to help with the integration work required in an automated factory and can now be more productive in maintaining automated software solutions.
### Conclusion
Manufacturers understand the importance of automation, but legacy factories have faced many challenges in implementing it. It has been difficult for them to keep up with the industry leaders due to these barriers. Recently, the industry has made great strides in addressing these issues through lowering costs and providing greater technological resources. Ultimately, we’re driving towards a more democratized automation landscape in the semiconductor industry.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [From chaos to harmony: Solving the configuration challenge in semi manufacturing automation](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/how-to-solve-configuration-challenge-in-semiconductor-manufacturing-automation/)
**Published:** November 10, 2025
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** Rethinking how configurations are used to improve productivity
**Content:**
## What’s Inside
- [ The hidden cost of configuration chaos ](#index1)
- [ Why legacy approaches fall short ](#index2)
- [ Introducing SmartFactory Common Config Hub ](#index3)
- [ Key capabilities ](#index4)
- [ Benefits for manufacturers ](#index5)
- [ Impact to factory operation ](#index6)
- [ Laying the groundwork for smart factories ](#index7)
- [ Conclusion ](#index8)
In today’s semiconductor manufacturing and factory automation ecosystems, machines are smarter, software is more advanced, and data flows in every direction. Yet behind all this progress lies a surprisingly stubborn problem–configuration chaos.
Every factory asset, whether it’s a furnace, lithography tool, or automated guided vehicle (AGV), must be configured in multiple applications. This could include, for example, the manufacturing execution system, equipment automation, recipe management, advanced process control, and materials control. Each of these has its own interface, data model, and configuration process. This can lead to duplicate effort, mismatched settings, and hidden risks that quietly erode productivity.
### The hidden costs of configuration chaos
Setting up a tool a few times across different systems may seem manageable, or at most a minor inconvenience. In reality, this problem scales quickly and painfully. Among the problems manufacturers experience are:
- **Configuration drift:** A parameter updated in one system but not another causes errors, misaligned recipes, or tool holds.
- **Operational inefficiency:** Engineers waste countless hours duplicating work across systems instead of optimizing processes.
- **Downtime and yield loss:** Misconfigurations are among the leading, hidden causes of unplanned downtime and scrap.
- **Compliance risk:** Auditors demand traceability, but when settings are scattered across five systems, proving control is difficult.
For a single factory, these issues can mean weeks of lost time per year. Across a network of plants, the costs multiply dramatically.
### Why legacy approaches fall short
Manufacturers have tried to address this problem with custom integrations, manual workflows, or one-off scripts. Unfortunately, these approaches rarely scale, resulting in a situation where: - **Point-to-point integrations** quickly become fragile, expensive to maintain, and hard to adapt when new systems are added.
- **Manual updates** are slow and error-prone, leaving no reliable audit trail.
- **Lack of governance** means no easy way to reconcile when mismatch occurs.
As factories grow more automated and connected, the stakes get higher. What’s needed isn’t more patchwork, but rather a new way to think about configurations altogether.
### Introducing SmartFactory Common Config Hub
SmartFactory Common Config Hub was built specifically to address this growing need in manufacturing environments. The solution acts as a central synchronization layer that ensures every system, every tool, and every stakeholder is working from the same, harmonized configuration.
Instead of setting common parameters five times in five systems, you define them once. SmartFactory Common Config Hub propagates the configuration automatically—reliably, securely, and with full governance.
### Key capabilities
- **Single source of truth**
One central repository for asset configurations, ensuring all connected systems are aligned.
- **Knowledge graph for traceability**
The graph links configuration data from MES, equipment automation, recipe management, advanced process control, and materials control. This unifies configuration context across systems without the need for full data consolidation.
- **Automated synchronization**
Changes propagate instantly across solutions.
- **Governance and compliance**
Built-in audit trails, access controls, and policy enforcement make it easier to meet industry regulations.
- **Open and extensible**
API-driven architecture allows easy integration with existing factory applications and future systems.
- **Digital twin integration**
Configurations can be tied to digital representations of assets, enabling smarter analytics and AI-driven optimizations.
### Benefits for manufacturers
Implementing SmartFactory Common Config Hub delivers immediate and measurable impact, including:
- **Harmonization:** Eliminate configuration drift and mismatches across applications.
- **Faster asset onboarding:** Bring new machines online in hours instead of weeks.
- **Reduced downtime:** Fewer misconfigurations mean fewer unexpected tool holds.
- **AI-driven anomaly detection and automated validation:** Detect configuration mismatches and flag inconsistent parameters.
- **Audit-readiness** Configuration changes are tracked, visible, and reportable.
- **Empowered workforce:** Engineers focus on improvement and innovation, not repetitive data entry.
### Impact to factory operation
Consider a semiconductor fab adding a new lithography tool. Traditionally, engineers would need to configure the tool in MES, equipment automation, recipe management, advanced process control, and materials control separately. Each step takes hours, involves manual copying, and risks error.
With SmartFactory Common Config Hub, the configuration is defined once and automatically synchronized across all systems. In this example, the fab would have achieved:
- **70% faster onboarding** of the new tool.
- **40% reduction in configuration-related errors.**
- **Improved audit readiness** for ISO and customer compliance checks.
Ultimately, this results in faster time-to-production, higher reliability, and more productive engineers.
### Laying the groundwork for smart factories
While the immediate benefits are clear, the long-term vision is even more exciting. By creating a harmonized configuration layer, manufacturers lay the foundation for:
- **AI-driven, self-configuring factories** that adapt automatically to changes in demand or process.
- **Smarter digital twins** that use synchronized configurations for more accurate modeling.
- **Seamless multi-factory scaling** where best-practice configurations can be applied globally in minutes.
### Conclusion
Configuration chaos has been negatively impacting productivity in factories for far too long, but manufacturers don’t have to accept it as inevitable. With SmartFactory Common Config Hub, they can move from duplication and drift to harmonization and efficiency. Semiconductor manufacturers can reduce errors, cut onboarding time, and enable the next wave of smart manufacturing.
It’s time to stop fighting configurations and start using them as a driver of operational excellence.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Manufacturing discipline starts at the substrate: Why execution can’t wait for the fab](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
**Published:** April 10, 2026
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Front-end execution increasingly determines semiconductor outcomes
**Content:**
## What’s Inside
- [ Introduction ](#index1)
- [ Wafer quality starts upstream ](#index2)
- [ How scaling changed the rules ](#index3)
- [ Shortcomings of execution models designed for downstream ](#index4)
- [ Moving traceability from discovery to origin ](#index5)
- [ What is “production grade” execution? ](#index6)
- [ Bringing fab‑level discipline forward ](#index7)
In semiconductor manufacturing, the industry often draws a clean conceptual line between “upstream” and “downstream.” The rationale is that upstream steps prepare the material, while downstream is where real manufacturing happens. Crystal growth and wafering happen upstream. Wafer fabrication, test, and assembly happen downstream. In today’s semiconductor manufacturing environment, these boundaries are no longer so clean-cut.
As device complexity increases and tolerance for variation shrinks, what happens during wafer substrate manufacturing is no longer a prelude to manufacturing. It is manufacturing. The level of execution discipline applied there increasingly determines what the fab can—and cannot—achieve. It also requires manufacturers to rethink how execution is managed at the very front of the semiconductor lifecycle.
### Wafer quality starts upstream
Every semiconductor device begins with a wafer whose physical properties are established long before it enters a fab. Characteristics such as crystal orientation, defect density, thickness uniformity, and surface quality are set during crystal growth and wafering. Once established, these attributes propagate forward through every downstream process step. When variation is introduced at this stage, the fab can detect and compensate for some effects—but it cannot undo them.
While this reality is not new, scaling has made it a much bigger problem.
Larger wafers, tighter geometries, and advanced device architectures amplify the impact of early‑stage variation. Small inconsistencies that once fell within acceptable margins now create meaningful downstream consequences. In that environment, treating substrate manufacturing as a loosely controlled preparatory phase is a growing liability.
### How scaling changed the rules
Historically, many wafer substrate operations evolved in environments that prioritized material science and process development over high‑volume execution. That made sense when volumes were lower and variability could be managed through expertise and manual intervention, but times have changed. Substrate manufacturers are scaling production to support growing demand across logic, memory, power, and specialty devices.
Scaling does not simply increase output—it multiplies the consequences of inconsistency. Practices that were successful in pilot lines or lower‑volume environments become fragile when throughput increases, shift structures expand, and product mixes grow more complex. At scale, consistency cannot rely on individual expertise alone. It requires systems that enforce standard execution, manage change deliberately, and make process behavior visible in real time.
This naturally pushes manufacturers toward more formal execution control. However, applying “standard” downstream playbooks upstream often exposes a mismatch between the tools and the reality of substrate workflows.
### Shortcomings of execution models designed for downstream
Manufacturing Execution Systems (MES) bring order and control to complex operations, so many manufacturers turn to the MES to bring order to substrate manufacturing before impacts are felt downstream. That instinct is correct—but not all MES platforms are created with substrate manufacturing in mind. This is where traditional execution models—and many MES implementations—begin to show strain.
Wafer substrate operations differ fundamentally from downstream fab and packaging environments. Process steps are longer; material transformations are physical and irreversible. Genealogy—from seed crystal, to ingot, to wafer—is central to understanding quality. Additionally, workflows do not resemble the short, tool‑centric cycles common in fabs.
When execution systems designed for other environments are forced upstream, manufacturers often compensate with workarounds: custom logic, external spreadsheets, manual handoffs. Over time, these adaptations create fragility instead of control, and the upstream processes most responsible for downstream outcomes remain under‑modeled and inconsistently enforced.
Existing approaches to traceability often exacerbate this gap, as they are downstream-focused— helping to identify outcomes rather than prevent issues at their source.
### Moving traceability from discovery to origin
Traceability is often discussed in the context of yield analysis and failure investigation. While this is important, traceability delivers the greatest value when it exists where problems originate, not where they are discovered.
When substrate‑level genealogy and process history are incomplete or loosely structured, downstream teams are left to infer root causes rather than identify them. Investigations take longer. Corrective actions are broader than necessary. Confidence in decisions erodes.
Instead, traceability needs to be built into upstream execution, with each wafer carrying a clear, system‑enforced record of how it was produced. This enables manufacturers to prevent problems from propagating, rather than search for the root cause after the fact.
In an industry where downstream rework and scrap are exceptionally costly, that distinction matters. The road to achieving that requires a broader shift, toward an execution standard that is reliable by design and can sustain repeatable performance at true manufacturing scale.
### What is “production grade” execution?
As substrate manufacturing moves into the critical path of semiconductor production, expectations change. The question is no longer whether a process can be made to work, but whether it can be run reliably, repeatedly, and at scale.
Production‑grade execution means more than automation. It means:
- Standardized workflows that reflect real manufacturing practices.
- Controlled change that preserves stability while enabling improvement.
- Real‑time visibility into execution, not just historical reporting.
- Reliability measured in uptime and consistency, not flexibility alone.
Manufacturers already hold these expectations for mission‑critical fabs, but they are increasingly recognizing the same need to be employed upstream.
### Bringing fab‑level discipline forward
Semiconductor manufacturing has always been an exercise in managing complexity. What is changing is where that complexity must be controlled.
As devices grow more advanced and margins for error shrink, the industry can no longer afford a disconnect between upstream material preparation and downstream device fabrication. Execution discipline must span the full lifecycle—from crystal growth through finished product.
Manufacturers that treat wafer substrate operations as critical infrastructure, rather than a handoff, position themselves to scale with confidence. They reduce downstream risk, shorten learning cycles, and create a stronger foundation for continuous improvement.
In the end, the lesson is straightforward: by the time a wafer reaches the fab, much of the outcome is already set in motion. The manufacturers who recognize that—and act on it—will be better equipped for the next era of semiconductor production.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular, Semi
---
### [故障検出とSPCの相乗効果：コスト削減につながるスマートな製造ソリューション](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
**Published:** March 22, 2024
**Author:** Vishali Ragam, Global Product Manager, SPC
**Excerpt:** 統計的プロセス制御（SPC）と故障検出（FD）の機能をインテグレーションすることで、半導体メーカーは品質、信頼性、効率をさらに向上させることができます。
**Content:**
## 内容
- [ SPC‑FDシステム統合の理解 ](#index1)
- [ 装置データとインライン測定データの相関付け ](#index2)
- [ ピアソンの相関係数 ](#index3)
- [ 相関分析を用いたSPCの実装 ](#index4)
- [ まとめ ](#index5)
複雑な半導体製造現場では、精度は「あればよいもの」ではなく、不可欠な前提条件です。わずかな偏差も重大な欠陥を生み、最終的に製品の品質や歩留まりに大きな影響を与える可能性があります。ますます小型化・複雑化するデバイスの要求に応えるため、メーカーには高度なツールや手法が必要です。その代表的なツールが、統計的プロセス制御（SPC）と障害検出（FD）システムです。どちらも単独で利点がありますが、統合プラットフォームに組み込むことで、半導体製造プロセスの高度化に役立つ多くのメリットが得られます。SmartFactory SPC3D®は、特に障害検出データとインライン測定データを相関させる際に、モデル構築の高度化が進んでいます。
### SPC–FDシステムインテグレーションの理解
SPCとFDシステムを一つのプラットフォームにインテグレーションすることで、製造プロセス全体を包括的に把握できます。オペレーターやエンジニアは、SPCが制御するプロセス変数を監視し、FDシステムが検出した異常や障害を確認できます。SPCとFDのデータをインテグレーションすることで、プロセス変動と潜在的な障害との相関を分析しやすくなり、両者の関係をより深く理解できるようになります。この総合的な視点により、より適切な判断が可能になります。
また、このインテグレーションによりデータ管理が効率化され、すべてのプロセス関連情報を一元的に管理できます。統合SPC-FDシステムは、欠陥の最小化、プロセスの最適化、ダウンタイムの削減を通じて、大幅なコスト削減に貢献します。歩留まりの向上は、生産ごとに使用可能なチップを増やし、収益の向上にもつながります。
### 機器データとインライン測定データの相関分析
半導体製造におけるSPCの高度な応用の一つに、機器データとインライン測定の相関分析があります。この分析により、機器の性能が製品品質にどのように影響するかを把握できます。FDシステムで検出された異常が、SPCシステムで監視される特定のプロセスパラメーターとどのように関連しているかを確認できます。例えば、電圧変動の急上昇（FDで検出）が、特定のツールの動作パラメーター（SPCで監視）と相関している場合、機器に潜在的な問題があることを示します。図1は、チャンバー温度と計測値の関係を示す別の例です。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/03/Interrelationship-between-equipment-temperature-and-the-inline-measurements-showing-inverse-correlation.jpg) 図1：機器の温度とインライン測定の相互関係における逆相関。
製造プロセスの初期段階で、予想される動作からの逸脱を早期に検出できる相関にはさまざまな種類があります。こうした相関を活用することで、パラメーターを調整してプロセスを最適化し、欠陥を減らして効率を高めることができます。その代表例であるピアソン相関係数は、変数間の関係の強さや方向を定量的に示すために有用な指標です。
### ピアソン相関係数
ピアソン相関係数（多くの場合「r」と表記）は、2つの変数XとYの線形関係を示す指標で、範囲は-1から1で表されます。
- 1は完全な正の線形関係を示します。
- -1は完全な負の線形関係を示します。
- 0は線形関係がないことを示します。
図2は、インライン測定値に基づいて各機器センサーがどのように動作するかを示しています。センサー1は線形関係を示しており、製品寸法に大きな影響を与えることがわかります。係数0.99は正の相関を示しており、予期しない動作が発生した際の原因分析にも役立ちます。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/03/Fault-Detection-sensors-correlations-with-SPC-inline-measurements-with-calculated-Pearson-Coefficient.jpg) 図2：故障検出センサーとSPCインライン測定の相関（ピアソン係数付き）
### 相関分析を用いたSPCの実装
SmartFactory SPC3Dは、このような分析モデルを簡単に実装できることを重視しています。このプラットフォームは、既存のデータと容易に連携できるデータ準備、モデル選択、実装のためのエコシステムを提供します。主な機能の一つに、ユーザー操作のしやすさや結果の解釈があり、工場システムへの導入を容易にします。ウェブベースのレポート機能により、モデルのパフォーマンスを継続的に監視・維持できます。このソリューションの利点の一つは、不良品を出しやすいツールの停止を支援すると同時に、新しいツールの適格性確認や予防保守（PM）サイクルの検証も可能にする点です。KPI改善によるツール性能の安定化や、ライン監視の向上とスクラップ削減によってプロセスウィンドウが広がる効果を、多くの顧客が得られています。
### まとめ
精度と効率が重要な半導体製造の競争環境では、SPCとFDの機能を一元化することで、プロセス管理に対してより包括的なアプローチが可能になります。単にチップを生産するだけでなく、可能な限り高い品質と信頼性、効率で生産することが求められます。
半導体技術の進歩に伴い、SPCや相関分析の重要性はますます高まっています。この統合アプローチを採用するメーカーは、常に先を見据え、自信と柔軟性をもって今日の半導体市場の需要に応えることができます。Applied SmartFactoryは、半導体メーカーが品質と効率の目標を達成できるよう、最高水準の手法をご提供することに注力しています。
## FAQ
#### 統計的プロセス制御（SPC）とは何ですか？
SPCは、製造プロセスの各ステップでさまざまなデータポイントを収集し、各ステップが正しく完了したかを判断できるプロセスです。
#### 障害検出（FD）システムとは何ですか？
Fault Detectionsシステムは、装置のパラメータを収集・分析することで、プロセス性能に関する問題に対して迅速なフィードバックを提供し、生産性を低下させる予期せぬ故障を回避します。
#### SPCと障害検出システムをインテグレーションすると、半導体工場にどのようなメリットがありますか？
SPCとFDを統合して一箇所に集約することで、データ管理が効率化され、すべてのプロセス関連情報を一元管理できるリポジトリが提供されます。統合システムは欠陥の最小化、プロセスの最適化、ダウンタイムの削減を実現し、その結果として大幅なコスト削減につながります。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [半導体工場における様々なスケジューリングソリューションの利点と課題](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solutions-for-semiconductor-factories/)
**Published:** August 9, 2023
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** 工場のニーズに適したスケジューリングソリューションの選択
**Content:**
生産現場のスケジュールは、様々な方法や技術を用いて作成することが可能です。これらの方法や技術には、以下が含まれます。単純な先入れ先出し（FIFO）や納期スケジューリング（DDO）ルールの使用、現在及び将来の仕掛品（WIP）を考慮した、簡単/基本的な生産サイクルの仮定に基づく手動/Excel形式の方法、生産エリアのルールに基づくヒューリスティックなスケジューリング、シミュレーションに基づくスケジューリング、最適化に基づくスケジューリング。さらに、将来の仕掛品（WIP）の到着を予測し、バッチの順序付けを行うハイブリッド手法を採用することも可能です。選択する方法やその適用方法は、スケジューリングの品質及びソリューションがもたらす生産効率に影響を与えます。同時に、スケジューリングシステムの種類によっては、工場の入力データの品質と正確性に対する要求も高まります。
Explore the possibilities
Build a new ecosystem of quality powered by Intelligence
[ Let’s Connect ](/connect/)
通常、スケジューリングソリューションはまず工場データを抽出し、それをソリューション用の入力データに変換または整形する必要があります。その後、スケジューリングエンジンは（どの手法を用いる場合でも）様々な考慮事項や目標に基づくロジックを適用し、スケジュール出力データを生成します。生成されたデータはさらに処理され、最終ユーザーが利用できるよう、ユーザーフレンドリーな可視化及び分析形式の計画として提供されます。このプロセスは、下図1の通りです。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/figure1-schedule-flow-picture.jpg) 図1：スケジューリングソリューションのプロセスフロー
以下では、様々な方法や技術のメリットと制約について説明します。
### ヒューリスティックベースのスケジューリングソリューション
これは、ルールに基づくバッチ割り当て及び順序付けの方法です。手作業中心の工場で単純な先入れ先出し（FIFO）、納期順（DDO）またはバッチ優先方式を用いたスケジューリングは、生産性を低下させる可能性があります。一方、エリア、製品構成、設備構成、工場目標に基づいたより複雑なヒューリスティック手法を使用することで、設備利用率、スループット、設備群の生産サイクルを迅速に改善することが可能です。
### シミュレーションベースのスケジューリングソリューション
シミュレーションスケジューリングでは、モデルが工場内すべての設備の現在状態や位置を考慮し、将来のバッチや仕掛品（WIP）の到着を予測します。シミュレーションスケジューリングは、工場のスケジューリングシステムとして機能するほか、エリアスケジューリングシステムと連携し、出力を下流エリアの入力として使用することもできます。
### 最適化ベースのスケジューリングソリューション
最適化スケジューリングでは、混合整数計画法（MIP）や制約プログラミング（CP）モデルを用いて、生産エリアの重み付き目的関数に基づきバッチを割り当て・配置し、最適な設備スケジュールを作成します。最適化スケジューリングシステムはエリアスケジューリングシステムの一種であり、シミュレーションベースの工場スケジューリングシステムとインテグレーションすることが可能です。
以下の表2では、各ソリューションのメリットを簡単に把握することができます。
### 各スケジューリングソリューションのポジティブ属性
ヒューリスティック シミュレーション 最適化 開発・設定・導入が容易
将来のバッチ/仕掛品（WIP）到着予測がより正確
実行可能かつ最適なスケジュール
学習・拡張・カスタマイズが容易
工場全体のスケジューリングが可能で、割り当てルールを実行できる
詳細な設備モデリング
KPI改善の早期効果
非生産環境で割り当てルールを検証可能
ボトルネック管理の改善
入力データの要求/品質への感度は中程度
複数工場・企業間での拡張が可能、より良い生産ラインのバランスを実現
変化する工場条件や目標に敏感に対応可能
表2：ヒューリスティック、シミュレーション、最適化スケジューリングソリューションのポジティブ属性
Explore the possibilities
Build a new ecosystem of quality powered by Intelligence
[ Let’s Connect ](/connect/)
各スケジューリングソリューションの限界は以下の表3の通りです。
### 各スケジューリングソリューションの限界
ヒューリスティック シミュレーション 最適化 継続的な微調整が必要になる場合がある
工場データの品質・遅延・粒度に非常に敏感
工場データの品質・遅延・粒度に非常に敏感
すべての潜在的な生産効果を実現できない
簡略化した割り当てルールを使用
スケジューリングシステムの意思決定が説明しにくい
非生産環境での効果検証が必要
数学的に最適な解ではない
生産環境で効果を評価する必要がある
導入に比較的長い時間がかかる
メンテナンスに必要なリソースが増加
メンテナンスに必要なリソースが増加
変化する工場条件や目標に鈍感で、反応が遅い
モデル性能時間が問題サイズに対して非線形で増加
表3：ヒューリスティック、シミュレーション、最適化スケジューリングソリューションの限界
### まとめ
工場は、自社のニーズ評価に基づいてスケジューリングソフトウェアソリューションを選択する必要があります。理想的には、ソリューションはこれらの要件や工場の具体的な要求事項、現在及び将来の新技術や業務プロセスの導入・適応能力、現行ソフトウェアソリューションの機能などをしっかりと満たす必要があります。意思決定の参考になる質問例は以下の通りです。
- 工場全体のスケジューリングシステムが必要か、それとも生産エリア単位のスケジューリングシステムで十分か？
- ボトルネックの状況や性質はどうか？
- 工場自動化の現在の基準
- 工場データの生成、利用可能性、収集、保存、処理能力を十分に把握している
- スケジューリング自動化のビジョンを支援・実現できる技術リソースは確保できる
ヒューリスティック、シミュレーション、最適化の各スケジューリング手法はいずれも、工場のKPI改善に寄与し、それぞれの手法にはメリットと制約があります。そのため、適用可能性や能力を十分に理解し、工場での成功実装を確実にすることが重要です。
ただし、経験がなく、複雑な自動化スケジューリングソリューションを導入したことのない企業は、ヒューリスティックベースのスケジューリングの導入を検討すべきです。これにより、工場改善における早期の投資回収（ROI）を実現するとともに、経験と専門知識を積むことができます。現時点で割り当てやスケジューリングシステムを導入していない企業が、シミュレーションや最適化に基づくより複雑なスケジューリングソリューションを導入すると、学習曲線が急すぎたり、導入がうまくいかない可能性があります。
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [Incremental automation delivers early wins and long-term gain](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/incremental-automation-delivers-early-wins-and-long-term-gain/)
**Published:** June 3, 2026
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** How SmartFactory enables a phased approach to fit specific manufacturers’ needs
**Content:**
## What’s Inside
- [ Why incremental automation matters to manufacturers ](#index1)
- [ What is SmartFactory? ](#index2)
- [ What manufacturing problems does this approach solve? ](#index3)
- [ Improved productivity ](#index4)
- [ Strengthening quality and yield ](#index5)
- [ Advancing supply chain and planning responsively ](#index6)
- [ Introducing AI when ready ](#index7)
- [ From incremental steps to long-term advantage ](#index8)
At every step of the process, semiconductor manufacturing has become more complex and competitive. Advanced automation is the path forward, but the realities of cost, infrastructure, and human adoption make large-scale implementation prohibitive. The ability to modernize through incremental, phased automation is as critical as the technology itself. This is where SmartFactory plays a distinct role.
### Why incremental automation matters to manufacturers
Many manufacturers delay smart manufacturing initiatives because transformation is often perceived as high-risk, capital-intensive, and disruptive. Large, all-at-once automation programs can strain resources, introduce operational instability, and deliver value too late to justify the investment.
SmartFactory is intentionally designed to avoid this trap. Rather than forcing a wholesale factory overhaul, it enables manufacturers to modernize in logical, value-driven phases. This approach delivers measurable results early while building a scalable foundation for long-term automation and intelligence. It also allows manufacturers to align automation investments with business priorities, factory maturity, and operational readiness. Risk is reduced and time to value is accelerated.
### What is SmartFactory?
SmartFactory is a portfolio of integrated automation solutions that improves productivity, yield, and quality across factory operations. It combines [manufacturing execution systems](/manufacturing-execution-solutions/) (MES), advanced automation, analytics, and AI with deep domain expertise in semiconductor, pharmaceutical, and battery manufacturing.
Its modular execution architecture supports incremental adoption without disrupting ongoing production. This enables a practical, stepwise path to smart manufacturing by helping organizations:
- **Identify** high-impact opportunities where automation delivers immediate operational benefit.
- **Deploy** targeted capabilities — such as MES, scheduling, or quality analytics — in manageable phases.
- **Scale** functionality over time, expanding automation, intelligence, and AI as operational readiness increases.
Each phase delivers measurable improvement on its own, while contributing to a broader, integrated execution framework. Semiconductor manufacturers can modernize continuously without waiting for a “perfect” future-state architecture to be defined.
### What manufacturing problems does this approach solve?
SmartFactory addresses the fragmented systems, siloed data, and reactive decision-making that prevent semiconductor manufacturers from achieving consistent yield, throughput, and operational control. Many semiconductor manufacturers operate with fragmented systems that limit visibility and slow decision-making. Planning, production, maintenance, and quality data often live in silos, forcing teams to react to problems after they’ve already impacted output or yield.
SmartFactory addresses this by unifying shop floor and operations systems into a single execution layer—starting where the impact is greatest. As new capabilities are added, manufacturers gain progressively deeper visibility, tighter control, and more consistent execution across operations.
At the core of this is an integrated manufacturing execution system (MES) that is the backbone of phased automation. It provides real-time visibility, enforcement, and orchestration across shop-floor operations—ensuring consistency as automation expands.
The MES serves as both the starting point and the scaling mechanism for incremental automation—ensuring each phase builds on a stable foundation. This has positive impacts across all critical KPIs.
### Improved productivity
The implementation of real-time scheduling, automation, and simulation are deployed where they will be most impactful. Early phases often focus on eliminating idle time, synchronizing workflows, and improving equipment utilization. As automation scales, these gains compound—driving sustained improvements in throughput and cycle time.
### Strengthening quality and yield
High-mix, high-precision manufacturing demands tight process control. SmartFactory supports a zero-defect strategy through automated monitoring, analytics, and feedback loops that detect variation early.
Semiconductor manufacturers can begin with targeted quality use cases, then expand analytics and control as data maturity grows—reducing yield loss while maintaining operational stability.
### Advancing supply chain and planning responsively
Incremental automation also applies to planning. SmartFactory integrates planning, production control, and simulation capabilities gradually to reduce constraints and improve responsiveness without overwhelming operations.
By aligning planning decisions with real-time execution data, manufacturers can adapt faster to demand changes while protecting throughput and delivery commitments.
### Introducing AI when ready
AI delivers the greatest value when built on reliable execution data. SmartFactory embeds AI and advanced analytics into manufacturing workflows after foundational systems are in place.
This ensures AI-driven insights—such as predictive maintenance, yield optimization, and intelligent scheduling—are accurate, actionable, and scalable across operations.
### From incremental steps to long-term advantage
Smart manufacturing success is defined by outcomes, not speed of deployment. SmartFactory helps manufacturers move forward with confidence—delivering early wins through phased automation while continuously expanding capability over time.
By combining execution, automation, and intelligence in a scalable architecture, SmartFactory provides a practical, technically grounded path from incremental improvement to sustained manufacturing advantage — helping semiconductor manufacturers modernize continuously without the risk of large-scale transformation.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [高度な生産計画・スケジューリングソリューションによる生産性向上](https://appliedsmartfactory.com/semiconductor-blog/planning/boosting-productivity-with-advanced-planning-scheduling-solutions/)
**Published:** October 18, 2021
**Author:** Madhu Mamillapalli, Global Product Manager, Planning Solutions
**Excerpt:** 設備の生産プロセスを簡素化し、生産性を向上させる新しいアプローチ。
**Content:**
設備の生産プロセスを簡素化し、生産性を向上させる新しいアプローチ。
[pdf-embedder url=”/wp-content/uploads/2021/07/Advanced-Planning-Scheduling-Solutions.pdf”]
[ PDFをダウンロード ](/wp-content/uploads/2021/07/Advanced-Planning-Scheduling-Solutions.pdf)
**Semiconductor Category:** Semiconductor Planning
**Semiconductor Tag:** Semi
---
### [ウェハー基板から始まる製造現場の規律: なぜファブに入ってからではもう遅いのか?](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-discipline-starts-at-the-substrate/)
**Published:** April 10, 2026
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** フロントエンドでの実行力が、半導体の成果を大きく左右する時代になっています。
**Content:**
## 内容
- [ はじめに ](#index1)
- [ ウェハー品質は上流工程で決まる ](#index2)
- [ スケーリングがどのようにルールを変えるか？ ](#index3)
- [ 下流工程向けに設計された実行モデルの限界 ](#index4)
- [ トレーサビリティを「発見」から「起点」へ ](#index5)
- [ 「プロダクション・グレード」の実行とは？ ](#index6)
- [ ファブレベルの規律を前工程へ ](#index7)
半導体製造では、「上流（アップストリーム）」と「下流（ダウンストリーム）」を明確に分けて考えることが一般的でした。上流は材料を準備する工程、下流こそが“本当の製造”が行われる場所、という考え方です。結晶成長やウェハー加工は上流、ウェハーの回路集積、テスト、組立は下流に位置づけられてきました。しかし今日の半導体製造環境では、こうした境界はもはや明確ではありません。
デバイスの複雑性が増し、ばらつきへの許容度が急速に厳格化する中で、ウェハー基板製造は、もはや製造の「前段階」ではなく、それ自体が製造そのものになっています。そこで適用される実行規律の水準が、ファブが達成できること、そしてできないことを大きく左右します。これは、半導体ライフサイクルの最も初期段階の実行管理を再検討する必要があることを意味しています。
### ウェハー品質は上流工程で決まる
すべての半導体デバイスは、ファブに入るはるか前に物理特性が決まったウェハーから始まります。結晶方位、欠陥密度、厚みの均一性、表面品質といった特性は、結晶成長やウェハー加工の段階で確立されます。いったん設定されたこれらの特性は、その後のすべての下流工程に引き継がれます。この段階でばらつきが生じると、ファブ側で検出し、ある程度補正することはできますが、完全に取り消すことはできません。
この現実自体は新しいものではありません。しかし、スケーリングによって問題ははるかに深刻になりました。
大口径ウェハー、微細化されたジオメトリ、先進的なデバイスアーキテクチャは、初期工程でのわずかなばらつきの影響を増幅します。かつては許容範囲内だった小さな不整合が、今では下流で重大な影響を及ぼすようになっています。この環境において、基板製造を「緩く管理された準備工程」として扱うことは、ますます大きなリスクになりつつあります。
### スケーリングがどのようにルールを変えるか？
従来、多くのウェハー基板製造工程は、高スループットの量産実行よりも、材料科学やプロセス開発を重視する環境で発展してきました。生産量が比較的少なく、熟練者の判断や手作業によってばらつきを管理できた時代には、それで十分だったのです。しかし状況は一変しました。基板メーカーは、ロジック、メモリ、パワー、特殊デバイスといった分野の需要拡大に対応するため、生産規模を急速に拡大しています。
スケーリングは単に生産量を増やすだけではありません。不整合がもたらす影響を指数関数的に拡大させます。パイロットラインや低ボリューム環境で機能していた運用方法は、スループットの増加、シフト体制の拡張、製品ミックスの複雑化とともに、非常に脆弱になります。大規模生産では、個人の経験や勘だけに頼った一貫性は維持できません。標準化された実行を徹底し、変更を計画的に管理し、プロセス挙動をリアルタイムで可視化するシステムが不可欠になります。
この流れの中で、よりルールに従った実行制御が求められるのは自然なことです。しかし、下流工程向けに設計された「標準的な」運用モデルをそのまま上流に適用しようとすると、ツールと現実の間にズレが生じることが少なくありません。
### 下流工程向けに設計された実行モデルの限界
製造実行システム（MES）は複雑なオペレーションに秩序と統制をもたらすため、多くのメーカーが、下流への影響が顕在化する前に基板製造へMESを導入しようとします。その判断自体は正しいものです。しかし、すべてのMESが基板製造を前提に設計されているわけではありません。ここに、従来の実行モデル、そして多くのMES実装の限界が現れます。
ウェハー基板の製造工程は、下流のファブやパッケージングの環境とは根本的に異なります。プロセスステップはより長く、材料の変化は物理的かつ不可逆的です。品質を理解する上で、種結晶からインゴット、そしてウェハーに至るまでの製造履歴は極めて重要です。さらに、そのワークフローは、ファブで一般的な、短期間で装置中心のサイクルとは異なります。
こうした環境に、別用途向けの実行システムを無理に適用すると、メーカーは回避策に頼ることになります。カスタムロジック、外部のスプレッドシート、手作業による引き継ぎ、時間が経つにつれ、こうした対応は統制ではなく脆弱性を生み出し、下流の成果を最も左右する上流プロセスほど、モデル化されず、一貫して管理されない状態に置かれてしまいます。
多くのトレーサビリティ手法も、このギャップをさらに広げています。下流視点に偏り、「原因の防止」ではなく「結果の特定」を助ける設計になっているからです。
### トレーサビリティを「発見」から「起点」へ
トレーサビリティは、歩留まり解析や不良解析の文脈で語られることが多いものです。もちろんそれは重要ですが、トレーサビリティが最大の価値を発揮するのは、問題が発見される場所ではなく、発生する場所に存在するときです。
基板レベルの系譜やプロセス履歴が不完全、あるいは構造化されていない場合、下流チームは根本原因を「特定」するのではなく、「推測」せざるを得ません。その結果、調査は長期化し、是正策は必要以上に広範となり、意思決定への信頼性も低下します。
本来あるべき姿は、上流の実行プロセスそのものにトレーサビリティを組み込み、各ウェハーが「どのように製造されたか」をシステムによって厳密に記録することです。これにより、問題を事後に追跡するのではなく、下流へ伝播する前に防止できるようになります。
下流での手戻りやスクラップが極めて高コストな業界において、これは非常に重要です。その実現には、「設計段階から信頼性を備え、真の量産規模で再現性あるパフォーマンスを維持できる実行基準」への転換が求められます。
### 「プロダクション・グレード」の実行とは?
基板製造が半導体生産のクリティカルパスに組み込まれるにつれ、期待される水準も変わります。問題は、「プロセスが動くかどうか」ではなく、「安定して、繰り返し、大規模に運用できるか」です。
プロダクション・グレードの実行とは、単なる自動化ではありません。必要なのは次の要素です。
- 現実の製造実態を反映した標準化されたワークフロー
- 安定性を維持しつつ改善を可能にする変更管理
- 過去レポートではなく、実行中のリアルタイム可視化
- 柔軟性だけでなく、稼働率と一貫性で測られる信頼性
メーカーはすでに、ミッションクリティカルなファブに対してはこれらを当然の要件としています。そして今、同じ考え方が上流工程にも必要であると認識し始めています。
### ファブレベルの規律を前工程へ
半導体製造は、常に複雑性との戦いでした。変わりつつあるのは、その複雑性をどこで制御するかです。
デバイスの高度化が進み、許容誤差が縮小するにつれ、業界は上流工程の材料準備と下流工程のデバイス製造との間に齟齬が生じることをもはや許容できなくなっています。結晶成長から完成品に至るまでのライフサイクル全体を通じて、厳格な実行管理が求められます。
ウェハー基板工程を単なる引き渡し地点ではなく、重要インフラとして扱うメーカーは、より高い確信をもってスケールできます。下流リスクを低減し、学習サイクルを短縮し、継続的改善のための強固な基盤を築くことができるのです。
結論はシンプルです。ウェハーがファブに到達する時点で、その結果の多くはすでに動き始めています。この事実を理解し、行動に移すメーカーこそが、次の半導体製造の時代に最も適した存在となるでしょう。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular, Semi
---
### [MES: Past, Present, Future](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-execution-system-past-present-future-in-smart-factories/)
**Published:** December 5, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** The evolution of MES from a simple paper replacement to the backbone of the factory, and what’s next
**Content:**
## What’s Inside
- [ The origins of MES: from artisanal to automated ](#index1)
- [ The birth of MES: digitizing the process flow ](#index2)
- [ MES at runtime: the power of lot tracking ](#index3)
- [ Beyond the basics: automating exception handling ](#index4)
- [ The future of MES ](#index5)
- [ Conclusion ](#index6)
The [manufacturing execution system](/semiconductor-blog-category/manufacturing-execution/) (MES) originated as a replacement to paper-based process flows at a time when no one could have foreseen its potential to become a digital orchestrator of automated factories. This blog explores the journey of the MES from its origins to the present and imagines possibilities for the future.
### The origins of MES: from artisanal to automated
Before the beginning of the Industrial Revolution in the 1700s, manufacturing was an artisanal process. There was no “mass production,” because each product was built from scratch based on tribal knowledge passed down through generations.
The turning point came in the late 18th century when inventor Eli Whitney introduced the concept of a written procedure to document the sequence of steps and parts required to build a product. This innovation enabled repeatability and mass production, laying the foundation for process change management and continuous improvement.
By the early 1900s, assembly lines became the physical representation of this process. Each workstation represented a single operation within the manufacturing process flow. At this stage, manufacturers had developed process instructions that could be replicated at each workstation. However, there was no effective method to reproduce the entire process flow for every item produced. Without a detailed record of each item’s manufacturing process, they had no way to ensure production was consistent, or to provide documentation for verification.
The commercial availability of the photocopier in the 1960s changed that. It enabled manufacturers to economically attach a copy of the process flow to each item. This allowed operators to record actions and enabled audits. This also paved the way for the MES as we know it today; the only missing piece was the computer.
### The birth of MES: digitizing the process flow
The first MES emerged in 1976 as an extension of Computer-Aided Manufacturing (CAM) systems. These systems controlled Computer Numerical Control (CNC) tools and were designed to automate the machining of complex parts. The MES took this a step further by digitizing the entire process flow—replacing paper-based instructions with computerized records.
Early MES systems defined and controlled machining operations, ensured machined product flowed properly through the process flow, and recorded processing history. They introduced capabilities like data collection, specification definitions, and the ability to place product on hold during manufacturing. However, their primary function remained the same: replicating paper process flows in digital form.
As manufacturing grew more complex in the 1980s, the limitations of early MES software became apparent. Manufacturers wanted to integrate with external systems like [Statistical Process Control (SPC)](/semiconductor-blog/quality/better-profitability-with-spc3d/) and automate equipment operations. MES vendors responded by creating customizable frameworks that allowed manufacturers to define process flows, manage equipment states, and track lots more flexibly.
### MES at runtime: the power of lot tracking
Lot tracking represents the MES at runtime. The MES pairs a lot with a process flow, transforming static instructions into dynamic operations. Each step in the process flow has its own resource and data requirements. Some steps require processing equipment while others need chemicals or parts. As a lot progresses along its process flow, the MES records processing history, evaluates quality, and ensures compliance. This granular tracking enables manufacturers to guarantee that each item is built correctly and provides a digital trail for audits and analysis.
### Beyond the basics: automating exception handling
Manufacturing isn’t always predictable. Non-standard scenarios—like out-of-spec measurements, failed tool processing, or engineering experiments—require manual intervention. These exceptions can disrupt productivity and introduce variability.
Modern MES systems, like [the SmartFactory 300works MES](/semiconductor/manufacturing-execution-solutions/300works-full-auto/), address this challenge by automating exception handling. Pre-built scenarios such as the Recovery Run Card and Experiment Run Card enable automated responses to many different types of exception conditions. Whether it’s reworking a lot, splitting a lot for parallel processing, or merging child lots, the MES exception handling scenarios ensure consistent and efficient lot processing.
This level of automation extends beyond product processing to include maintenance, qualifications, and R&D. In a lights-out factory, everything is automated, even non-product events, and this makes integration across the entire Computer Integrated Manufacturing (CIM) system critical.
### The future of MES
As we look ahead, artificial intelligence tools will help the MES move from executing processes to optimizing them in real time. Innovations such as digital twins, predictive analytics, and autonomous decision-making will drive new capabilities. The MES will be able to anticipate failures, recommend corrective actions, and continuously improve operations.
Integration also will expand across the manufacturing ecosystem—from design and engineering to supply chain and customer service—with the MES serving as the backbone that connects disparate systems.
### Conclusion
The journey of the MES from paper to digital, from reactive to proactive, has taken place in keeping with the evolution of manufacturing itself. As such, we can expect it to continue to evolve and redefine what’s possible in manufacturing.
As we embrace the future, the MES will continue to evolve, unlocking new possibilities and redefining what’s possible in manufacturing. Whether you’re building semiconductors, cars, or medical devices, the MES is your [partner in progress](/semiconductor-mes-video-channel/) —a silent force driving the smart factory revolution.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Navigating the challenges of chiplets, 3D stacking and sustainability](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/semiconductor-chiplets-3d-stacking-sustainability-challenges/)
**Published:** September 24, 2025
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** Automation solutions need to keep up with increased complexity
**Content:**
## What’s Inside
- [ Chiplet-based architecture ](#index1)
- [ 3D integration and advanced packaging ](#index2)
- [ Sustainability initiatives ](#index3)
- [ Integration across the value chain ](#index4)
- [ Looking ahead ](#index5)
The semiconductor industry has increasingly embraced chiplet architectures, 3D stacking, and resource-efficient production. As the industry continues to evolve to achieve higher yields and lower costs in a high-demand environment, technologies and initiatives such as these are emerging as part of the next frontier. However, they also inject new challenges and complexities into the manufacturing process. To continue to transition toward more intelligent, flexible, and sustainable operations, fabs need integrated automation solutions that can help mitigate these challenges.
### Chiplet-based architectures
Rather than building monolithic systems-on-chips (SoCs), manufacturers are now assembling modular chiplets—each optimized for a specific function—into a single package. This approach improves yield, reduces cost, and accelerates time-to-market. However, it also creates several challenges such as heterogeneous process flows across different nodes and materials, the need for die-to-die interconnect validation, and advanced packing and test requirements.
To overcome these challenges, manufacturers require solutions that can manage the intricacies of chiplet assembly while maintaining high yield and quality standards. Ideally, solutions should be based on a flexible manufacturing execution system (MES) platform that supports high-mix, low-volume production environments. [SmartFactory PROMIS](/semiconductor/manufacturing-execution-solutions/promis/) is one such solution. Among its features are essential recipe management and traceability tools that can be tailored for multi-die workflows. Additionally, real-time analytics and scheduling engines optimize throughput, even across diverse process steps.
### 3D integration and advanced packaging
Monolithic 3D integration (M3D) is another technique often adopted by semiconductor manufacturers looking to significantly boost performance and increase density. This process stacks multiple layers of transistors and interconnects vertically. The increased density leads to better performance, efficiency and functionality at a lower cost per transistor. As with chiplet production, however, the complexity of this process poses challenges, including having to precisely align the layers and the need for thermal management and defect detection across vertical stacks. Fortunately, automation solutions such as [SmartFactory’s SPC](/semiconductor-blog/quality/better-profitability-with-spc/) provide statistical process control for 3D structures, enabling real-time monitoring and correction of variations. SmartFactory also supports other processes required with [advanced packaging technologies](/semiconductor-blog/manufacturing-execution/assembly-test-part-1/), such as: - Automated inspection workflows for stacked dies
- Run-to-run control systems that adapt recipes based on feedback
- Integrated fault detection and classification (FDC) to identify anomalies early
### Sustainability Initiatives
It’s no secret that semiconductor manufacturing is resource intensive, consuming large amounts of water, energy, and chemicals. With tightening environmental regulations and environmental, social and governance (ESG) goals, fabs are under pressure to reduce their footprint while maintaining production and quality.
Increased automation affords manufacturers the ability to monitor and control systems and processes that impact sustainability. For example, energy and resource optimization modules help fabs monitor and control facility usage. Predictive maintenance tools reduce waste and downtime, while simulation modeling enables them to evaluate the environmental impact of process changes. By integrating sustainability metrics into its automation stack, SmartFactory enables fabs to make data-driven decisions around both operational and environmental objectives.
### Integration across the value chain
Chiplet and 3D manufacturing rely on collaboration between design houses, foundries and packaging providers. Solutions that can integrate across these key partners offer the benefits of increased communication and collaboration and, ultimately, efficiency. SmartFactory’s portfolio supports integration across the semiconductor ecosystem—whether in front-end wafer fabrication or back-end assembly and test. Its unified automation framework enables essential functions such as tool-to-tool communication, supply chain visibility, and secure data exchange. It also supports digital twin technology, allowing fabs to simulate process flows and identify bottlenecks without disrupting production—a critical capability in fast-moving markets like AI, automotive, and consumer electronics.
### Looking ahead
As semiconductor manufacturing grows more complex and interconnected, automation platforms must evolve from static process control systems to dynamic, intelligent ecosystems.
SmartFactory is ready to address these growing needs. Its modular architecture adapts to emerging technologies while AI-driven analytics enable predictive and prescriptive decision-making. By supporting chiplet integration, 3D stacking, and [sustainability](/semiconductor-blog/smart-manufacturing/achieve-efficiency-and-sustainability-goals/), SmartFactory helps fabs stay agile, competitive, and ready for the future.
No single platform can address every challenge in semiconductor manufacturing, but SmartFactory offers the tools to modernize operations today—and scale for tomorrow’s innovations.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [The integration of AI and cloud technologies (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-2/)
**Published:** May 2, 2025
**Author:** Samantha Duchscherer and Emrah Zarifoglu
**Excerpt:** Deciding when and how to move AI to the cloud based on scalability and flexibility
**Content:**
[ Part 1: AI and Cloud Integration ](/ai-and-cloud-integration-part-1/)
## What's Inside
- [ Phases of AI deployment ](#index1)
- [ Synchronizing data ](#index2)
- [ AI resource transition ](#index3)
- [ Edge computing ](#index4)
- [ Cloud advantages for AI developers ](#index5)
Samantha Duchscherer, Global Product Manager, and Emrah Zarifoglu, Head of R&D for Cloud and AI/ML, are among the automation experts working to bring AI powered technologies to SmartFactory’s solutions. In the first article of this two-part series, they defined cloud and discussed the decision-making process companies use when choosing to move to the cloud. As AI transforms industries, understanding its relationship with cloud technology is essential; in this second discussion, they explore how transitioning to cloud could affect deploying AI models.
Sam: Now I can begin incorporating AI into our discussions, which is really exciting for me. Let’s start by discussing the different phases of AI deployment.
When deploying AI, I would say there are three main stages: data preparation, model development, and model deployment. Thinking of the terms we previously
discussed \[[Part 1](/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-1/)\], how do they relate to the different phases of AI deployment?
Emrah: Eventually, all different phases of AI can be done using Docker containers. If you’re doing a production level deployment, it should be in Kubernetes or, ideally, it should be configured by Helm charts. This methodology is what we follow when working with our products and teams, as it represents a widely recognized best practice in the industry. However, it is important to note that these methods are not the only ones available.
When you’re trying to decide which components or phases of AI to move to the cloud, consider where scalability, flexibility and high use of resources are most beneficial. For instance, areas with significant data flow and preparation benefit greatly from the cloud’s scalability. The process of training and evaluating models repeatedly also benefits. During deployment, the cloud provides necessary visibility as you manage the process.
Ultimately, cloud has the most advantages for AI where high levels of scalability and flexibility are needed.
Sam: Yes, it makes sense to move certain aspects to the cloud while keeping others on-prem, but how does that work for the AI data preparation stage? How do we address the challenges of synchronizing data and creating a pipeline across different environments?
Emrah : For data as well as applications, most companies already operate in a hybrid cloud model where part of their data and applications are on the cloud and the rest is on prem. Depending on the technology and location, it’s always a challenge to synchronize the data and bring them together to create a pipeline. It’s easy to suggest moving everything to one cloud, but that’s not always feasible. Realistically, we need to be prepared to operate in a hybrid setting and to address its challenges.
One of the biggest challenges in that environment is securing data and preventing access with malicious intent. In this sense, it’s not the infrastructure but the network that represents the larger vulnerability and area for concern. On the other hand, if your network is secure enough, another challenge could be synchronization across your various technologies.
While having everything in one place is ideal, we don’t impose this solution on our customers but rather help them to feel comfortable and prepared to manage whichever environment (cloud or hybrid) they rely on.
Sam: Shifting the conversation from AI phases to AI resources, I assume there is a transition in resources as well. How does moving to the cloud impact the roles of data engineers, data scientists, and industrial engineers for a customer already using AI in production?
Emrah: The level of change is based on their use and level of connection to the infrastructure. Data engineers are closest to the infrastructure; the tools they use are directly impacted by the technology choices around infrastructure data. They need to be able to operate anywhere using whatever technology is chosen for them.
Data scientists, on the other hand, may or may not be impacted. Their proximity to the infrastructure depends on the tool they use and how they choose to use it.
Industrial engineers are the end users, the furthest removed from the infrastructure. Changes to the underlying infrastructure of the applications they use are likely to go unnoticed.
Sam: I could ask another hundred questions, but to keep it brief, I’ll end with a skeptical question. How would you respond to critics who argue that latency is a significant drawback when utilizing cloud services for AI applications, especially when the intent of AI in some use cases is to make real-time decisions?
Emrah : You can address this concern with a hybrid approach known as edge computing. While still local, edge computing leverages cloud technologies to mitigate latency issues. Companies can decide which components run on the cloud and which run on the edge. As long as there is seamless integration between them, latency should be minimal.
### Cloud advantages for AI developers
As we discussed in our earlier conversation, choosing between a cloud and on-prem infrastructure often comes down to flexibility, scalability, and cost efficiency requirements. However, selecting a cloud environment is also driven by data needs. For handling large amounts of data, whether public or private, cloud technology is essential. This is because tools like containerization and Kubernetes streamline tasks, allowing AI developers to focus more on development rather than data management and infrastructure configuration. Cloud offers several advantages, which makes it a better environment for an AI developer to be working in.
## About the Authors
Samantha Duchscherer, Global Product Manager
Samantha is the Global Product Manager overseeing SmartFactory AI™ activities. Prior to joining Applied Materials Automation Product Group Samantha was Manager of Industry 4.0 at Bosch, where she also was previously a Data Scientist. She also has experience as a Research Associate for the Geographic Information Science and Technology Group of Oak Ridge National Laboratory. She holds a M.S. in Mathematics from the University of Tennessee, Knoxville, and a B.S. in Mathematics from University of North Georgia, Dahlonega.
Dr. Emrah Zarifoglu, Head of R&D for Cloud and AI/ML
Emrah leads the team delivering AI/ML solutions and cloud transformation of APG software for semiconductor manufacturers. He is a pioneer in developing SaaS applications, cloud transformation efforts and building optimization and analytics frameworks for cloud computing. He holds patents in semiconductor manufacturing, cloud analytics and retail science. He also has a well-established research record in planning and scheduling in semiconductor manufacturing. His work is published in IEEE and INFORMS and has been presented in IERC and INFORMS. He earned his Ph.D. in Operations Research and Industrial Engineering from University of Texas at Austin. He holds B.S. and M.S. degrees in Industrial Engineering from Bilkent University, Turkey.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [The integration of AI and cloud technologies (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-1/)
**Published:** May 2, 2025
**Author:** Samantha Duchscherer and Emrah Zarifoglu
**Excerpt:** As AI deployment grows, cloud could pave the way forward
**Content:**
[ Part 2: AI and Cloud Integration ](/ai-and-cloud-integration-part-2/)
## What's Inside
- [ Defining cloud ](#index1)
- [ Private vs. public cloud ](#index2)
- [ Containerization and related concepts ](#index3)
- [ Cost as a factor ](#index4)
- [ State of the industry ](#index5)
- [ Cloud and AI deployment ](#index6)
Samantha Duchscherer, Global Product Manager, and Emrah Zarifoglu, Head of R&D for Cloud and AI/ML, are among the automation experts working to bring AI powered technologies to SmartFactory AI solutions. In this two-part series, they share a conversation about the role of cloud in AI training and deployment. Because, in today’s tech landscape, the concept of ‘cloud’ varies widely, they begin with a discussion around what cloud is and the decision-making process for moving to the cloud.
Sam: I want to discuss AI and its integration with cloud technology, but I think it’s essential to first ensure I have a solid understanding of what ‘cloud’ means. How would you define cloud? Is it as straightforward as “a data center filled with countless machines that you can utilize without having to log into each one separately”?
Emrah: To some extent, yes. Being able to scale these resources dynamically and efficiently without needing to log into each machine individually is an important aspect of cloud. However, it is more than just a data center with a lot of machines. ‘Cloud’ is more of a catch-all. It is often a term that is used to encompass many technologies that provide computing power, storage, and a network infrastructure that is scalable and flexible.
Sam: I also understand that there are options like private and public clouds. Could you explain the key differences between them and how a company should decide which one to use?
Emrah: The difference between the two is basically who owns the infrastructure. A third party owns the infrastructure of public cloud and offers services and resources to the customer. There is a lot of standardization of technology that is easier for the less experienced user, so that is a great choice if you don’t have any other concerns about public clouds. Many companies are satisfied with the public cloud option.
However, when it comes to customization or a desire to use different technology, public cloud can present challenges. When you need flexibility, the containerized, moveable and portable technology is better. My recommendation would be to have a private cloud on premises so you can use containerization and Kubernetes to orchestrate your payload and configure your work according to your needs.
As long as you have an effective flow of communication between your cloud and on prem infrastructure, private versus public cloud is really a matter of preference. The choice comes down to whether you want to own the infrastructure and the responsibility that comes with it, or you want to outsource that so you can focus on your main function. The choice is ultimately use-case specific, driven by the factory’s needs and requirements
Sam: What about all the new terms for cloud such as containerization, Docker, Kubernetes, and Helm charts? How do you even begin to explain these?
Emrah: Most of what we understand as cloud now is derived from the cloud revolution of the early 2000s, which introduced virtual machines as representations of physical machines.
The container is a simple, lightweight virtual machine and containerization refers to a method of packaging an application and its dependencies in a single unit. Docker, Kubernetes and Helm charts are all tools of container management.
Docker is the most common platform that enables you to do containerization by automating the process. You’ll see containerization and the use of Docker at the development stage.
Kubernetes and Helm charts, on the other hand, are used during the deployment phase to manage the deployment at scale. Kubernetes is basically an orchestration tool for managing containerized applications and the Helm charts are pre-configured Kubernetes resources.
Sam: I’m now curious if companies have specific thresholds they follow when making decisions about their cloud infrastructure, or if these decisions are more dependent on individual situations and specific circumstances?
Emrah: Cost plays a big role in this. For instance, if you already have the infrastructure – servers with a good lifetime of 5 to 10 years left—you might not want to incur additional cost for the next five years for new technology. You’d only want to move to the cloud if there are obvious advantages from the standpoint of scaling, flexibility or such. However, it’s really based on a particular use case.
If, for example, you are running a very GPU-heavy application, you’ll probably want to be closer to an on-prem solution rather than a cloud solution because running GPUs on the cloud is pretty expensive. If I’m going to be doing this on a continuous basis for an extended period of time, I would probably rather have a GPU data center on my premises or rented in another physical location because it could be half as much as running this on the cloud. Most often, in a case like this, these are AI companies who are training large language models (LLMs) and others. They have their own data centers or rent them to do that training.
Sam: To wrap up our brief yet insightful conversation and to set the stage for the next series of questions, I’m curious about your perspective on where the industry currently stands. Are we closer to the idea that “AI can’t do it alone,” or are we leaning more towards “AI boom is here, but maybe the cloud isn’t ready”?
Emrah: First, we need to define what we mean by the AI boom. In certain areas, such as training large language models, there has definitely been significant progress. However, this progress often relies on scaling up existing technologies like graphics processing units (GPUs), which isn’t necessarily tied to the cloud.
When we talk about revolutionary changes in AI training techniques and methodologies, like the advent of transformers, we’re building on an existing understanding of these models. This has created a high demand for compute resources, which the current supply of GPUs is needed. From this perspective, the cloud isn’t a bottleneck; it’s the underlying technology, like GPUs, that plays a crucial role.
However, if there’s an inflection point where AI no longer relies on GPUs or we can utilize a different type of computing tool, then the cloud might need to adapt to embrace this new technology. For example, at that point, we could leverage all the connected resources globally to improve our training processes.
One area where the cloud might need to catch up is Kubernetes. While Kubernetes works with GPUs, it doesn’t do so as efficiently as we’d like for large-scale AI training. This is why many prefer non-Kubernetes deployments for significant AI training tasks. So, in that sense, the cloud might need to evolve, but in other areas it’s a different story.
### Cloud and AI deployment
Cloud infrastructure, whether public or private, is crucial for companies that need to process large volumes of data. This is especially true as the deployment of AI increases the demand for computing power, including GPUs. In our next blog, we’ll look more specifically at the relationship between cloud and AI technologies.
## About the Authors
Samantha Duchscherer, Global Product Manager
Samantha is the Global Product Manager overseeing SmartFactory AI™ activities. Prior to joining Applied Materials Automation Product Group Samantha was Manager of Industry 4.0 at Bosch, where she also was previously a Data Scientist. She also has experience as a Research Associate for the Geographic Information Science and Technology Group of Oak Ridge National Laboratory. She holds a M.S. in Mathematics from the University of Tennessee, Knoxville, and a B.S. in Mathematics from University of North Georgia, Dahlonega.
Dr. Emrah Zarifoglu, Head of R&D for Cloud and AI/ML
Emrah leads the team delivering AI/ML solutions and cloud transformation of APG software for semiconductor manufacturers. He is a pioneer in developing SaaS applications, cloud transformation efforts and building optimization and analytics frameworks for cloud computing. He holds patents in semiconductor manufacturing, cloud analytics and retail science. He also has a well-established research record in planning and scheduling in semiconductor manufacturing. His work is published in IEEE and INFORMS and has been presented in IERC and INFORMS. He earned his Ph.D. in Operations Research and Industrial Engineering from University of Texas at Austin. He holds B.S. and M.S. degrees in Industrial Engineering from Bilkent University, Turkey.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [From downtime to uptime: the case for spares kitting in modern semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/spares-kitting-in-semiconductor-manufacturing/)
**Published:** December 11, 2025
**Author:** Yoram Barak, Global Product Manager
**Excerpt:** The right parts, at the right place, at the right spec and in the right time
**Content:**
## What’s Inside
- [ From reactive to prescriptive maintenance management ](#index1)
- [ The plug and play spares and ERP module advantage ](#index2)
- [ Spares kitting advantage ](#index3)
- [ Use case example ](#index4)
- [ The impact: Persona driven efficiency ](#index5)
- [ Conclusion ](#index6)
### From reactive to prescriptive maintenance management
According to a [NIST report](https://nvlpubs.nist.gov/nistpubs/ams/NIST.AMS.100-34.pdf)[1](#references), preventable maintenance issues across U.S. discrete manufacturing (which includes semiconductor manufacturing) resulted in $119.1 billion in annual losses as of 2016. These losses stem from:
- Increased downtime
- Higher defect rates
- Lost sales due to delays and defects
- Inventory surpluses caused by maintenance inefficiencies
Smart manufacturing—often called “Industry 4.0”—is characterized by a shift from reactive and preventative maintenance approaches to more predictive and prescriptive operations, known as the “four ‘ives’ of smart manufacturing.” This shift is foundational, enabling factories to support all these capabilities at once. While some processes, like detecting component degradation, are moving toward predictive and prescriptive methods, others (such as random failure detection) remain reactive (Figure 1).
Maintenance represents an area of manufacturing where there is an opportunity to apply these advanced methods, because improvements can significantly boost factory throughput, quality, and cost efficiency. The application of smart manufacturing to maintenance is called Prognostics and Health Management (PHM), which connects failure mechanism studies to system lifecycle management. PHM encompasses equipment health monitoring (EHM), predictive maintenance (PdM), and maintenance assessment. These tools work together to reduce unscheduled downtime and improve uptime[2](#references).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/12/figure-1-prescriptive-maintenance-2-scaled.webp) Figure 1: The journey from reactive to prescriptive maintenance
### Plug and play spares and ERP modules advantage
In a recent [blog](/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/), we discussed the complexity in modern semiconductor fabs that rely on thousands of highly specialized tools. Each of these tools may contain tens of thousands of parts sourced from hundreds of suppliers. The problem they have is part availability and association. To maintain high Overall Equipment Effectiveness (OEE), fabs must ensure that the right spare parts are available at the right time. This requires tight coordination between physical systems (suppliers, warehouses, tools) and logical systems (ERP and maintenance management platforms). A key issue is associating part numbers (P/Ns) with maintenance work orders efficiently.
SmartFactory Maintenance Management addresses this challenge with two plug-and-play modules.
- **Spares module:** Links work orders to serialized and consumable parts, and tracks part consumption during preventive maintenance.
- **ERP module:** Enables fast integration with ERP systems using standardized data dictionaries and server-side rules. It supports (P/N) tracking, queries, and return flows.
The benefits this poses for semiconductor fabs include:
- **Improved mean time to repair (MTTR):** Faster maintenance due to better part-to-work-order association.
- **Lower integration costs:** Simplified ERP connectivity via standardized touchpoints.
- **Enhanced data traceability:** P/N usage and history are easily tracked.
- **Reduced system complexity:** P/Ns can move between systems without duplication.
- **Boosted OEE:** Outlier parts affecting Mean Time Between Failures (MTBF) can be identified and addressed.
### Spares kitting advantage
Spare parts kitting in the semiconductor industry is the process of grouping all necessary components and tools for a specific maintenance or repair task into a single, pre-packaged kit. This method streamlines operations by ensuring that service engineers or production staff have all required items readily available, minimizing machine downtime and enhancing overall efficiency in the demanding cleanroom environment.
Among the key aspects and benefits of this process are:
- **Minimized downtime:** Technicians don’t spend valuable time locating individual parts in a warehouse because a complete kit can be quickly deployed when a need arises. A kit with all necessary parts is available through the ERP. This is done via simpler parts management—stores deliver one pre-packed kit rather than spending time searching for parts, bundling them, processing parts, etc. This saves time for both the technician and the warehouse worker (in ERP). This will also improve efficiency and productivity for engineers, as they can focus on high-value repair and assembly tasks rather than material handling and searching for parts. This accelerates production cycles and service response times.
- **Enhanced inventory management:** Each kit is managed under a single stock keeping unit (SKU), which simplifies inventory tracking and control. This makes demand forecasting easier and helps prevent overstocking or stockouts of individual, often expensive, components.
- **Reduced errors and quality control:** Pre-verified kits ensure that all the correct components, with full traceability and quality assurance, are available before a job starts. This minimizes the risk of using incorrect or defective parts, which is crucial in a high-precision industry like semiconductor manufacturing.
- **Cost savings:** Kitting reduces administrative overhead (fewer purchase orders are needed), lowers storage costs, and minimizes waste from obsolete or damaged parts.
- **Optimized logistics:** Kitting simplifies shipping and logistics by consolidating multiple items into a single package, reducing handling and transport costs. Kitting can be performed in-house or outsourced to a third-party logistics provider with expertise in handling sensitive electronic components and a network of strategic stocking locations to meet service level agreements.
By standardizing the parts needed for common repairs or maintenance schedules, semiconductor manufacturers can build a more resilient and efficient supply chain.
In recent release we enabled an enhancement to the spares module by improving kitting functionality to address the above.
There are several key benefits of SmartFactory Maintenance Management spares kits, including:
- Simplified ordering: A single request for a kit replaces multiple part orders.
- Streamlined logistics: Related components are grouped for easier transportation and tracking.
- Improved maintenance workflow: During maintenance, all parts in the kit are installed, and the removed parts are returned in the same container.
There are two types of spares kit, a process kit and a consumable kit. The process kit contains durable serialized parts and follows the serialized part state model and transitions. A consumable kit contains consumable non-serialized parts and follows the non-serialized part state model and transitions. A kit is considered a part, and all actions applicable to parts can also be performed on a kit. This can be done by creating a work order estimate in the work order parts section and executing relevant actions.
### Use case example
The core maintenance management software personas and their primary roles relevant to this use case are listed in table 1 below.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/12/table-1-core-maintenance-1-scaled.webp) Table 1: Core maintenance management software personas and roles
In a high-volume 300mm semiconductor fab, a critical photolithography tool fails during peak production. The maintenance team scrambles to diagnose the issue and initiate a corrective work order. However, the required parts—scattered across multiple suppliers and storage locations—are not readily available. Some are serialized, others consumable, and a few are missing due to ERP mismatches. The result?
- 12+ hours of tool downtime
- Missed production targets
- Increased defect rates from rescheduling stress
- Excess inventory from over-ordering “just in case” parts
To address this, the fab implemented SmartFactory Maintenance Management Spares and ERP Modules, with a focus on spares kitting. Table 2 shows how each persona plays a critical role in making it work:
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/12/table-2-role-in-kitting-2-scaled.webp) Table 2: Role in kitting workflow based on persona
### The impact: persona-driven efficiency
With kitting in place: - The maintenance planner triggers a single kit request.
- The materials planner ensures the kit is stocked and delivered.
- The technician receives a pre-packed container with all required parts.
- Used parts are returned in the same container for traceability.
- The operations supervisor sees a 50% reduction in MTTR and improved OEE.
You probably ask yourself what the economic impact of a 12-hour downtime in 300mm fab is. Well, a 12-hour downtime in photolithography in 300mm fab with 30,000 wafers start per month (WSPM), with average revenue per wafer of $2,000, and photolithography contribution to cycle time of ~20-30% could cost a >$1 million in lost revenue, not including: - Ripple effects on downstream tools
- Increased defect rates due to rescheduling
- Labor and recovery costs
### Conclusion
Kits supported in Spares and ERP modules provide a structured approach to grouping related parts. This allows for efficient transportation, simplified ordering, and improved maintenance workflows. A kit serves as a physical container for parts meant to be replaced together during maintenance, reducing downtime and enhancing operational efficiency. It also simplifies procurement, transportation, and maintenance activities, ensuring that operations are more efficient and less prone to delays. If you’re ready to rethink how your fab handles maintenance, [reach out](/connect/?page_source=https://appliedsmartfactory.com/semiconductor/manufacturing-execution-solutions/alarmmanagement/).
### References
[1] Economics of Manufacturing Machinery Maintenance – A Survey and Analysis of U.S. Costs and Benefits. NIST Advanced Manufacturing Series 100-34.
[2] Toothman et al., 2023. Overcoming Challenges Associated with Developing Industrial Prognostics and Health Management Solutions. Sensors 2023, 23, 4009.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Taking factory quality to the next level, combining data in a cohesive manner](https://appliedsmartfactory.com/semiconductor-blog/quality/taking-factory-quality-to-the-next-level-combining-data-in-a-cohesive-manner/)
**Published:** October 18, 2021
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** Quality improvement strategies that provide users with recommended actions.
**Content:**
Quality improvement strategies that provide users with recommended actions.
[pdf-embedder url=”/wp-content/uploads/2021/07/Taking-Factory-Quality-to-the-Next-Level.pdf” height=”1000″]
[ Download this PDF ](/wp-content/uploads/2021/07/Taking-Factory-Quality-to-the-Next-Level.pdf)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [零缺陷战略：引领汽车制造电子革命](https://appliedsmartfactory.com/semiconductor-blog/quality/automotive-manufacturing/)
**Published:** March 7, 2024
**Author:** Selim Nahas and Manan Dedhia
**Excerpt:** 提高汽车制造的良率并降低非质量成本
**Content:**
汽车制造商在很大程度上依赖于获得所需的大量电子零件，以满足高性能汽车的需求。 事实上，随着零件数量不断增加，减少故障和加强质量控制的需求也变得复杂而昂贵。 制造商若要真正制定零缺陷战略，就必须将人员、技术和经济因素考虑在内。 了解汽车制造商应如何以及为什么要大胆探索建立零缺陷战略的新方法。
[ 相关阅读 ](/zh-hans/semiconductor-blog/automotive-quality/)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [运行时配方控制的本质](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
**Published:** July 8, 2022
**Author:** Eric Warren
**Excerpt:** 最新版本的 SmartFactory Recipe Management，为运行时配方控制提供更佳的数据同步选项。
**Content:**
配方管理（RM）的基本要求是管理成千上万个配方。 为了在工厂中打好实现配方控制的基础工作，制造商必须将其 MES 和设备之间的信息进行同步。 如今，RM 系统必须适应单个用户组织的不同偏好，提供灵活的配置选项。 部分设备所有者可以将配方存储在设备的单个文件夹中， 其他所有者可以根据不断变化的技术、产品或特定约定，创建特定文件夹和子文件夹。 无论采用哪种方法，设备上定义的配方名称和位置，都必须在运行时进行同步。
为更好地管理 MES 和设备之间的数据同步，由Applied E3™框架赋能的Applied SmartFactory™ Recipe Management System (RMS) 2.1.0 版，专为设备配方主体和配方参数控制量身打造。 和以往一样，这个新版仍然建立在经验证的大批量制造方法的基础上，包括完全限定配方映射的配方解析模式。
### 减少跨应用变更
借助2022 年 4 月发布的 SmartFactory RMS 2.1.0 版，我们的愿景是将配方管理作为运行时配方控制的“本质”，减少跨应用变更。 现在，一个简短的配方名称（例如，配方\_产品\_A）是通用标识符，而在整个系统内*配方名称**和**目录*（设备上定义的）决定完全限定配方：
**配方目录 + 配方名称（简称）= 完全限定配方**
在以 MES 为中心的环境中，限定配方包含在 MES 路径定义中。 这种方法虽然有效，但是如果在设备上修改了配方目录或配方名称，需要在 RM 系统和 MES 中相应地进行变更。 这个挑战在于，从组织角度讲，负责在设备上创建和修改配方的人和负责 MES 路径的人，通常分属不同团队，执行不同的时间表。
对于这种情况，我们的 RMS 通过增强和扩展运行时解析模式，提供外部简称转换建模和外部上下文解析，在 MES 和设备之间实现数据同步更新，效率更高。
- **外部简称模式。** 外部简称模式从 MES 定义中继承简称配方名称，在 RM 中提供配方目录转换建模接口，来生成完全限定名。 将配方目录从 MES 定义中剥离可以实现组织响应，例如根据产品更改或引入新技术时在设备上添加或修改文件夹名称。
- **外部上下文解析。** 该功能通过使用 MES 的上下文信息在运行时解析完全限定名，来增强灵活性。 例如，可以对“操作+设备+产品”的关键组合进行建模，来获得适当的配方（例如，配方目录+配方\_产品\_A）。 将配方目录和配方名称从 MES 路径定义中剥离，可以灵活地满足各个组织的偏好。
在任一模式下，SmartFactory RM 都定义并解析完全限定名映射，以最大限度减少 MES 路径的修改。 这反过来使 RM 团队能够独立运作，同时保持运行时配方控制的同步。
### 欲知 SmartFactory Recipe Management 2.1.0 版更多信息
[ 请与我们联系 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi, Newly Released
---
### [运用高级计划和排程解决方案提高生产率](https://appliedsmartfactory.com/semiconductor-blog/planning/boosting-productivity-with-advanced-planning-scheduling-solutions/)
**Published:** November 25, 2021
**Author:** Madhu Mamillapalli, Global Product Manager, Planning Solutions
**Excerpt:** 简化设备生产流程和提高生产率的新方法。
**Content:**
简化设备生产流程和提高生产率的新方法。
[pdf-embedder url=”/wp-content/uploads/2022/04/Advanced-Planning-Scheduling-Solutions_Chinese.pdf” height=”1000″]
[ 下载PDF文件 ](/wp-content/uploads/2022/04/Advanced-Planning-Scheduling-Solutions_Chinese.pdf)
**Semiconductor Category:** Semiconductor Planning
**Semiconductor Tag:** Semi
---
### [详解派工和排程算法对工厂 KPI 的影响](https://appliedsmartfactory.com/semiconductor-blog/scheduling/dispatching-scheduling-algorithms-impact/)
**Published:** August 1, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** APF Fusion™ 支持派工和排程算法的集成。
**Content:**
为了改善设备瓶颈情况，半导体制造工厂往往会在8-10 个生产区域启用派工规则，同时也会在 4-5 个生产区域部署排程系统。 每种算法通常会涉及 5-10 个参数，生产管理人员通过调整这些参数值来优化产线运营效率； 参数值的调整频率也较高，往往需要一周多次。
由于很难在离线环境下重新创建复杂的逻辑，因此工厂在生产环境中通过软运行来分析派工和排程算法对产线的影响。 但是，在生产环境中做这种分析，可能会导致停机或给产线的生产带来负面影响。
企业通过动态仿真功能来预测工厂的每周产量、识别瓶颈设备、规划设备维保时间，并为各个区域设置生产目标。 他们往往使用简单、基本的派工规则，而不是生产中实际使用的规则，这将导致仿真结果和产线实际产出之间存在差异。 如下图 1\[1\] 总结了在批次层级观察到的仿真与实际生产之间的典型差距。 在这个例子中，差距反映了批次实际经过的站点数和仿真情形下站点数之间的差值，并且在一段时间后，该差值大于允许的阈值。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig1-min.jpg) 图 1：仿真与生产在批次层级的差距对比图
为了应对这些挑战，应用材料公司开发了 APF Fusion 模块，它将基于应用材料公司 APF Real-Time Dispatcher™ (RTD) 规则在生产环境中开发的派工和排程算法集成到了SmartFactory AutoSched™ 的仿真模型中。 我们的 APF Fusion 模块能够让工厂直接重用生产线的派工规则，而无需工程师在 AutoSched 仿真模块中再定义这些规则。 图 2 显示了 APF Fusion 的架构。 Fusion 引擎充当 AutoSched 的调度器。 Fusion 和 APF Dispatcher 之间的主要区别在于， Fusion 被设计为在内存中使用 Autosched 的工厂数据，而不是来自存储库中的数据。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig2.jpg) 图 2：Fusion 的架构
如需创建仿真和生产的派工规则，须遵循如下步骤，如图 3 所示。 - 您需要创建单独的块“分支”，以便从相应的数据源读取输入数据。 然后，使用 Switch-in 块来切换和标识规则运行时所需的输入数据， 它们可能是来自 AutoSched 模型（如果规则运行在仿真环境）或 MES（如果规则运行在生产环境）。
- 由于AutoSched 模型架构与MES 数据架构不同，因此该规则使用一个功能块来重命名 AutoSched 模型中的数据元素，并执行类型转换（如有必要），以便其名称和类型与 MES 中相应数据元素相匹配。 然后，规则的逻辑可运用相同的输入参数，执行相同的操作，而不用考虑数据的来源情况。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig3.jpg) 图 3：使用 APF Fusion 创建规则
使用集成派工和仿真解决方案的好处在于，工厂可以在生产系统环境中，利用实际的产线数据来实现持续改进。
### SmartFactory 集成派工和模拟解决方案的优势
- 在不影响生产的情况下评估派工规则/排程策略的更改
- 确定产线停工和其他场景对 KPI 的影响
- 降低规则改变可能带来的生产风险，增强信心
- 降低拥有成本
- 无需使用 C++ 扩展来对派工和排程策略进行建模
- 在生产和仿真环境间共享规则
- 在生产和仿真环境间共享KPI 报告
- 消除不必要逻辑，降低规则的复杂性
- 在线获取 RTD 培训资源，使得工厂能够在安全的沙箱中进行试验
**参考**
图1 – \[1\] [Proceedings of the 2013 Winter Simulation Conference, AN INTEGRATED APPROACH TO REAL TIME DISPATCHING RULES ANALYSIS AT SEAGATE TECHNOLOGY, Gowling, Peterson, O’Donnell, Kidambi, Muller](https://dl.acm.org/doi/10.5555/2675983.2675864)
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [英飞凌科技介绍他们如何优化生产效率](https://appliedsmartfactory.com/semiconductor-blog/use-cases/infineon-technologies-describes-how-they-optimize-productivity/)
**Published:** November 25, 2021
**Author:** Michael Förster
**Excerpt:** 使用与实时数据集成的派工、规划和排程解决方案，提高工厂生产效率。
**Content:**
使用与实时数据集成的派工、规划和排程解决方案，提高工厂生产效率。
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Semi
---
### [汽车质量生产：力求实现零缺陷](https://appliedsmartfactory.com/semiconductor-blog/quality/automotive-quality/)
**Published:** May 23, 2022
**Author:** Selim Nahas and Manan Dedhia
**Excerpt:** 了解如何通过加倍坚持“零缺陷”的思维模式来引导汽车电子革命，从而降低质量生产以外的成本。
**Content:**
近 10 年来，对汽车电子零部件的需求量呈爆炸式增长。 例如 2016 年，一辆顶配宾利需要 110 磅电缆线束与 90 台计算机进行连接。 到了 2020 年，消费者购买的大多数汽车都已满足了类似的布线和连接要求。 汽车行业是对前沿供应链技术依赖程度最低的行业之一，选择使用在传统节点上制造且可靠性得到验证的零部件。 大多数传统节点晶圆厂采用半自动到自动化生产方式，且已在过去 15 到 30 年间都在用这种方式进行生产。 尽管这种生产方式预计在未来 5 年内不会发生变化，但是推动使用 150mm 和 200mm 生产设施的这一决定的经济因素也在发生变化。 汽车电子委员会 (AEC) 和国际标准化组织 (ISO) 最近发布了关于提高安全性、可测性设计 (DFT) 和可制造性设计 (DFM) 的公告，其体现了 L4 级和 L5 级自动驾驶汽车、汽车原始设备制造商 (OEM) 和 1 级供应商兴起的必然性。 上述公告理所当然地加倍坚持了“零缺陷”的思维模式，以降低质量生产以外的成本。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/automotive-electronic-scaled.jpg) 图 1：汽车电子革命
### 现场退货剖析
国际汽车工作组 (IATF) 的标准在本质上要求我们努力实现零缺陷。 纵观目前的行业状况，数据表明汽车供应链的缺陷零部件数约为百万分之一 (PPM) 或以上。 在了解构成保修退货或零公里故障（图 2）的现场退货的情况时，现场预估表明，大约 25% 的故障来自前道晶圆厂。 在上述的数据中，出厂后的 50% 的故障均已接受了参数测试，但是依然无法检测到问题。 另有 30% 未接受测试，因此无法检测出故障。 另外 15% 为未定义项，也就是说我们无法找到故障的特定原因。 第三类本质上是未知项。 在上述这些情况下，无法部署真正的纠正措施，检测误差依然存在。 最后，业界人士对大约 5% 的故障根源是来自供应链内部的这个结论无法达成统一的意见。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/packaging-contributions-scaled.jpg) 图 2：晶圆和包装对现场退货的影响。
### 供应链的疑难杂症
晶圆厂、封装和电气测试构成了当前的供应链，三者在评估时的作用相当于质量门禁，随着检测越来越细致，成本也会越来越高。
从晶圆厂角度来看，汽车零部件可分为以下几类：安全/高级驾驶辅助系统 (ADAS)、推进系统和信息娱乐系统。 首先，安全/ADAS 部分包括在较大节点上制造的传感器（微机电系统 \[MEMS\]、光学、温度），或专业晶圆厂（GaAs、GaN、SiGe 等）生产的射频 (RF) 组件，后者的生产自动化和可检测性低于平均水平。 第二，随着电动汽车 (EV) 的出现，带来了越来越多的产品需要推进系统，他们的工艺制程在 180nm 至 32nm 范围之间。 这个部分包含动力组件和发动机控制装置 (ECU)。 在某种程度上，上述零部件应被视为任务关键型组件，对可靠性的要求更高。 最后，信息娱乐系统无需相同水平的可靠性，在对最新、最大晶圆节点抽样时具有一定的灵活性。
鉴于汽车供应链中抽样的晶圆节点范围广泛，因此我们要遵守多种质量等级规定。 降低每个组件的成本以实现利润最大化，还意味着将可接受的质量水平降至最低可接受限度。 每一个检测步骤都不会为零部件增值，因此相应的成本会被进一步传递到下游。 这意味着，即使业内最好的晶圆厂也不提供 PPM 等级检测，亦不为批量生产的零部件考虑相应的检测。 随着使用较旧的节点或专业技术，这种情况会进一步恶化。
电气测试是检测零部件缺陷的最佳机会；这种测试需要对封装的零部件进行晶圆探针或终极自动测试设备 (ATE) 等测试。 理论上，如果零部件特征已被完整界定，并采用已知的低缺陷率技术生产，电气测试步骤中就可测出剩余的 PPM 等级故障。 表征的界定取决于： 1) 可模拟所有故障模式的设计失效模式及后果分析 (DFMEA)； 2) 产品工程师可测试涵盖所有客户任务配置文件； 3) 随着零部件中软件组件数量的增加，确保始终保持数据保真度。
大多数零部件没有晶圆级可追溯性，这进一步降低了将故障与晶圆厂工艺关联的能力。 面对紧迫的客户时间表和成本压力，我们再次看到此阶段的可接受质量水平降至最低限度，因此出厂产品在电气测试时无法获得检测的全部益处。 这导致多数客户质量问题与测试问题相关，还会导致非质量成本的增加，进一步激励我们采用整体性方法处理进度和安全的问题。
### 拟定问题
如果我们考虑采取一种策略以更有针对性地实现零缺陷概念，那就必须改变当前的工厂运营方式。 大多数传统设施采用半自动或手动生产流程。 这意味着他们从根本上拥有大量的单点解决方案和准则来管理质量标准。 也就是说，他们既没有捕获有效流程管理所需的所有数据，也无
法以快速有效的反馈方式分析这些数据。 根据现场退货和内部故障，我们已经能够了解这个策略对我们有多大作用。 如果不完全重新考虑流程，我们不太可能稳定地突破 1PPM 障碍。
换句话说，我们无法扩展检测范围，加上无法确保我们的测试覆盖率；更甚者，我们有太多的案例无法完全确定根本原因。 所有这些问题都源于对质量管理采用了拼凑的方法以及对无法统筹质量数据的管理。 采用一套整体化方法就可以简化信息共享，并促进一次性正确决策（图 3）。 那为什么各个系统还未采用整体化的方法呢？
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/holistic-intelligent-scaled.jpg) 图 3：改用整体化和智能化的系统。
### 采纳必要更改
单点解决方案的根本缺陷在于，它们无法解决在晶圆厂层面观察到的、具有挑战性的问题，包括封装和表面贴装线。 这个问题的解决方案必须采用整体化的方法。 在这种情况下，整体化的方法是指洞察整条生产线的能力。 在单一生产设施之外，整体化的方法还意味着将整个供应链作为一个实体。 此外，我们必须引入新的信号检测准则才 可成功管理图表缩放。 当控制图根据已知参数完成了正确的设置，它就可以相应地检测到各种异常；如今许多系统都基于此类理念而开发。 尽管这在原则上是正确的，但在一个只有骨干人员的生产设施中管理 100,000 张图表，这样的工作量令人生畏。 无论控制措施和规格限制如何，每个测量值都被赋予与设备整体质量相关的含义。 换言之，它是审查总体变异对零部件性能和可靠性影响的能力。 该方法目前未在行业中实施。
### 实施和培训的成本
半导体晶圆厂适应新自动化解决方案的速度始终伴随有各种问题，进而阻碍了晶圆厂快速改变质量生产的能力。 如今的多数自动化系统基本上仍然沿用过去 20 年所见的相同范式构建 – 由 Western Electric 规则驱动的图表和基于错误图表的失控行动计划 (OCAP)。 当行业采用简化的自动化解决方案时，传统制造设施早已摊销了其建筑成本和折旧制度，仅靠运营要素来维持业务的营运。 这种情况就导致可以投入新开发的资源少之又少，原因是这些工厂的盈利能力无法支持解决任何单一问题所需的投资。
整体自动化解决方案解决系统性问题，而非单一差距的问题。 各家工厂的设施不同，50 万美元很有可能代表着 0.5% 的利润，这会大量侵蚀薄弱的利润。 此外，投资回报要么太小，不足以证明冒风险的合理性，要么需要很长时间才能实现。 单点解决方案投资范围则为 15 万美元至 75 万美元，这是难以突破的障碍。 了解它们的要求、所处领域的复杂性以及支持它所需的信息技术 (IT) 基础设施需要大量的投资。 定义和测试那些“可取代大量当前自动化举措的”破坏性系统需要大量成本。 除非解决方案能够为质量生产提供系统性解决方案（即实现多个高价值目标），否则无法对这些设施进行投资。 这些范式需要跨越整个供应链。
这些工厂中多数人的工作重点并非开发新的自动化解决方案，而是以具有成本效益的方式生产可靠的零部件。 因此，通过技术构建整体化和简化的质量体系等相关的期望在这些工厂中并不现实。 这将需要改变财务和生产制造的思维方式。 强大的整体化质量计划需要针对操作人员建立自动化和学习系统。 尽管有很多机会可以将过去的手动任务和决策自动化，但是人们对理解信号和质量指标的含义的期望仍然很高。
### 走向零缺陷
传统工厂必定存在不同程度的自动化需求。 自动数据采集是很好的起点，然后在集中警报管理系统中连接信号，并防止将材料移动到不应运行产品的工艺设备中。 加工过程中，减少人为失误的需求也很明显。 配方管理系统与集中配置管理系统一样发挥着关键作用。 自动化层到位后，扩展能力得以增强。 例如，当晶圆厂通过统计制程控制 (SPC) 方法访问原始晶圆测量数据，工程人员就可以将其用于隔离晶圆内的变化问题。 新产品认证非常耗时，生产准备过程可能很慢，并且可能无法确定所需的测试类型。 对生产设施中变异来源了解得越多，快速验证新产品的机会就越多。 这个理论将直接影响测试覆盖率差距，使 30% 的现场故障持续存在。
将这些传统的良好标准转为整体化的方法，需要部分集成基础设施。 第一步是定义在此情况下的“整体”的意义。 整体是理解制程步骤相互依赖行为的能力。 控制计划说明了与任何产品相关的已知测量值。 自动化系统将需要为用户提供“定义不同制程步骤相互依赖关系”的能力，如控制计划和制程故障模式和影响分析 (FMEA) 中所述。 在运行时，系统将使用控制计划中定义的、来自多个制程步骤的数据，并概述哪些数据与我们预期的 特定制程中不相符。 这需要通过实时数据工具完成，原因是单个决策中，每位用户需要通过 12 至 20 个站点访问 15 个参数。 每个站点都需要通过各自的统计数据进行细分，以揭示晶圆内的差异概况、同一制程中晶圆间的差异，以及来自上游步骤中的差异。 这个方法将减少最终测试前的变化，减少故障零部件出厂的机会。 最重要的是这个方法为最终测试带来了有效性的变化。 更严格的变异验证，将更有效地捕获更大程度的不合格。
另一个关键区别是，整体化系统不仅是根据错误驱动的，而且对规格限制内的变化也很敏感。 数据表明，这种情况发生在良率 88% 到 92% 的工厂中。 前道晶圆厂与封装操作相结合，故障率约为 0.76PPM。 符合规格限制的设备最终将可以运作，但性能或寿命各异。 晶须和桥接等制程问题将避开上述众多测试，从而导致在现场发生短路的故障。 因此，自动化系统可以让用户叠加各个生产步骤的定性，以此来度量特定质量问题的可接
受范围。
确实，其他因素对整体故障率有一定影响，包括可能在整个供应链多处发生的静电损坏和其他形式错误处理。 因此，突出的质量问题需要进行快速的谱系分析，其中包括设计问题。 比如已经生产和使用了很长时间的零部件，在超出了最初设计的范围下被使用。 这对现场故障构成了大约 0.15PPM 的贡献。 “未知”的案例代表了大约 0.21PPM 的故障贡献，并且是供应商的主要责任。 在无法确定原因的情况下，小型供应商将承担故障责任，并将从与大型汽车制造商的协议中扣除成本。 如果这种能力可以自动化跨越前道和后道，并最终纳入表面贴装技术 (SMT) 生产线，那么就能为任何特定设备和原因快速识别问题。 在这种情况下，解决速度将影响责任成本，更重要的是影响安全性。 除非新自动化系统的设计采用这些指导原则，否则任何供应链都将无法有效地趋向零缺陷（图 4）。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/zero-defects-scaled.jpg) 图 4：力求实现零缺陷
**引用**
原始设备供应商协会
Automotive defect recall report2019
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [更快地解决 SPC 和 FDC 违规问题](https://appliedsmartfactory.com/semiconductor-blog/quality/spc-and-fdc-violations/)
**Published:** March 7, 2023
**Author:** Todd Snarr
**Excerpt:** 使用 SmartFactory Knowledge Advisor 内建 OCAP 解决方案，来扩展工厂的自动化智能能力。
**Content:**
您知道工厂里将近 **50%** 的报废是人为错误造成的吗（参见图 1）？ 实现异常管制计划 (OCAPs) 的自动化是一个获得投资回报的重要机会。
*OCAP* 是供工程师为了解和纠正流程或生产设备上的缺陷而遵循的计划。 例如，如果统计过程发生异常，相关设备的处理就会停止，从而允许工程师执行一系列任务，使设备尽快恢复在线状态。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig1-min.png) 图1： 虽然其他原因通常被认为是停机的最大原因，但人为错误是停机的最大因素
### 数据可用性、可访问性和完整性
但是，并非所有的任务都是现成的，或是平均地分配给工程师，并且没有一个流程中的单一参数数据集能够提供变异来源的完整图景。 用于控制计划的数据通常驻留在不同的组件中，如 SPC 或 FDC，它们各自具有的集成方法和数据结构模型。 在某些情况下，数据不存在、不完整，或者是在某个人的笔记本电脑上手动进行维护。 此外，正确执行恢复任务需要工程师制定适当的计划，阅读并理解步骤，然后正确地执行这些步骤。
### 内建方法的价值
如今的晶圆厂需要一种更具凝聚力的方法，一种管理信息集并扩展设施自动化智能的方法。 图 2 概述了这种方法的需求，并重点介绍了实现具有适当功能的 OCAP 解决方案的价值。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig2-min.png) 图 2： 使用适当的自动化策略，OCAP 解决方案可使解决 SPC 和 FDC 违规的速度提高 40%
### 减少可变性的集成工作流
为成功实施 OCAP 的这些组成部分并在您的工厂中扩展自动化智能，SmartFactory Knowledge Advisor 提供集成的工作流引擎，该引擎可以：
- 在工作流中如上下文模式匹配 (CPM) 和数据模式中嵌入 AI 功能，帮助引导用户
- 让用户能够制定解决异常的行动计划
- 通过提供具有直观用户界面体验的工作流详细信息来指导用户解决错误（参见图 3 示例）
- 减少与错误解释因果关系相关的人为可变性
- 管理行动跟踪，识别以前的故障排除活动
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig3-min.png) 图3： 此示例计划说明了浏览器上 Web Analytics 中用户界面的可用性，并展示了如何在右侧的主面板中轻松查看左侧所选步骤的详细信息
### Knowledge Advisor 有何与众不同之处？
许多第三方或内部 OCAP 解决方案缺乏多规程方法所需的“自动化挂钩”。 例如，它们可能只与 SPC 应用一起工作，而缺乏从其他系统收集数据以帮助排除异常故障的能力。
然而，Knowledge Advisor 可容纳来自任何应用材料 E3™ 解决方案的数据，包括高级过程控制 (APC)、SPC、FDC 和配方管理 (RM)。 如图 4 所示，该解决方案利用应用材料 E3 的全部功能，促进从各种来源和 AI 功能收集数据。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig4-min.png) 图4： Knowledge Advisor 是唯一一套用于构建与 SmartFactory E3 系列完全集成的异常解决行动计划的解决方案
通过使用通用平台，工程师可以更好地管理配方、设备、SPC 和 FDC 违规。 如果您将 E3 用于 FDC 或 SPC，那么拥有一个通用平台可以为您减少跨 CIM 的管理点。
### 结论
在当今的晶圆厂中，人为错误是造成报废和停机的最大原因。 自动化的成本必须对照回收和报废的成本来考虑。 因此，关键是衡量什么样的自动化水平适合保持具有竞争力的利润率和对未来增长的投资。 Knowledge Advisor 旨在为客户提供具有成本效益的灵活性。 凭借其集成和准确决策的能力，Knowledge Advisor 使用户能够更有效地解决设备和流程故障。 主要成果包括减少重复违规和错误决议、改进审计合规、标准化错误处理活动和减少信噪比管理的 AI 能力。
我们的 SmartFactory 自动化解决方案已经服务半导体行业超过 30 年，并在半导体工厂的各个方面都拥有一流的专业技术。
您是否需要了解更多有关 SmartFactory Knowledge Advisor 或其他解决方案的更多信息？
[ 联系我们 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [提高良率学习并加速良率上升](https://appliedsmartfactory.com/semiconductor-blog/quality/improve-yield-learning/)
**Published:** April 27, 2022
**Author:** SJ Wang
**Excerpt:** 在您的晶圆厂中使用预集成 SmartFactory Yield和Defect Management（SmartFactory 良率和缺陷管理）解决方案，构建一个高质量生态系统。
**Content:**
为了实现接近 100% 的良率，半导体制造商必须掌握一种名为“良率学习”的程序。 这包括逐个消除故障源，直至绝大多数制造单元按规范运行。 在当今的晶圆厂中，需要更好的数据收集、集成和可见性来改进良率学习并加速产量提升。
本博文介绍了良率和缺陷管理解决方案在“与其他晶圆厂系统集成以提供更快良率学习”方面提供价值。 它重点介绍了应用材料公司最近发布的良率和缺陷管理解决方案，并通过两个示例展示了这些系统如何控制 Q-time，并通过更好的可视化功能识别缺陷源。
### 合作价值
为帮助客户实现其良率学习，应用材料公司自动化产品部最近与台湾地区一家专门从事良率和缺陷管理的公司 XDMTech Inc. 进行合作。
此次合作的成果推出了基于 XDMTech Vidas 和 xDMS 技术的 SmartFactory Yield和Defect Management（SmartFactory 良率和缺陷管理）解决方案。 SmartFactory Yield Management 是一套集成的、应用于晶圆厂范围内的良率数据管理和分析系统。 它可以帮助工程师提高良率学习并加速良率上升。 与之互补的另一款产品 SmartFactory Defect Management ，减少了对不可靠的手动缺陷分类的需求，还降低了良率损失、识别良率限制因素的时间和制造成本。
该解决方案的推出，增强了应用材料公司 CIM 产品组合的性能，并为制造商进行良率学习提供一站式服务。
### 这些解决方案有何不同？
SmartFactory Yield Management 消除了加载和预对齐数据所需的**80%**的时间和精力。 此外，来自客户现场良率管理实施的数据记录显示了参数一致性问题的早期根本原因识别，从而显著节省成本。
SmartFactory Yield和Defect Management（SmartFactory 良率和缺陷管理）解决方案的主要不同之处包括： 1. **简化数据库。**良率和缺陷管理是唯一能为单一事实来源和更快根源分析提供简化、可扩展数据库结构的解决方案 ，通过增加产品组合和降低成本实现盈利能力的提高。
2. **统计分析工具。**与很多仅依赖商业智能 (BI) 工具的缺陷管理解决方案不同的是，SmartFactory Defect Management 提供额外的统计分析工具和工作流引擎，以自动生成分析报告。
3. **更好地集成。**SmartFactory Yield Management 是唯一可将良测和其他数据集成以进行高级统计和缺陷相关性分析的解决方案。 它也是唯一基于通用平台的制程质量解决方案，可与其他质量子系统集成，包括 MES、FDC、SPC、EDC 和 APC。 此类集成很重要，因为它可以实现跨系统的信息共享，对晶圆厂中的各种数据源进行分析，以及经过验证的多晶圆厂数据集成以及可追溯能力。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/smartFactory-yield-and-defect-management-value.png) 图 1： SmartFactory Yield和Defect Management （SmartFactory 良率和缺陷管理）的价值和关键优势
### 示例 1：通过集成解决 Q-time 问题中体现出的价值
SmartFactory Yield Management 的主要优势之一是可在各种过程控制元素之间的**共享信息**。 举例来说，亚洲的一家大型 300mm 晶圆厂面临许多与 Q-time 问题相关的良率挑战。 Q-time 是指跨两个或以上连续步骤之间的总时间的限制。 如超过此时间限制值，则晶圆可能会报废或导致潜在良率损失。
为了减少晶圆报废或良率降低的风险，各批次在**在生产周期中所需的时间**必须低于 Q-time 的限制值。 如使用该晶圆厂当前的内部系统，将难以与 SmartFactory Fault Detection 集成，因而无法快速生成显示 Q-time 问题的报表。 此外，该工厂也没有适当的自动报告生成工具， 以及控制 Q-time的方法，从而导致响应时间过慢和不准确。
应用材料公司通过集成 SmartFactory Yield Management 与 SmartFactory Fault Detection，解决了上述的问题。 这使工厂能够设置警报以通知工程师任何 Q-time 违规，并自动生成每小时报告以清楚地显示良率管理中的违规趋势（参见图 2）。 通过**共同**使用 SmartFactory Fault Detection 的建模和良率管理功能，晶圆厂可控制和监测到晶圆级别的 Q-time，从而加快良率学习。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/with-smartFactory-yield-management.png) 图 2： 晶圆厂可通过 SmartFactory Yield Management 检测 SmartFactory Fault Detection 中的 Q-time 问题， 并在良率管理界面显示这些问题
### 示例 2：通过更出色的可视化工具识别缺陷
晶圆生产需要很多机台和工艺步骤，因此对机台零件和机械手臂引起的缺陷进行分析非常耗时。 如果制造商没有足够的可视化和分类工具，很难确定缺陷的根本原因。
在传统的缺陷管理系统中，晶圆制造商只能根据预定义区域定义晶圆区域，例如“上”和“下”或“中心”和“边缘”。 但是，通过 SmartFactory Defect Management，制造商可执行**触针**分析，该分析通过将设备零件 CAD 图导入应用程序库实现。制造商可在叠加比对 CAD 图的帮助下完成分析，如图 3 所示。制造商可在叠加比对 CAD 图的帮助下完成分析，如图 3 所示。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/with-smartFactory-defect-management.png) 图 3： 制造商可通过 SmartFactory Defect Management 中导入的 CAD 叠加比对图，识别机械手臂引起的缺陷
SmartFactory Defect Management 利用工具追踪和分类缺陷来源，以帮助识别潜在趋势。 其几何可视化功能叠加比对几何设备组件可能在晶圆上释放的颗粒。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/how-smartFactory-defect-management-checks-repeated-defects.png) 图 4： 此示例所述为 SmartFactory Defect Management 在检查晶圆曝光区的重复缺陷。 如果制造商发现多处重复缺陷，则通常意味着这些缺陷可能是由Reticle导致的，可能需要清洁Reticle或需要检查设备调平情况
### 结论
哪些类型的良率问题会影响您的工厂效益？ 缺陷？ 参数？ 两者都会？ 您是否需要分析来自多家工厂的数据？ SmartFactory Yield和Defect Management（SmartFactory 良率和缺陷管理）解决方案具有简化且可扩展的数据库结构，可提供单一信息来源，提供经过验证的多工厂数据集成和可追溯能力，为您的工厂构建一个高质量生态系统。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [实现数据高效整合，带领工厂质量建设进入下一个阶段](https://appliedsmartfactory.com/semiconductor-blog/quality/taking-factory-quality-to-the-next-level-combining-data-in-a-cohesive-manner/)
**Published:** November 25, 2021
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** 质量改进策略为用户提供建议性操作。
**Content:**
质量改进策略为用户提供建议性操作。
\[pdf-embedder url=”/wp-content/uploads/2022/04/Taking-Factory-Quality-to-the-Next-Level\_Chinese.pdf” height=”1000″\]
[ 下载PDF文件 ](/wp-content/uploads/2022/04/Taking-Factory-Quality-to-the-Next-Level_Chinese.pdf)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [坚定地迈向零缺陷制造，让您的工厂更智能](https://appliedsmartfactory.com/semiconductor-blog/quality/moving-toward-zero-defects/)
**Published:** June 19, 2024
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** 本系列博客讨论了制造商在任何规模工厂的自动化过程中实现零缺陷制造所面临的战略、优先事项和挑战。
**Content:**
### 智能制造中的零缺陷战略是什么？
[零缺陷战略](/zh-hans/semiconductor-blog/quality-zh-hans/automotive-manufacturing/)并非新概念，大多数公司多年来一直在努力制定这样的战略。 然而，在智能制造中构建零缺陷战略的方法是需要不断演进的。 技术在变化，期望也在变化，因此有了更多可能性，甚至从自动化和质量的角度来看，对我们的要求也发生了变化。 因此，我们需要关注在制定零缺陷战略时面临的挑战，并思考如何应对这些挑战。
### 我们面临哪些挑战？
以大众熟悉的汽车行业为例。 汽车配备的传感器、自动驾驶系统、安全系统和功能越发繁多。 因此，汽车行业面临着更大的压力，需要构建更多由芯片驱动的子组件。
然而，从潜在故障的角度来看，汽车行业正在经历一个难题。 这是指工厂制造的一个组件流经供应链并在现场发生故障。 最终，确定故障原因成了一个挑战。 由于 22% 的保修期内故障与电子元件有关，查出故障原因变得尤其困难。 此外，这些故障都发生在汽车的保修期内。 该行业面临着一项艰巨的任务，那就是追踪工厂所制造零部件的“基因”。 85% 的汽车零部件是在 150mm 和 200mm 的生产设施中进行制造的，这些生产设施不具备对零部件进行追踪的能力。 这种情况会持续数年。 挑战非常严峻。 准确收集、核对和追踪海量数据是一项非常繁重的工作。 这项任务如此庞大和重要，为此业界专门制定了 IATF 标准（IATF 16949 标准）来评估满足制造实践要求的能力，以最大限度地降低风险。 挑战来自于传统的设施在设计时没有考虑到如此精细的追踪。 尽管我们渴望解决数据差异的问题，但如何高效地解决这一问题并持续满足质量标准的要求，是一项艰巨的任务（图 1）。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/streamline-quality-standards.jpg) 图 1：强调精确性对于简化质量标准的重要性。
图 1：强调精确性对于简化质量标准的重要性。
### 识别故障原因
除了遵循标准之外，重要的是要问问自己：“我们当前是如何做的？” 回答这些问题的第一步是剖析故障的原因。 我们可从宏观层面加以考虑，将故障原因分为三类：
- **系统性：**工厂对某些产品进行了参数测试，仍然有可能发出有问题的产品。 出于某些原因，未能发现问题。 这是潜在故障最常见的原因。
- **测试覆盖率**：三分之一的潜在故障是这个原因导致的。 工厂设计新产品或具有新特征的产品时，如果需要进行新参数测试但未进行，就会发生这种情况。 这是因为他们不知道需要进行这种测试，或没有这种测试
- **随机性：**在这种情况下，无法对故障来源进行分类，因此被视为随机故障。 这些是一些更令人不安的问题，因为它们表明自动化能力存在更为系统性的缺陷。
通过对潜在故障的原因进行剖析，可以了解工厂可能存在的自动化缺陷类型（图 2）。
图 2：潜在故障原因剖析
在本系列博客**《坚定迈向零缺陷制造，使您的工厂更智能》**的下一章节中，我们将讨论如何识别缺失的自动化 CIM 组件类型。 敬请期待。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [及早发现并修复缺陷](https://appliedsmartfactory.com/semiconductor-blog/quality/defect-management/)
**Published:** March 30, 2023
**Author:** Todd Snarr
**Excerpt:** 借助完整、集成的缺陷分析解决方案，快速确定故障的根本原因。
**Content:**
在您的晶圆厂里，缺陷分类有多可靠？ 您是否还在依赖手动流程来确定故障的根本原因？ 为避免代价高昂的良率偏移，应用材料公司 SmartFactory™ Defect Management 缺陷管理解决方案可快速识别缺陷的来源和位置，对缺陷进行分类和分析，并为后续步骤提供明智的决策。
在 xDMS 缺陷改善管理系统的支持下，提供一套完整的缺陷跟踪、识别和分类的解决方案，从而降低良率损失、识别良率限制因素的时间和制造成本。
有关我们解决方案的详细信息，请查看我们的解决方案简介：
\[pdf-embedder url=”/wp-content/uploads/2024/06/SmartFactory-Defect-Management-Solution-Brief\_CN-1.pdf” height=”1000″\]
[ 下载 PDF 文件 ](/wp-content/uploads/2024/06/SmartFactory-Defect-Management-Solution-Brief_CN-1.pdf)
想了解关于缺陷管理和其他解决方案的更多信息？
[ 联系我们 ](/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [半导体工厂各种排程解决方案的利弊](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solutions-for-semiconductor-factories/)
**Published:** October 6, 2023
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** 选择适合您工厂需求的排程解决方案
**Content:**
可以使用各种方法和技术为生产车间创建计划。 这些方法和技术包括：使用简单的先进先出 (FIFO) 或以交货日期排序 (DDO) 规则,考虑当前在制品 (WIP) 和/或未来在制品 (WIP) 以及简单/基本的生产周期假设，基于手动/ Excel 形式的方法；基于生产区域规则的启发式排程；基于模拟的排程，以及基于优化的排程。 此外，还可以采用混合方法来预测未来在制品 (WIP) 的到达，并对批次进行排序以生成排程。 方法的选择和应用会影响排程的质量以及解决方案所能产生的生产效益。 同时，不同类型的排程系统对工厂输入数据的质量和准确性的要求也随之提高。
通常，排程解决方案需要提取工厂数据，并将其转换或转化为解决方案输入数据。 然后，排程引擎（无论采用何种方法）根据不同的考虑因素和目标应用逻辑，生成排程输出数据。 然后，这些数据经过处理，以用户友好的可视化和分析格式发布成计划，供最终用户使用。 这个过程如下图1所示。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/figure1-schedule-flow-picture.jpg) 图1：排程解决方案工艺流程
下面将介绍各种方法和技术的一些优点和局限性。
### 基于启发式方法的排程解决方案
这是一种基于规则的批次分配和排序方法。 人工操作的工厂采用简单的先进先出 (FIFO)、以交货日期排序 (DDO) 或批次优先方法进行排程，会降低生产力。 使用基于区域、产品组合、设备配置和工厂目标的更复杂的启发式方法，可以快速提高设备利用率、产出和设备组的生产周期。
### 基于模拟的排程解决方案
在模拟排程中，模型根据工厂中所有设备的当前状态和位置，使用模拟来预测未来批次或在制品 (WIP) 的到达情况。 仿真排程被视为工厂的排程系统；它还可以与区域排程系统协同工作，将其输出作为下游区域的输入。
### 基于优化的排程解决方案
在优化排程中，混合整数编程 (MIP) 或约束规划 (CP) 模型根据生产区域的加权目标函数进行批次分配和指派，从而创建最优的设备排程。 优化排程系统是一种区域排程系统，可以与基于仿真的工厂排程系统集成。
下面的表2可以让您轻松了解每种解决方案的优点。
### 每种解决方案的积极属性
启发式方法 模拟 优化 易于开发、配置和部署
更准确的未来批次/在制品 (WIP) 到达预测
最佳可行和最优排程
易于学习、扩展和自定义
可以对整厂进行排程，并在排程中执行派工规则
详细的设备建模
改善 KPI 的早期收益
在非生产环境中验证派工规则
更好的瓶颈管理
对输入数据要求/质量的适度敏感性
可跨多个工厂和公司进行扩展，实现更好的生产线平衡
对不断变化的工厂条件和目标保持敏感并做出响应
表 2：基于启发式、模拟和优化的排程解决方案的积极属性
每种解决方案或技术也有其局限性，如下表 3 所示。
### 每种解决方案的局限性
启发式方法 模拟 优化 可能需要不断进行微调
对工厂数据质量、延迟和粒度高度敏感
对工厂数据质量、延迟和粒度高度敏感
没有实现所有潜在的生产收益
使用简化版派工规则实施
难以解释排程系统的决定
需要在生产环境中进行效果评估
不是数学上的最优解
需要更长的部署时间
通常能提供良好但非最佳的解决方案
维护所需资源增加
维护所需资源增加
对不断变化的工厂条件和目标不敏感，反应迟钝
模型性能时间与问题大小呈非线性关系
表 3：启发式、模拟和优化的排程解决方案的局限性
### 结论
工厂应根据对工厂需求的评估来选择排程软件解决方案。 理想情况下，解决方案应能很好地满足这些要求、工厂当前和未来吸收新技术和业务实践的成熟度，以及现有软件解决方案的功能。 以下问题有助于您的决策过程：
- 工厂需要全厂排程系统还是生产区域排程系统？
- 您的瓶颈情况和瓶颈的性质是什么？
- 工厂自动化的当前基准
- 全面了解工厂数据的生成、可用性、收集、存储和处理能力
- 帮助实施和支持排程自动化愿景的技术资源可用性
启发式排程、模拟排程和优化排程都可以帮助您改善工厂 KPI，每种方法都有其优点和缺点。 您应该充分了解这些排程方法的适用性和能力，以确保在您的工厂成功实施。
不过，需要注意的是，没有经验和没有实施过复杂自动化排程解决方案的公司应考虑部署基于启发式方法的排程。 这将帮助您在工厂改进方面尽早实现投资回报率 (ROI)，同时还能积累经验和专业知识。 在目前没有派工或排程系统的公司实施基于模拟或优化的更复杂的排程解决方案，可能会导致学习曲线过浅或部署不成功。
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [半导体制造中统筹生产过程控制的优势](https://appliedsmartfactory.com/semiconductor-blog/quality/unifying-process-control/)
**Published:** August 12, 2024
**Author:** Christopher Reeves, Global Product Manager, E3
**Excerpt:** 通过统筹生产过程控制，实现更好的检测、更佳的决策和更低的成本
**Content:**
## 概要速览
- [ 孤岛式的工作场景 ](#index1)
- [ 统筹 SPC 和 FDC 功能 ](#index2)
- [ 实现流程优化 ](#index3)
- [ 总结 ](#index4)
- [ 常见问答 ](#index5)
在工业界，我们经常被大数据、数字孪生、人工智能和机器学习这样的流行词所迷惑，误以为这些课题是我们要实现的目标，然而真正的目标是提升工厂生产效率。针对这一根本目标，我们需要关注各种关键性能指标，如故障诊断时间，决策效能（图1）和行动成本等，来驱动工厂生产效率的改善。
工厂中各种数字化系统的部署及实施方式，直接影响了上述工厂指标的优化难度和理想上限。
图 1：提高效率依赖于既好且快的决策
### 孤岛式的工作场景
由此推论，我们首先需要审视工厂设备维护和工艺可靠性的常规方案。通常，这些动作是在各自的细分工作范围内孤立进行。举例来说，设备故障分析是 FDC 工程师负责的工作范围。当发生机台运行故障等 FDC 事件时，FDC 工程师会分析设备数据并提出合适的解决方案。SPC 工程师负责的工作范围则面向工艺基准。当发生量测异常等 SPC 事件时，SPC 工程师会检查统计图表并制定应对方案。理想情况下，他们彼此间可以互相交流，获取不同角度的建议，但实际情况并非如此。因为实现跨领域的沟通和决策，需要付出高昂的的成本，一般体现在更繁杂的工厂事务、更困难的质量管控以及更多的资金需求上。
### 统筹 SPC 和 FDC 功能
通过创建标准化的平台将 FDC 和 SPC 领域集成在一起，我们可以减轻多领域沟通的成本。对我们而言，“统筹”表示所有过程控制系统在内核底层上的集成，这需要：
- 标准化的数据结构，这对引入先进分析系统和人工智能/机器学习应用非常重要
- 合适的数据共享工具，可以规范各种事件的操作和反馈
- 同样风格的用户界面，为不同的应用程序提供相同的外观和质感
- 通用的管理模式，以简化不同应用的权限管理
- 规范的知识库，使我们能够快速复用现有案例并降低学习成本
- 可拓展系统结构设计，可随着工厂规模的扩大而不断扩展
### 实现流程优化
这些系统被整合后，非孤岛化的处理流程可以改变设备维护和工艺可靠性的评估方式。一种新的模式应运而生，即单一事件会触发一系列联动方案，能够实现跨领域评估分门别类的统计数据。最终，这套流程不仅解决了事件本身，还能同时梳理并优化工作流程来规避同类问题。此外，跨领域分析作为一种更优秀的流程方案，能够更快地检测到异常事件，帮助您从被动应对转变为主动出击。
### 总结
在获取设备维护和工艺可靠性进行全面的了解和评估后，并且获益于简化系统联通层级架构，工程师团队可以快速做出高质量且正确的的决策。这种系统集成方式和团队成员之间的资料渠道共享可以降低异常事件的负面影响和其附带的损失，与此同时，工厂也可以在保证质量生产并快速提高整体生产效率。
图 2：对设备维护、工艺可靠性和团队协作的全面了解和评估，可以推动广泛而深入的成功。
## 常见问答
#### 工厂中统筹生产过程控制的首要目标是什么？
首要目标是提高工厂生产效率，但实际的问题是如何实现这一目标。
#### 有哪些关键绩效指标 (KPI) 可以帮助提高工厂生产效率？
关键绩效指标包括故障诊断时间、决策效能以及行动成本。
#### 在工厂生产效率提升方面，为什么要透过大数据、数字孪生、人工智能和机器学习等流行语看清其本质呢？
流行语可能会产生误导，因此必须把重点放在提高生产效率切实可行的方案上。
#### 评估工厂设备和工艺可靠性的传统做法如何影响生产效率的改进？
传统的做法通常是各孤立领域各自进行决策并处理，不利于跨部门沟通，且解决问题的时间成本也很高。
#### 生产过程控制通常涉及哪些领域？为什么孤立决策会导致问题产生？
其领域主要包括设备（FDC工程师）和工艺基准（SPC 工程师）。孤岛式的工作模式会阻碍沟通并增加成本。
#### 提升统筹生产过程控制功能的关键点是什么？
有效的统筹管控需要标准化的数据结构、合适的数据共享工具、同样风格的用户界面、通用的管理模式、规范的知识库及可扩展系统结构。
#### 生产过程控制领域的集成如何降低成本、提高生产效率？
通过跨领域模式简化分析和沟通成本，从而实现更细的分析、更快的事件检测和更好的前瞻性决策。
#### 全面了解设备维护和工艺可靠性对决策和降低成本有什么好处？
全局的视角可以让我们快速做出正确的决策，并降低异常事件的负面影响和其附带的损失。
#### 如何才能更加主动地改进工厂生产效率？
工厂可以通过集成系统、团队成员共享访问权限和跨领域数据分析，从被动应对转变为主动出击。
#### 统筹生产过程控制对工厂生产效率和生产质量的总体影响是什么？
统筹生产过程控制可以保证质量的同时，提高工厂生产效率，最终节约整体成本并实现更高效的运维。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [助力晶圆厂迈入高效和高品质生产新阶段](https://appliedsmartfactory.com/semiconductor-blog/quality/bringing-new-levels-of-efficiency-and-quality-to-the-fab/)
**Published:** November 25, 2021
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** Selim Nahas分享在晶圆厂如何减少人为差异和提高解决问题能力的见解。
**Content:**
Selim Nahas分享在晶圆厂如何减少人为差异和提高解决问题能力的见解。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [使用结构化框架验证工厂排程解决方案系统 （下篇）](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-2/)
**Published:** November 14, 2023
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** 进行更高级的验证并对工厂排程解决方案系统生成的排程结果进行微调，以使您的半导体工厂实现显著的效益提升
**Content:**
## 概要速览
- [ 排程调试与可追溯性 ](#index1)
- [ 高级验证：排程的质量 ](#index2)
- [ 在成功实施中的作用 ](#index3)
在“使用结构化框架验证工厂排程解决方案系统”的[上篇](/zh-hans/semiconductor-blog/scheduling-zh-hans/scheduling-solution-systems-part-1)，我们探讨了验证框架如何帮助制造商确定由[工厂排程解决方案系统](/zh-hans/semiconductor/productivity-solutions/advanced-scheduling/)生成的排程结果的有效性。我们讨论了基础级别和次级级别的验证方法，以及对模型数据的验证。现在，我们将关注下一步，即进行高级验证和微调排程。
### 排程调试与可追溯性
要验证、理解并微调排程解决方案，您需要能够解释并理解该解决方案背后的决策过程。当最终用户在配置排程系统时，他们是基于对排程系统行为的期望和假设来配置的。当实际情况并非如此时，工厂需要能够通过测试和验证这些假设来找出原因。（这也是排程微调过程的一部分）。以下信息将帮助您理解决策过程：
- 批次分配：为什么要在排程中将特定批次分配给特定设备？这可以用分数、权重、条件、百分比和/或设备及批次属性以表单的形式进行可视化编码来解释。
- 批次排序：为什么在排程中将特定批次的分配并安排在另一个批次的前面或后面，或者某个设备批次顺序的某个位置。这可以用打分、权重、条件、百分比或/和设备及批次属性以表单的形式进行可视化编码来解释。
- 分配和未分配批次：与任何被分配或选定的批次发生冲突并失去被分配资格的具体原因。在有大量可派在制品 (WIP) 的工厂中，当排程时间范围内无法分配所有可派批次时，用户应能够获取分配和未分配原因的详细信息。
### 高级验证：排程的质量
根据工厂的情况不同，排程可设置为每五分钟至一小时自动刷新一次。作为解决方案验证的一部分，需要对工厂排程在每次运行之间以及滚动运行期间的稳定性和可靠性进行跟踪，因为这一过程模拟了客户工厂的实际生产环境。好的排程可以基于量化标准和关键绩效指标 (KPIs) 来判断，但评估中也存在基于工厂实际权衡的主观成分，这些又可以追溯回关键绩效指标。
根据实际业务场景，排程解决方案的有效性能够通过所追踪的一些关键绩效指标展现出来，这些关键绩效指标包括：
- 排程执行率：分配方案执行率的后期统计指标，用于衡量在实际生产中，批次是否在排程结果中被分配到的设备上运行。
- 预计晶圆 move 数量和产出：排程系统在班次结束或一天结束时预计的晶圆 move 数量和产出，这是衡量工厂产出的一项指标。
- 设备利用率：有货 (WIP) 时的待机时间 (SBY)（可能导致排程中出现可避免的空白时间）以及无货 (WIP) 时的待机时间 (SBY)（可能导致瓶颈设备无法工作）。设备的待机时间是衡量设备中未利用产能的指标，通常而言，排程系统的目的是最大限度地减少总设备时间中的这一部分。
- 已完成批次的生产周期：跟踪一段时间内的已完成批次生产周期，是衡量排程有效性的后期统计指标。如果产品组合、下线数量和设备能力矩阵没有发生重大变化，那么在部署排程系统前后，完成批次的生产周期应呈下降趋势。
- 工厂实际加工天数/理论加工时间 (X factor)、每个掩膜层所需的天数 (DPML)、生产周期 (CT) 频率或在制品 (WIP) 周转：追踪显著的生产周期指标（如每层掩膜所需天数、实际加工天数/理论总加工时间 (X factor) 或在制品 (WIP) 周转）的趋势，是衡量排程有效性的指标。如果产品组合、下线数量和设备能力矩阵没有发生显著变化，那么在排程系统部署前后，这些关键绩效指标应呈下降趋势。
- 准时交付率或落后的批次比率：在那些重视批次交货日期并将其作为核心目标的工厂，排程系统有望改善准时交付 (OTD) 指标。
- 批次平均队列大小：在那些将设备菜单转换最小化作为排程解决方案核心目标的工厂中，批次平均队列大小是衡量排程有效性的一项指标。
这些关键绩效指标 (KPIs) 也需要作为排程输出的一部分，以前瞻性的方式生成。这将允许最终用户了解排程预测的结果，并对排程计划进行验证。
### 在成功实施中的作用
验证框架提供了一种结构化的方法，对解决方案生成的排程进行全面评估。软件供应商和客户都需要在这一点上达成共识，并成功部署和管理解决方案。不存在所谓的“完美排程”。在不基于人工智能/机器学习的方法上自动进行微调，以实现理论上可达到的生产效率提升。
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [使用结构化框架验证工厂排程解决方案系统 (上篇)](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-1/)
**Published:** November 14, 2023
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** 高效的工厂排程解决方案可提高设备产能、产品质量以及产品的准时交付
**Content:**
## 概要速览
- [ 结构化验证框架的必要性 ](#index1)
- [ 创建生产排程 ](#index2)
- [ 基础级别验证 ](#index3)
- [ 次级验证：模型数据的质量和完整性 ](#index4)
- [ 模型数据追踪 ](#index5)
- [ 下一步工作 ](#index6)
半导体工厂的生产排程直接影响到关键业务指标，如设备产能、产品质量和准时向客户交付产品。因此，如果排程执行不如预期，可能会造成成本损失。幸运的是，我们可以对生产排程进行验证，确保它是基于正确的数据创建的，并能在工厂应用中产生正确的结果。
### 结构化验证框架的必要性
[工厂排程解决方案系统](/zh-hans/semiconductor/productivity-solutions/advanced-scheduling/)可帮助半导体工厂充分利用其设备和人力资源。为确保有效，排程解决方案将生成准确、完整的生产计划。验证框架可让工厂通过查看排程的输出以及用于创建排程的输入数据的质量，来确定排程的有效性。工厂使用排程解决方案系统为在制品、设备和光罩创建短周期（12-24小时）的工厂排程。该排程通常每5-10分钟至1小时刷新和更新一次，具体取决于工厂的使用情况及其生产周期、产品组合和产能管理方法。在工厂部署排程解决方案时，也必须部署验证框架，以确定所生成的排程的有效性。重要的是，验证框架需要有足够的颗粒度，能够从对摘要级别的验证深入到设备级别和批次级别的验证，以便进行更深入的分析。
### 创建生产排程
典型的排程工作流程如下图 1 所示。获取包括 [MES ](/zh-hans/semiconductor/manufacturing-execution-solutions/)(制造执行系统) 在内的工厂数据源，生成排程解决方案所需的模型数据。然后，排程引擎应用逻辑生成在制品批次到设备的分配，以实现区域或整厂的设定目标。排程计划中的任何差异、不准确、无效和无解方案，都可以追溯到解决方案模型数据和/或排程引擎。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure1-scheduling-workflow.jpg) 图 1：典型的排程工作流程
如下图2所示，排程计划的评估和验证包括对基础级别的验证，以及模型数据质量和完整性的验证。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure2-three-levels.jpg) 图2：排程计划的三个验证级别
### 基础级别验证
排程结果以甘特图的形式显示。使用一组特定问题来验证排程结果。如果用户对以下任何一个问题的回答是“是”，则该排程结果无效，需要进行更多检查来追踪根本原因并修复。
与设备相关的问题：
- 排程系统是否没有给处于可运行状态的设备分配任何批次？
- 当前是否有任何可派的在制品 (WIP) 且可以在这些设备上运行？
- 排程系统是否给宕机的设备分配了批次？
- 排程系统是否给计划内停机的设备分配了与维修保养事件时间范围重叠的批次？
- 排程系统是否给计划外宕机的设备分配了批次？
- 是否给设备分配了它们不能执行的生产工序的批次？
- 是否给设备分配了不属于该产品生产流程中的工序的批次？
- 批次分配是否考虑了设备的子部件，包括晶圆上下料口和腔室？
批次相关问题：
- 是否有处于可派状态的在制品 (WIP) 批次未被分配给任何设备进行当前和未来工序的生产？
- 是否有处于不可派状态的在制品 (WIP) 批次被分配给任何设备进行当前和未来工序的生产？
- 排程系统是否分配了会违反 Q-time 管控时长的批次或在队列中显示最高等级批次排在优先级较低的批次后面等待加工？
生产排程通常以每五分钟到一小时的频率刷新。因此，验证框架需要提供汇总报告和分析（如下图3所示），以追踪每个排程结果有效性的趋势。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure2-table-analytic.jpg) 图3：汇总表分析示例
### 次级验证：模型数据的质量和完整性
当排程不完整或无效，通常由解决方案的模型数据提取和转换 (ETL/ETM) 层导致。例如，由于数据提取和转换过程的不完整和不正确，可能会导致设备、批次和工序站别缺失。需要数据验证报告来确保排程解决方案的模型数据准确无误。以下是在模型数据不完整时生成的结果示例：
- 在制品 (WIP)：工厂的实际在制品与排程结果中的在制品比对。
- 设备：工厂中所有已安装并运行的设备都显示在排程解决方案的模型数据中。
- 工序站别：一些站别没有被加工流程工序所调用，且没有定义可以运行该站别的机台组。
- 产品：一些产品没有有效的加工工序。
- 产品：一些在工厂中运行的批次，其运行的工序与排程系统模型数据中定义的工序不匹配。
- 通用资源：要求使用探针卡或光罩等通用资源的步骤数。
- 设备菜单转换：设备当前使用何种菜单配置未进行定义。
### 模型数据追踪
加工工艺时间等模型输入数据的准确性会影响排程结果的执行和准确性。如图4所示，要检查工艺时间的漂移和偏差，您必须能够将产品-站别-设备组组合的工艺时间与基于历史数据统计生成和计算的工艺时间进行比较。这可以帮助用户识别需要定期校正或更新的项（如果用户有定期更新这些模型数据的话）。工作流程中还需要有自动预警，以通知用户工艺时间的变化情况。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure3-example.jpg) 图4：工艺时间追踪表示例
### 下一步工作
一旦完成了这些基础验证，工厂可以继续进行高级验证并对排程进行微调。这包括了解创建排程的决策过程以及特定关键绩效指标 (KPIs) 的考虑。这些内容在“使用结构化框架验证工厂排程解决方案系统[（下篇）](/semiconductor-blog/scheduling-solution-systems-part-2/)”中进行了讨论。
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [使用 SmartFactory 统一工艺管控流程 (UPC) 解决方案提高生产力](https://appliedsmartfactory.com/semiconductor-blog/quality/manufacturing-operations/)
**Published:** October 9, 2023
**Author:** Vishali Ragam, Global Product Manager, SPC
**Excerpt:** 在 Applied SmartFactory 发布的这篇引人入胜的文章中，SmartFactory UPC 解决方案将带您探索 AI 驱动的过程质量改进。
**Content:**
## 概要速览
- [ 解决方案 ](#index1)
- [ 统一工艺管控流程解决方案是如何运作的？ ](#index2)
- [ AI 赋能的生态系统 ](#index3)
- [ 打破数据孤岛 ](#index4)
- [ 为每个工厂提供特定的解决方案 ](#index5)
- [ 不中断生产的情况下进行修复 ](#index6)
- [ 更深远的价值 ](#index7)
- [ 结论 ](#index8)
- [ 常见问答 ](#index9)
芯片制造过程中产生的信息来自工厂的多个来源，纷繁复杂。将这些信息汇集在一起可以带来巨大收益。数据的多样性、来源、质量和数量等特征使得信息整合这项任务充满挑战。本文将探讨 SmartFactory 解决方案如何帮助克服这一挑战。
### 解决方案
SmartFactory 构建了一个统一工艺管控流程 (UPC) 解决方案，将不同的过程质量原则（特别是与管控产品有关的原则）汇聚整合至同一平台。
### 统一工艺管控流程解决方案是如何运作的？
该统一平台可以从多个不同来源获取数据，并首次将这些数据转换为综合数据，从而对半导体工厂情况有更深入的了解。在核心层面整合所有过程控制系统需要： - 标准化的数据建构，这对先进分析和 AI/ML 应用至关重要
- 可以共享的设备，这帮助我们规范对事件的行动和响应
- 统一的用户界面，为不同的应用程序提供相同的外观和触感
- 通用的管理模式，以简化应用程序的管理
- 标准化的知识库，使我们能够重复使用专业知识并降低总体投资
- 架构设计，可随着的工厂规模的扩大而扩展
(有关统一工艺管控流程的需求和优点的更多信息，请查看相关[博客](/semiconductor-blog/unifying-process-control/)。 )
### AI 赋能的生态系统
我们选择在应用材料公司 E3™ 设备和过程控制平台上构建解决方案，该平台具有所有[核心功能](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/cim-solution/)，并且大多数客户已在使用。由此产生的生态系统提供了模型和与 E3 的连接，使过程质量的自动决策（AI 决策）成为可能。
### 打破数据孤岛
统一工艺管控流程 (UPC) 解决方案从许多设备中提取数据，而不是孤立地查看每个设备数据。这是关键所在，因为每一个不同的数据都对过程质量产生影响，综合考虑可以让我们对实际情况获得更深层次的认知。该解决方案汇集了来自多个来源的相关数据，对其进行综合分析，并阐述发生的事实、需要采取什么措施以及如何应对。
它的分析视角不仅能识别事故，还能分析导致问题发生的具体和综合性的影响，并告诉您需要解决什么问题，以及如何解决这些问题。
### 为每个工厂提供特定的解决方案
SmartFactory的统一平台仅配置了提供洞察所需的资源，仔细过滤那些不会影响过程质量的杂乱信息。
重要的是，该解决方案不采用“一刀切”的方式。由于模型必须可靠，且与各个半导体工厂相关，因此模型都是逐个设计的。用户可以输入适用于特定工厂的信息，以及识别管理情况的协议。
### 不中断生产的情况下进行修复
例如，某工厂在短时间内多次发出相同来源的警报，而在每次修复后，问题来源仍继续触发警报。在这样一个快节奏的环境下，厂家没法停下来彻底分析警报原因。修复每个警报的触发原因是恢复生产的权宜之计，但显然这样的处理方式收效甚微。
在这种情况下，UPC 可以在不中断生产的情况下完成警报原因分析。UPC 会查看多个班次中有关这一警报来源的历史记录，确定其为反复出现的问题。该模型收集并阐释多个班次的数据，关注可能影响过程质量的众多因素；同时整合各类数据，分析它们之间的联系，找到触发警报的根本原因，最终提出补救措施。这样，制造商就能更快地做出业务决策。
### 更深远的价值
该模型还是一种持续改进的工具。在确定了某个问题的解决方案后，可以结合考虑其他过程质量问题，分析综合数据，寻找其他解决方案。
### 结论
借助统一平台的互联互通，可以有效利用集成工具和数据的协同作用，简化运营环节、为团队赋能，充分释放工厂的潜力。
## 常见问答
#### 应用材料公司 E3 是什么？
这一先进的设备和过程控制解决方案是一套全面的工厂自动化软件包，旨在提高半导体制造的生产力并降低成本。利用专有算法，应用材料公司 E3 系统可将制程能力提高30%以上，减少计划外停机，并缩短生产周期，从而将整体设备效率提高20%。应用材料公司 E3 系统独一无二地继承了所有关键设备自动化和工艺控制组件，提供当今市场上高度灵活、用户友好和功能强大的全工厂设备工程系统解决方案。
#### 统一工艺管控流程 (UPC) 解决方案从哪里获取数据？
UPC 可以汇集所有过程控制领域的数据，包括Run-to-Run，Recipe Management 以及 Defect Management 等。
#### 统一工艺管控流程 (UPC) 解决方案对我的团队有何帮助？
UPC 可为团队成员提供共享访问，改善沟通与协作。例如，负责不同生产环节的工程师可以更方便地查看综合数据，而不仅仅是各自权限范围内的数据。这样，不同团队之间就能相互协作，共同制定事件解决方案。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [使用 SmartFactory 派工解决方案，让产出增加5-10%](https://appliedsmartfactory.com/semiconductor-blog/scheduling/smartfactory-dispatching-solutions/)
**Published:** October 12, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** 集成 SmartFactory 排程和派工解决方案，让生产效率再提升 3-5%。
**Content:**
在半导体厂，“排程”和“派工”这两个术语通常是混用的。 在本篇博客中，我将借助语境定义这两个术语、概述与它们有关的常见误解和挑战、强调部署集成的排程和派工的价值。
### 排程：批次分配
在本篇博客中，*排程*指将批次分配给特定区域的一组给定设备。 批次分配是基于当前和预测的批次到达，以及当前和未来的设备状况。 制造商通常以 12 小时为单位创建班次排程表，每隔 10-15 分钟生成一份排程表。 通常，对瓶颈设备或具有复杂处理要求的区域实施排程解决方案。 具体例子包括光刻、湿刻/扩散、真空室设备、测试仪等。 排程解决方案可以基于优化方法，也可以基于启发式方法， 这两种选项都有助于提高产出。 众所周知，与启发式方法相比，以优化为基础的方法可使得产出多增加 **3-5%**。 关于产出提升的详细信息，请参考这篇 [Michael Förster介绍英飞凌技术](https://appliedsmartfactory.com/zh-hans/blog/infineon-technologies-describes-how-they-optimize-productivity/) 的博客，了解他们如何利用 SmartFactory 集成解决方案优化生产效率。
### 派工：批次序列
*派工* 在本篇博客中，派工指特定设备上实时处理的批次序列。 派工规则在全厂范围内实施，且通常作为全厂和本地规则实施。 **全厂规则**包括能够管理客户承诺的产线平衡逻辑，**本地规则**包括优化给定区域（如光刻）产出的附加逻辑。
### 误解
一个常见误解是，为特定设备创建处理批次序列时，派工规则不理解上游和下游 WIP/设备的情况。 我们的 SmartFactory 派工解决方案整合了上游和下游 WIP 的工况，同时整合工厂的当前和未来状态，以便实时创建派工单。 按照当前的产能，我们的派工解决方案可视作为“实时排程”，而排程解决方案可视作为“近实时排程”。 表 1 总结了计划、排程和派工解决方案之间的区别。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig-min.jpg) 表 1：计划、排程和派工解决方案的范畴
一个更常见的误解是，您只需要排程解决方案，而不需要派工解决方案。 通常，工厂每隔 5-15 分钟生成一份排程单。 而在此期间，工厂车间会发生许多变化。 设备状态可能会改变，某个批次可能会被暂停，或一个合格设备的流程可能会受到限制。 Govind 等人在关于近实时排程和派工的论文中，通过数据说明某个区域的状态变化频率1。 根据该数据，**50%** 的变更在不到<5 分钟内发生，**80%** 的变更在不到<15 分钟内发生。 鉴于上述发生的变更情况，公布的排程表对车间意味着不明确、不一致的决定。 部分挑战在于：
- **手动调整。** 执行 5-15 分钟间隔旧排程表的操作员，试图为该设备选择批次，却发现该批次现已暂停。 而屏幕上的为下一批次安排的设备则刚刚下线。 在这种情况下，操作员现在必须手动调整。 这种调整导致产生了更多手头有WIP的闲置设备，影响了产出和生产周期。
- **排程单响应性。** 发布的排程表无法实时响应以恢复关键良率的偏移。 在这种情况下，工程部门需要立即限制某些设备，并“在可能的情况下”将工作输送到黄金设备上。
- **自动化运输。** 在使用高架轨道 (OHT) 系统、自动导向车 (AGV) 或其他类型机器人进行自动化运输的工厂中，自动化运输系统经常无法将批次交付给正确的设备，导致大量异常处理场景，及出现设备空窗期的情况。
为克服这些挑战，需要集成的派工解决方案。 在制造商实施排程的区域，派工规则试图遵循排程结果，但由于前面提到的一些挑战，派工规则根据工厂实时状态调整排程结果。 图 1 显示 SmartFactory 集成的派工解决方案如何实施。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-table1-min.jpg) 图 1：执行集成的派工和排程解决方案
部署集成的排程和派工解决方案可以确保：
- 采用一致、基于启发式的方法对工厂中的动态事件进行实时调整。
- 各项规则以快速逻辑执行时间（以秒为单位），结合全球和本地参数，实现最低的生产效率。
- 当规则变得太复杂而无法提供最佳路径时，在高度受限区域实施排程可以提供额外价值。
- 每个领域都与工厂目标和关键指标一致、紧密地关联起来。
使用 SmartFactory 派工解决方案的客户，通过集成这些解决方案，产出增加了 5-10%，生产效率又提升了 3-5%。\[1\]
**参考**
\[1\] Operations Management in Automated Semiconductor Manufacturing with Integrated Targeting, Near Real-Time Scheduling, and Dispatching, Nirmal Govind, Eric W. Bullock, Linling He, Bala Iyer, Murali Krishna, and Charles S. Lockwood, IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, VOL. 21, NO. 3, AUGUST 2008
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [以更好的可见性推动良率提升](https://appliedsmartfactory.com/semiconductor-blog/quality/yield-management/)
**Published:** January 5, 2024
**Author:** Todd Snarr
**Excerpt:** 使用集成的良率分析解决方案，改进良率学习并加快良率提升。
**Content:**
在您的晶圆厂里，哪些类型的良率问题会影响您的工厂效益？ 缺陷？ 参数？ 两者都会？ 您的晶圆图是否存在低良率、量测或参数化的“斑点”？ 为解决这些问题，一套集成的、应用于晶圆厂范围内的良率集成管理系统对加速良率学习和减少质量分析时间至关重要。
SmartFactory Yield Management （SmartFactory良率管理解决方案）采用单一存储和分析平台，适用于所有半导体数据，为整个企业提供单一的真实数据源。 它加载并预对齐来自 WIP、FDC、量测、缺陷、排序、封装、最终测试和其他来源的各种数据，从而缩短分析时间，避免代价高昂的良率偏移的发生。
凭借 SmartFactory Yield Management（SmartFactory良率管理解决方案），客户达到成熟良率所用时间缩短了 **30%**，实现质量数据分析的时间缩短了 **80%**。
有关我们解决方案的详细信息，请查看我们的解决方案简介：
[pdf-embedder url=”/wp-content/uploads/2024/01/SmartFactory-Yield-Management-Solution-Brief_CN-1.pdf” height=”1000″]
[ 下载 PDF 文件 ](/wp-content/uploads/2024/01/SmartFactory-Yield-Management-Solution-Brief_CN-1.pdf)
想了解关于良率管理和其他解决方案的更多信息？
[ 联系我们 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [UMC分享他们如何实现生产制造的卓越运营](https://appliedsmartfactory.com/semiconductor-blog/use-cases/umc-describes-how-they-achieved-manufacturing-operations-excellence/)
**Published:** November 25, 2021
**Author:** YY Chen
**Excerpt:** UMC将实时派工、全自动化工作流程、MES 300works™等系统进行集成
**Content:**
UMC将实时派工、全自动化工作流程、MES 300works™等系统进行集成
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Bingeworthy, Semi, Newly Released, Popular
---
### [SmartFactory Activity Manager™ 助力英飞凌达到 ROI 实时最大化](https://appliedsmartfactory.com/semiconductor-blog/use-cases/maximize-roi-real-time/)
**Published:** August 1, 2023
**Author:** Joerg Weigang (Applied Materials) and Julius Schmidkonz (Infineon Technologies)
**Excerpt:** Activity Manager 快速测试模型，将数据置于易于比较的界面
**Content:**
SmartFactory Activity Manager 解决方案通过实时感知工厂资源的变化、决定工作流程，并对工厂资源做出响应，从而提高资源利用率和生产效率。 实现更好地管理和控制资源、设备、软件应用及人力，ROI 达到最大化。[英飞凌](/zh-hans/blog/infineon-technologies-describes-how-they-optimize-productivity/)在其工厂中广泛使用 [Activity Manager](/zh-hans/semiconductor/productivity-solutions/activity-manager/)，包括批次派工、控制自动化物料搬送系统以及机器人控制等，类似用例还有很多，不在此一一列举。英飞凌希望找到一种方式，能够最准确地确定顺序集群工具适用性。 他们采用 Activity Manager 来快速测试自动化解决方案，选择其中一个解决方案作为标准方案，并在整个公司共享模型。
### 挑战
与大多数半导体制造商一样，英飞凌采用 SEMI E10 规范来确定设备状态并精确测量变量。 同时，准确确定无腔室设备和并行集群。 但这对于顺序处理的集群工具来说不太适用，因为需要更复杂的建模。 因此，英飞凌开始寻找定义他们顺序集群工具状态的最佳实践方法。 为了测试可行性，他们选择了一个具有挑战性的集群工具，该工具需要产品按指定顺序通过多个设备腔室。
不同的人对这台机器状态的定义也不一样。 例如，状态指示器显示六个腔室中的三个处于工作状态，另外三个处于闲置状态。 根据当时运行的腔室数量，一些人会认为机器处于 50% 的闲置状态。 但是有些人认为，只要内部保持满荷载运行，这台机器就是 100% 运行状态。 很难确定在决定设备状态时谁是对的、谁是错的，本质上来说，这是回答“我工具的实际可用性是多少？ ”这一问题。无法对性能进行基准测试会对生产力造成直接影响，因为这会导致工厂不清楚该修复什么或何时修复。 如果不对工具进行基准测试，则无法充分发挥其潜力。
英飞凌希望找到一种简便的解决方案，仅通过简单的代码即可计算不同站点的顺序集群工具的可用性。 他们决定实施多种不同的策略，并使用 Activity Manager 进行测试。 他们利用实时设备状态、处理时间以及其他资源，从集群中每个单元启动和关闭时的工具收集实时事务数据。 他们使用 Activity Manager 的点击和拖动界面轻松地对每个策略进行建模。这些操作会与 Activity Manager 操作一起自动执行，如图 1 所示。 此类数据被不断收集、计算，并存储在英飞凌的数据库中。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/activity-manager-extracts-factory-data-runs-apf-reports-to-compute-results-for-each-scenario-and-stores-those-results-to-an-external-database.png) 图1：Activity Manager 提取工厂数据，运行 APF 报告以计算每种场景的结果，并将这些结果数据存储至外部数据库中
这些数据此后在 APF Analytics 查看器中显示，可一站式查看每种方法、计算和结果，如图 2 所示。 您可以轻松将该结果与设备工业工程师、工艺工程团队、制造经理和其他专家的输入数据进行比较，以精准确定最适合的方法。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/result-of-modeling-solutions-as-shown-in-solution-ui.png) 图 2 ：建模解决方案的结果如解决方案用户界面所示
由于开发 Activity Manager 代码不需要深入的编程知识。因此该领域专家们可以自己编写不同的逻辑，无需组织大型 IT 项目。 英飞凌团队有能力选择最佳模型，并轻松将该方法扩展到公司的其他站点。 借助 Activity Manager，原本需要花费数月的“测试、实施和扩展模型至其他站点”的流程得到了极大缩短。
现在，英飞凌已确定其顺序集群工具的可用性，可以与公司旗下的其他工厂以及竞争对手进行比较。 在了解自己的真实性能表现（以及预测未来的性能表现）， 他们可以更好地规划发展，这种基准测试能力还将帮助他们进行容量建模、更好地分配资源，并提高生产力。
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Semi
---
### [FDC 与 SPC 协同优化：实现降本增效的智能制造解决方案](https://appliedsmartfactory.com/semiconductor-blog/quality/synergizing-fault-detection-and-spc/)
**Published:** March 22, 2024
**Author:** Vishali Ragam, Global Product Manager, SPC
**Excerpt:** 将 SPC 与 FDC 功能集成，可助力半导体制造商实现更高质量、更高可靠性与更高效能。
**Content:**
## 内容概览
- [ SPC-FDC 系统集成原理解析 ](#index1)
- [ 设备数据与在线测量的关联分析 ](#index2)
- [ 皮尔逊相关系数应用 ](#index3)
- [ 基于相关性分析的 SPC 实施 ](#index4)
- [ 结论 ](#index5)
在高度复杂的半导体制造领域，精密不仅是一项标准要求，更是确保产品质量与性能的关键所在。任何微小的偏差都可能导致严重缺陷，进而影响最终产品的质量与良率。为满足日益缩小的器件尺寸和日益复杂的工艺要求，制造商依赖先进的工具与方法论来实现高精度生产。SPC（统计过程控制）与 FDC（故障检测与分类）系统是其中两项至关重要的工具。尽管 SPC 与 FDC 系统各自具备独特优势，但将二者集成至统一平台，可带来一系列显著效益，有效提升半导体制造工艺的效率与稳定性。SmartFactory SPC™ 在模型构建方面日益成熟，尤其在将故障检测数据与在线测量结果进行关联分析方面表现尤为出色。
### SPC – FDC 系统集成原理解析
将 SPC 与 FDC 系统集成至同一平台，可实现对制造流程的全面监控。操作人员与工程师能够同步跟踪 SPC 管控的工艺变量，并及时发现 FDC 系统识别的异常状况。当 SPC 与 FDC 数据实现联动时，工艺波动与潜在故障的关联性将更易研判，从而深化对因果关系的认知。这种全景化视角能显著提升决策质量。
这种集成系统还简化了数据管理流程，为所有工艺相关信息提供了一个集中式的数据存储平台。通过减少缺陷、优化工艺流程及降低停机时间，集成的 SPC-FDC 系统能够显著降低制造成本。良率的提升意味着每次生产中可用芯片数量增加，从而带来更高的收入。
### 设备数据与在线测量的关联分析
在半导体制造中，SPC 的一项先进应用是将设备数据与在线测量数据进行关联分析。这种关联分析有助于深入了解设备性能如何影响产品质量，此类关联分析有助于揭示 FDC 系统检测到的异常现象与 SPC 系统所追踪的关键工艺参数之间的关系，从而更准确地定位问题根源并优化制程控制策略。例如，电压波动异常（由 FDC 系统检测）与某一特定设备的运行参数（由 SPC 系统监控）之间存在相关性，表明可能存在设备问题。图 1 展示了另一个示例，即腔体温度与量测数据之间的关系。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/03/Interrelationship-between-equipment-temperature-and-the-inline-measurements-showing-inverse-correlation.jpg) 图 1：设备温度与在线测量数据的负相关关系
在半导体制造过程中，多种关联分析模型可早期识别偏离预期行为的异常。通过调整工艺参数来优化制程，此类关联分析能有效减少缺陷并提升效率。皮尔逊相关系数 (Pearson Correlation Coefficient) 便是量化这种关系强度与方向的重要工具之一。
### 皮尔逊相关系数
皮尔逊相关系数（通常以“r”表示）用于衡量两个变量 X 与 Y 之间的线性相关程度，其取值范围为 -1 至 1：
- r = 1 表示完全正线性相关
- r = -1 表示完全负线性相关
- r = 0 表示无线性相关
图 2 展示了不同设备传感器与实时产品测量数据的关联特性。如图所示，传感器 1 呈线性相关关系，表明其对产品尺寸有显著影响。0.99 的相关系数显示强正相关性，当出现异常行为时，该指标可为根本原因分析提供明确方向。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/03/Fault-Detection-sensors-correlations-with-SPC-inline-measurements-with-calculated-Pearson-Coefficient.jpg) 图 2：故障检测传感器与 SPC 在线测量数据的相关性分析（含皮尔逊系数计算结果）
### 基于相关性分析的 SPC 实施
SmartFactory SPC 专注于简化此类分析模型的部署流程。该平台提供了一个完整的生态系统，用于数据准备、模型选择和部署，并且能够直接与现有数据协同工作。该应用的核心优势之一是良好的用户体验和结果解读功能，便于将分析模型快速集成到工厂系统中。基于 Web 的报表功能实现模型性能的持续监控与维护。该解决方案的优势之一是能够自动关停可能生产不良品的设备，同时支持新设备认证和预防性维护 (PM) 周期验证。通过众多客户实践，我们观察到设备关键绩效指标 (KPI) 得到平稳提升，工艺窗口的扩展带来了更高效的产线监控和废品率降低。
### 结论
在半导体生产这一精准与效率至关重要的竞争领域，将 SPC 与 FDC功能整合于同一平台，为工艺管理提供了全面解决方案。这不仅关乎芯片生产本身，更是实现最高质量标准、可靠性与效率的必然选择。
随着半导体技术的不断进步，SPC 与相关性分析的重要性也将持续提升。采用这种集成方案的制造商，必将以更强的信心与应变能力，应对当前半导体市场的严苛要求。应用材料公司 SmartFactory 解决方案始终致力于为半导体制造商提供行业前沿的先进实践，助其达成质量与效率的双重目标。
## 常见问题解答
#### 什么是统计过程控制 (SPC) ?
统计过程控制是通过收集制造流程每个步骤的各类数据点，从而判断特定步骤是否正确完成的过程控制方法。
#### 什么是故障检测与分类 (FDC) 系统？
FDC 通过采集和分析设备参数，快速反馈工艺性能问题，有效预防突发故障导致的产能损失。
#### SPC 与 FDC 系统集成能为半导体工厂带来哪些效益？
将 SPC 和 FDC 系统集成在同一平台可简化数据管理，为所有工艺相关信息提供集中存储。该集成系统能最大限度减少缺陷、优化工艺流程并降低停机时间，从而实现显著的成本节约。
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Reduce costly, unplanned downtime in your factory with SmartFactory Monitor](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/smartfactory-monitor/)
**Published:** March 19, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Monitor your manufacturing software and system performance from anywhere in the world
**Content:**
#### Transcript
The challenges manufacturers face are everywhere, from process problems to equipment issues. One challenge that often flies under the radar, that is, until it’s too late, is issues with the software and servers that are critical in supporting factory operations. If a process tool goes down, it’s inconvenient.
But if your MES goes down, the entire factory goes down with it. In this video, we’ll take a look at the SmartFactory Monitor, a system specially designed to monitor all those supporting systems to prevent downtime and to keep your factory running smoothly. Your factory’s uptime is critical, and you almost certainly have metrics in place to monitor it and quality programs in place to improve it.
After all, keeping product moving through the factory and processing correctly are keys to your company’s profitability. And your manufacturing software systems all play a key role in both productivity and quality. That is, until something stops working.
Yes, we all hate it when that happens, but it does from time to time. A server goes down, or a network issue, or the power is accidentally shut down to the whole server room because of a tool install that’s happening nearby. The result is unplanned downtime, sometimes for the entire factory.
And that is a significant business impact. How many times has that happened in your factory? And how long did it take your IT team to respond to the problem and resolve it? How did it affect your production? And perhaps most importantly, how did it affect your company’s profits? The impact isn’t trivial. For a modest, low-volume wafer fab, an hour of unplanned downtime can have a $10,000 impact on the company’s bottom line.
Just an hour! For a medium-volume fab, it’s more like $100,000. And for a state-of-the-art, high-volume wafer fab, it can be as much as a million dollars. The painfully obvious question then is, how can we reduce or even avoid unplanned downtime for our manufacturing software systems? And the answer is using SmartFactory Monitor.
SmartFactory Monitor is a real-time monitoring software solution that allows you to identify problems and facilitates corrective action before your production systems are impacted, any of your production systems. In its most basic form, it provides a customizable, easy-to-digest dashboard showing the current state of your production systems.
This makes it almost trivial to see and send a notification when a problem occurs. Customizability is a key feature. It’s possible to create custom visualizations to display performance trends over time.
And it has predictive analytics capabilities that allows detection of performance anomalies before they become production impacts. SmartFactory Monitor runs on modest hardware in a small process footprint using your choice of OS. And perhaps best of all, it’s pre-integrated with other products in the SmartFactory software portfolio.
SmartFactory Monitor keeps track of all your manufacturing software and systems. The applications, the databases, and the servers, both Windows and Linux. The system monitors in real-time system performance logs, error logs, event logs, application logs, system logs, server logs, anything and everything that can provide a clue to system performance and health.
Everything is aggregated into Splunk, software that captures, indexes, and correlates real-time data that can then be used to generate automated notifications and create visualizations to highlight trends and spot problems. And it can be used as training data for machine learning algorithms that enable predictive analytics so issues can be identified and resolved before they become problems in the factory. Pre-built dashboards are available to get you up and running quickly, monitoring all your system logs.
And using Splunk, you can easily visualize system performance and detect trends, anomalies, and outliers using sophisticated prediction algorithms developed by Applied Materials engineers. To ease the load on your IT staff, we also offer optional remote monitoring for your production systems. This is a 24x7x365 service provided by Applied Materials’ own Global Information Systems support staff to monitor production and maintain performance, stability, and high availability of your manufacturing software and systems.
And if you purchase the supporting server hardware from Applied Materials, we can also include on-site hardware repair services for your SmartFactory Monitor installation. Experienced teams supporting remote monitoring are located around the world to provide continuous support for your factory wherever it’s located. Our team can help you get up and running quickly with SmartFactory Monitor in just a couple of weeks for basic production monitoring and a typical installation.
It’s only one additional week to add AI-based log analytics capabilities. And if you opt for remote monitoring, just a couple of more weeks to get you set up with a fully managed solution supported by experienced teams that will monitor your factory systems continuously. SmartFactory Monitor provides a comprehensive set of production monitoring capabilities to address many of the key support system challenges that manufacturers encounter.
The primary objective is to reduce unplanned factory downtime by decreasing the time it takes to identify and resolve system problems and, indeed, to prevent factory impacting problems altogether through performance trend analysis and predictive analytics. The result is increased system and application availability, improved operational efficiency, and, ultimately, increased profitability. SmartFactory Monitor provides the ideal monitoring solution with its comprehensive feature set, the ability to visualize system state and performance trends, quickly detect and even predict system failures, 24×7 global support for remote monitoring, and backed by a team you can trust that understands manufacturing.
Sound interesting? Reach out to us to learn more about SmartFactory Monitor. We’d be happy to schedule a technical session with your IT team to discuss your system and learn more about your system performance pain points. If you like what you see, and we think you will, we’ll be delighted to add you to the queue to install SmartFactory Monitor at your factory.
SmartFactory Monitor. It’s the ideal solution.
#### Transcript
The challenges manufacturers face are everywhere, from process problems to equipment issues. One challenge that often flies under the radar, that is, until it’s too late, is issues with the software and servers that are critical in supporting factory operations. If a process tool goes down, it’s inconvenient.
But if your MES goes down, the entire factory goes down with it. In this video, we’ll take a look at the SmartFactory Monitor, a system specially designed to monitor all those supporting systems to prevent downtime and to keep your factory running smoothly. Your factory’s uptime is critical, and you almost certainly have metrics in place to monitor it and quality programs in place to improve it.
After all, keeping product moving through the factory and processing correctly are keys to your company’s profitability. And your manufacturing software systems all play a key role in both productivity and quality. That is, until something stops working.
Yes, we all hate it when that happens, but it does from time to time. A server goes down, or a network issue, or the power is accidentally shut down to the whole server room because of a tool install that’s happening nearby. The result is unplanned downtime, sometimes for the entire factory.
And that is a significant business impact. How many times has that happened in your factory? And how long did it take your IT team to respond to the problem and resolve it? How did it affect your production? And perhaps most importantly, how did it affect your company’s profits? The impact isn’t trivial. For a modest, low-volume wafer fab, an hour of unplanned downtime can have a $10,000 impact on the company’s bottom line.
Just an hour! For a medium-volume fab, it’s more like $100,000. And for a state-of-the-art, high-volume wafer fab, it can be as much as a million dollars. The painfully obvious question then is, how can we reduce or even avoid unplanned downtime for our manufacturing software systems? And the answer is using SmartFactory Monitor.
SmartFactory Monitor is a real-time monitoring software solution that allows you to identify problems and facilitates corrective action before your production systems are impacted, any of your production systems. In its most basic form, it provides a customizable, easy-to-digest dashboard showing the current state of your production systems.
This makes it almost trivial to see and send a notification when a problem occurs. Customizability is a key feature. It’s possible to create custom visualizations to display performance trends over time.
And it has predictive analytics capabilities that allows detection of performance anomalies before they become production impacts. SmartFactory Monitor runs on modest hardware in a small process footprint using your choice of OS. And perhaps best of all, it’s pre-integrated with other products in the SmartFactory software portfolio.
SmartFactory Monitor provides a comprehensive set of production monitoring capabilities to address many of the key support system challenges that manufacturers encounter.
The primary objective is to reduce unplanned factory downtime by decreasing the time it takes to identify and resolve system problems and, indeed, to prevent factory impacting problems altogether through performance trend analysis and predictive analytics. The result is increased system and application availability, improved operational efficiency, and, ultimately, increased profitability. SmartFactory Monitor provides the ideal monitoring solution with its comprehensive feature set, the ability to visualize system state and performance trends, quickly detect and even predict system failures, 24×7 global support for remote monitoring, and backed by a team you can trust that understands manufacturing.
Sound interesting? Reach out to us to learn more about SmartFactory Monitor. We’d be happy to schedule a technical session with your IT team to discuss your system and learn more about your system performance pain points. If you like what you see, and we think you will, we’ll be delighted to add you to the queue to install SmartFactory Monitor at your factory.
SmartFactory Monitor. It’s the ideal solution.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Avalign Technologies 公司借助 SmartFactory Production Control 将计划员工作效率提升约 75%](https://appliedsmartfactory.com/semiconductor-blog/use-cases/avalign-technologies-case-study/)
**Published:** October 27, 2023
**Author:** Madhu Mamillapalli, Global Product Manager, Planning Solutions
**Excerpt:** Production Control 通过仿真模拟识别瓶颈并克服挑战。
**Content:**
## 内容概览
- [ 生产管控挑战 ](#index2)
- [ 借助 SmartFactory Production Control 解决方案提升关键绩效指标 (KPI) ](#index3)
- [ 附加收益 ](#index4)
- [ 迈向持续改进之路 ](#index5)
- [ 常见问题解答 ](#index6)
[SmartFactory Production Control](/zh-hans/semiconductor/productivity-solutions/production-control/) 是一套用于模拟生产和计划操作的产能规划系统。通过在模拟环境中复制生产活动，该系统能识别出提高在制品 (WIP) 流转、产能利用率和产出效率的机会——所有这些都不会影响实际工厂运营。作为骨科医疗器械领域全球领先的委托生产商之一，Avalign Technologies 公司采用 SmartFactory Production Control 解决方案成功应对了多项关键挑战，包括生产排程优化、按时交付率提升以及瓶颈工作中心的利用率改善。
### 生产管控挑战
作为一家高资本投入的订单型制造商，Avalign 公司面临着该领域固有的多项挑战：
- 缺乏强大且优化的有限生产排程系统
- 缺少全面的中长期产能规划
- 支持持续改进的“假设分析” (What-if analysis) 能力有限
- 针对客户订单交期变更（提前 / 延后）的重新排产耗时过长
- 跨厂区数据标准不统一导致数据挖掘流程冗长
这些挑战导致客户满意度下降、设备生产效率降低、生产周期延长、产线失衡以及制造成本增加。
### 借助 SmartFactory Production Control 解决方案提升关键绩效指标 (KPI)
为应对这些挑战，Avalign 公司部署了 SmartFactory Production Control 解决方案。该方案使其能够模拟工厂运营情况，并预先识别生产排程中的潜在瓶颈。
通过将该系统的输出与派工和排程解决方案集成，Avalign 公司成功实现了精细化生产计划的制定。由此，其计划制定周期从原先耗时 2-3 天的周计划模式，转变为如今每日不足 1 小时的动态排程模式。这一改进使计划员的工作效率提升约 75%，使他们能够将更多精力投入到多种假设情景分析及其他规划工作之中。
*这一改进使计划员的工作效率提升约 75%，使 Avalign 公司能够将更多精力投入多种假设情景分析及其他规划工作之中。*
此外，通过运行高速 Production Control 仿真模拟（采用精细化建模），Avalign 公司能够为客户提供更快速、更准确的未结订单状态更新及新交货排期。这一改进将客户订单响应时间从原先的 2-3 天缩短至数小时，同时数据准确率显著提升，并推动按时交付率提高约 5%。
*这一改进将客户订单响应时间从原先的 2-3 天缩短至数小时，同时数据准确率显著提升，并推动按时交付率提高约 5%。*
通过简易建模模拟运行，Avalign 公司实现了基于场景的排程优化，有效提升设备利用率和产线平衡性，使瓶颈工作中心利用率提高 5-10%。
*Avalign 公司的瓶颈工作中心利用率提高 5-10%。*
详细的报表和图表帮助识别生产瓶颈和低效环节，在执行前即可优化生产计划，从而实现更高效的在制品 (WIP) 管理和更动态的工单发放机制——从原先的固定周期模式转变为按需发放模式，同时保持更均衡的在制品水平。此外，通过实施搭载 AutoSched™（专为复杂规划设计的强大仿真工具）的 Production Control 解决方案，Avalign 公司实现了精细化的中长期产能规划。
### 附加收益
Avalign 公司通过采用 SmartFactory Production Control 解决方案还实现了以下显著改进，如下图 1 所示。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/production-control-solution.png) 图 1：SmartFactory Production Control 解决方案实施后解决的问题对照表
### 迈向持续改进之路
通过采用 SmartFactory 解决方案，Avalign 公司得以利用统一平台提升工厂生产与计划管理效率。公司重点改善了数据集成、可用性与准确性，同时完成了与自动化解决方案相关的业务流程变革，并成功建立了持续改进的文化理念。
## 常见问题解答
#### SmartFactory Production Control 解决方案为 Avalign Technologies 公司带来哪些效益？
Avalign Technologies 公司实现计划员工作效率提升约 75%，优化了生产排程，提高按时交付率，并改善瓶颈工作中心利用率。
#### 客户服务水平因 SmartFactory Production Control 解决方案获得哪些提升？
订单响应时间从 2-3 天缩短至数小时且准确率更高，按时交付率提升约 5%。
#### SmartFactory Production Control 解决方案如何优化设备利用率和产线平衡？
通过简易建模模拟实现基于场景的排程，提升设备利用率和产线平衡，使瓶颈工作中心利用率提高 5-10%。
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Semi
---
### [从 FactoryView（运营可视化）迈向智能决策支持（下篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
**Published:** June 25, 2025
**Author:** Samantha Duchscherer and Michael Frenna
**Excerpt:** 通过 AI 赋能，提升晶圆厂运营决策效率与整体绩效
**Content:**
[ 上篇：FactoryView 与 AI ](/zh-hans/semiconductor-blog/al-ml-zh-hans/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
## 内容概览
- [ 当前 FactoryView 的使用体验 ](#index1)
- [ 实时洞察与智能决策建议 ](#index2)
- [ 利用合成数据提升准确性 ](#index3)
- [ 减少结果变异性 ](#index4)
- [ 分阶段的部署方法 ](#index5)
- [ 总结 ](#index6)
在本篇 FactoryView 介绍的下篇中，Sam 与 Michael 深入探讨了 AI 如何推动 FactoryView 从实时运营监控平台，演进为面向晶圆厂的智能决策助理。他们讨论了 AI 如何实现更精准的预测并提供可执行的建议——这在复杂且快速运转的晶圆厂环境中尤为关键——同时阐述了团队在迈向更高自主化运营的过程中，如何逐步建立对技术的信任。
Sam：现在我对 FactoryView 有了更深入的了解，我们来聊聊 AI 吧。你能介绍一下，目前用户是如何使用 FactoryView 的吗？如果 AI 能够在这个过程中提供智能建议，那么用户的体验或最终结果会发生怎样的变化？
Michael: 目前，用户需要手动监测并解读工厂的关键绩效指标 (KPI)。他们会根据应用中看到的数据，决定在特定时间点应该关注哪个区域，或者将资源部署到哪里。当前决策仍主要依赖人工判断，而 FactoryView 提供的是一个面向晶圆厂日常运营的决策支持平台，协助用户更高效地做出判断。
而 AI 的真正价值在于提升决策本身的质量。人工决策往往会因为决策者未能掌握晶圆厂整体运行状态，而给产线引入更多不稳定性。比方说，操作员可能会非常专注于某个特定区域的特定问题，但他们并不清楚这种局部优化会对整座晶圆厂的绩效产生什么影响。理想的做法是，利用 AI 从全局审视工厂，并确定对整体最优的行动方案。这样才能避免那种有时会导致工厂运行效率低下的局部优化。
Sam：听起来，你希望 AI 能够通过实时的洞察和建议来主动引导用户，对吗？
Michael: 没错。我认为可以先从提供类似建议开始，比如： “某区域的1号机台宕机了，如果优先恢复该设备，将能提升工厂整体吞吐量 X%。” 同时，系统还会给出决策背后的理由，比如：“基于接下来几小时即将进入该区的在制品数量，以及该设备过去一周的运行次数，我们预测如果能重启这台设备，工厂吞吐量将提升 X%。”
Sam：明白了——所以不仅仅是解释预测结果，还要提供可操作的建议。换个话题，你能谈谈 AI 如何预测的准确性吗？特别是在缺乏或没有历史数据可供参考的情况下。
Michael: 目前，FactoryView 依赖统计方法，基于历史数据做出预测。当数据基础扎实时，效果不错。但如果数据有限或不可靠，比如晶圆厂导入新设备时，就会面临挑战。在这种情况下，传统统计方法的预测准确性会显著受限，因为没有足够的运行历史来做精准预测。
而这正是 AI 的用武之地。它可以通过分析类似产品来生成合成数据，填补数据空白，从而提升预测的准确性。举个例子，在 FactoryView 中，有一张图表追踪每个批次从投入到出货的全流程。对于已完成的步骤，我们可以显示真实数据；但对于未来的步骤，目前只能依靠基于历史平均值的基础预测。这种方法对于几乎没有历史记录的新设备就失效了。而 AI 可以介入，做出更智能、更具上下文感知的预测——将预期在制品数量、设备性能以及类似产品的生产模式等因素都考虑进去。这将使系统更加可靠，尤其是在高度动态、快速变化的生产环境中。
Sam：明白了。现在我扮演一下怀疑论者。如果有人觉得他们需要的不是 AI，而是更好的报表工具，你会怎么回应？我们如何证明 AI 带来的是本质上的不同？
Michael: 我会说，在半导体工厂里，变量太多了，人类根本无法凭一己之力判断自己的决策是否最优。人们在晶圆厂里做出自认最优的决策时，常常会忽略掉很多变量；他们看到的只是所有变量中的一小部分。即便有报表能够呈现所有相关变量，人工也很难在有限时间内完成跨系统、跨流程的综合判断。
Sam：很有见地！我希望能继续聊下去，但最后我们还是来谈谈信任问题。如果用户连手动决策都难以完全信任，我们又如何帮助他们建立起对 AI 驱动型建议的信心呢？
Michael: 在我看来，这需要采用一种分阶段的方法。首先，AI 只是提出建议并解释其理由。这个阶段需要接受制造运营团队一定程度的审视和训练，因为总有一些 AI 尚未掌握的情况，需要从该团队的反馈中学习。一旦制造团队开始信任这些更加充分、更加全面的建议，晶圆厂就可以开始允许 AI 不仅提出建议，还能采取行动。例如，执行 MES 系统（制造执行系统）变更、处理自动化晶圆厂中的特定警报、调度自动物料搬运系统将物料运送到指定区域等等。
### 总结
FactoryView 作为面向日常运营的决策支持系统，助力半导体企业高效利用资源，精准定位并处理影响晶圆厂绩效的关键问题。借助 AI 技术，FactoryView 将不仅能够识别影响晶圆厂的问题，还能提供优化建议，并在未来逐步实现从 “识别问题” 到 “预测风险” ，再到 “自动化执行优化动作” 的闭环运营能力。
## 关于作者
Samantha Duchscherer，全球产品经理
Samantha 是 SmartFactory AI™ Productivity、Simulation AutoSched™ 和 Simulation AutoMod™ 的全球产品经理。在加入应用材料公司自动化产品事业部之前，她曾担任博世工业4.0项目经理，并曾任数据科学家一职。早期她还曾作为研究助理任职于橡树岭国家实验室地理信息科学与技术组。Samantha 持有田纳西大学诺克斯维尔分校数学硕士学位，以及北乔治亚大学达洛尼加分校数学学士学位。
Michael Frenna，全球产品经理，工作流自动化与工厂分析
在现任职位上，Michael 负责推动工作流自动化和工厂分析产品的路线图规划，以满足全球半导体客户不断增长的业务需求。在此之前，Michael 曾在半导体行业从事制造运营与系统优化工程工作，积累了深厚的专业经验，在一家 150mm/200mm 前道晶圆厂任职期间主导并推进了多项数字化转型和工业 4.0 相关项目。凭借对技术的热忱以及持续推动创新的使命感，Michael 目前正与全球各地的客户紧密合作，持续提升制造能力和运营效率。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [从 FactoryView（运营可视化）迈向智能决策支持（上篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
**Published:** June 25, 2025
**Author:** Samantha Duchscherer and Michael Frenna
**Excerpt:** 通过先进的决策支持系统，推动工厂运营转型。
**Content:**
[ 下篇：FactoryView 与 AI ](/zh-hans/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
## 内容概览
- [ 定义 FactoryView ](#index1)
- [ 实时监控 ](#index2)
- [ 无需编码，创建新报表 ](#index3)
- [ 获取最佳实践 (Best Known Methods) ](#index4)
- [ 变更管理 ](#index5)
- [ 部署与集成 ](#index6)
在这篇博客中，Sam 与 Michael 展开对谈，探讨 FactoryView 如何通过实时运营可视化、标准化指标体系以及可直接指导运营决策的洞察，推动晶圆厂运营方式的全面升级。从简化决策流程，到为无缝集成现有的 APF 产品和解决方案做准备，本次对话深度剖析了 FactoryView 为何不仅仅是一款报表工具——它更是推动制造运营更智能、更高效、更高度协同的关键催化剂。
Sam：按照惯例，我还是想从 AI 这个话题聊起。不过我们是不是可以先明确一下， FactoryView 到底是什么？它能给制造商带来哪些实际价值？
Michael: 当然。FactoryView 属于我们 SmartFactory 报表解决方案 (SmartFactory Reporting) 的一部分。它通过对工厂运行状态及关键绩效指标 (KPI) 的实时可视化呈现，帮助制造组织监控最关注的核心运营指标，并确保规划与排程目标在整个制造组织内保持一致。
理想情况下，它应作为一套面向日常运营的决策支持系统，帮助制造团队提升资源利用效率，聚焦并处理影响晶圆厂运行的关键问题区域。
Sam：明白了。那这套系统是预设好的固定报表，还是说用户可以自定义运营看板内容？
Michael: 看什么内容，我们有预设。不过，客户也可以根据预设的瓶颈判定逻辑，来确定每个班次中哪些区域最需要关注。不同晶圆厂识别瓶颈的方法也不尽相同。
报表的设计充分考虑了不同用户的视角：高层概览图主要面向制造经理或制造总监，而各个模块区域的视图则服务于相应的生产区域经理。
Sam：在这个系统里， “实时 “具体是怎么定义的？
Michael: 所谓实时，是指工厂的 MES 系统（制造执行系统）每发生一笔事务，这笔事务会立即被复制并显示在 FactoryView 应用中。跟这些事务关联的 KPI 指标也会同步刷新。比如说，一个批次从当前工序流转到下一道工序，这是一笔事务；设备宕机了，记录状态变化，这是一笔事务；设备恢复运行了，这也是一笔事务。
所有与设备实时状态相关的报表，以及反映工厂内物料流转情况的关键指标，都会受到 FactoryView 实时特性的影响。
Sam：听起来确实很有价值。但说实话，这和制造组织中的工程团队（如制造运营工程师）使用其他工具自行开发定制化看板相比，到底有什么实质性的不同？
Michael: 问得好！关键要理解一点：FactoryView 不需要制造运营工程师、IT 或开发人员去搭建和维护运营看板。它是开箱即用的，制造运营工程师或 IT 人员完全可以把它当作辅助决策、协调制造团队的工具。换句话说，就是把报表开发的工作从 IT 和 IE 的职责中剥离出来，让他们能专注于利用数据为工厂做更优决策。
另外想补充的是，大多数客户其实都有自己的工厂报表体系——他们都需要从宏观上掌握工厂的运行状态，朝着既定目标推进。但问题是，制作这些报表对负责这项工作的人来说相当繁琐，开发和维护都要花大量时间。而且这些报表往往分散在不同的团队或系统中，形成了数据孤岛，甚至存在信息缺口。说到运营报表，经常出现的情况是：好几张报表都在统计同一个 KPI，但计算逻辑却不一致。更重要的是，有些报表是工厂原本没有、但 FactoryView 能提供的。其一大优势就在于，能够为晶圆厂运营报表提供一个统一、权威的“单一数据源” 。
Sam：所以，我们是在做标准化和可扩展的事，并向客户提供他们过去并不具备的报表能力。不过我们再深入一点——相比现有的报表工具或自行开发的定制化看板，FactoryView 到底能为团队带来哪些实质性的增益？
Michael: 我们的解决方案是建立在多年为客户部署定制化报表的经验之上的，因此积累了大量的半导体行业特定需求。当向客户展示某个方案时，他们通常能获得新的洞察，比如发现一些原本没想过要追踪、但其实是源自业界最佳实践 (Best Known Methods) 。当客户参与到这一报表解决方案的产品路线规划中时，他们就能借鉴行业通用的报表方面的最佳实践，而不是仅仅依赖自己一直在用的那套指标体系。
Sam：听你这么介绍，FactoryView 的价值已经非常清楚了。那我们来聊聊实际落地的问题——实施这类系统，最棘手的准备工作是什么？制造商应该提前考虑哪些方面才能确保顺利落地？
Michael: 我建议先做好变更管理。制造团队多年来已经形成了自己的一套关键指标审视方式，而引入新系统可能会改变这种固有模式。每天的站会流程可能需要微调，要把新报表融入进去，团队也需要一个学习如何使用这套应用的过程。所以，前期必然会经历一个变更管理周期。
除了变更管理，另一个非常关键的前期工作是验证指标。每次部署，我们都需要全面采集 MES 系统数据，确保应用能够适配客户需求，最关键的是要让每项指标的计算逻辑和客户定义完全对齐。
Sam：最后我们来总结一下——变更管理能否成功，很大程度上取决于这个解决方案与现有系统的集成难易度，可以这么说吗？
Michael: 没错。因为 FactoryView 与我们所有 EngineeredWorks 解决方案基于相同的通用数据模型，所以在这个方案中使用的许多输入数据以及所生成的工厂 KPI，都可以与其他解决方案实现共享。举个例子，我们计算排程所需的吞吐量统计数据，和 FactoryView 里用的是同一个口径。在 FactoryView 里显示为 “运行” 的设备，在排程解决方案里也同样被视为 “运行” ，而且设备清单也是完全一致的。
实施这套报表解决方案，实际上也是在为后续部署排程解决方案打下很好的基础——因为报表所需的关键数据，排程系统也同样需要。这样就能有效缩短部署周期。
### 下期预告
在下一篇文章中，Sam 和 Michael 将继续探讨 AI 技术如何为 FactoryView 带来更多优势。
## 关于作者
Samantha Duchscherer，全球产品经理
Samantha 是 SmartFactory AI™ Productivity、Simulation AutoSched™ 和 Simulation AutoMod™ 的全球产品经理。在加入应用材料公司自动化产品事业部之前，她曾担任博世工业4.0项目经理，并曾任数据科学家一职。早期她还曾作为研究助理任职于橡树岭国家实验室地理信息科学与技术组。Samantha 持有田纳西大学诺克斯维尔分校数学硕士学位，以及北乔治亚大学达洛尼加分校数学学士学位。
Michael Frenna，全球产品经理，工作流自动化与工厂分析
在现任职位上，Michael 负责推动工作流自动化和工厂分析产品的路线图规划，以满足全球半导体客户不断增长的业务需求。在此之前，Michael 曾在半导体行业从事制造运营与系统优化工程工作，积累了深厚的专业经验，在一家 150mm/200mm 前道晶圆厂任职期间主导并推进了多项数字化转型和工业 4.0 相关项目。凭借对技术的热忱以及持续推动创新的使命感，Michael 目前正与全球各地的客户紧密合作，持续提升制造能力和运营效率。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [The potential to transform reporting with FactoryView and AI (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
**Published:** June 25, 2025
**Author:** Samantha Duchscherer and Michael Frenna
**Excerpt:** Improve user experience and factory outcomes with AI
**Content:**
[ Part 1: FactoryView and AI ](/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
## What's Inside
- [ Current FactoryView experience ](#index1)
- [ Real-time insights and recommendations ](#index2)
- [ Improving accuracy with synthetic data ](#index3)
- [ Reducing variability ](#index4)
- [ Stepwise approach to deployment ](#index5)
- [ Conclusion ](#index6)
In this follow-up to their FactoryView intro, Sam and Michael explore how AI can transform the tool from a real-time monitor into an intelligent assistant. They discuss how AI improves forecasting and offers actionable recommendations—especially key in complex, fast-moving fab environments — and how teams can build trust as they move toward more autonomous operations.
Sam: Now that I understand FactoryView better, let’s bring AI into the discussion. Can you walk me through how someone is currently using FactoryView, and how their experience or outcomes might change if AI could start offering intelligent suggestions along the way?
Michael: Currently, the user monitors and interprets the factory KPIs. Based on what they’re seeing in the application around those, they’ll decide what area to focus on or where to deploy resources at any given time. Decision-making is currently a manual process. We’re just providing a decision support system.
Where AI would add significant value would be in the quality of the decision itself. Often, when humans are making decisions, it causes more variation because they don’t understand the factory’s overall dynamics. They might be very focused on a specific problem in a specific area, but they don’t know the impact that local optimization may have on the factory’s performance. It would be ideal if instead you used AI to take a holistic view of the factory and determine the best action for it. This would avoid the kind of local optimizations that can sometimes make a factory run very inefficiently.
Sam: Essentially it sounds like you would like AI to actively guide users with real-time insights and recommendations, right?
Michael: Yes, I think it could start out as something along the lines of making suggestions like, “Tool one is down in this area and recovering it would optimize your factory throughput by X percent.” There also would be some kind of rationale behind why it’s making that decision, such as “Based on the amount of WIP you’re going to receive in the next few hours and how many moves that equipment has made in the past week, we expect if you got this machine up you would improve the factory throughput by X.”
Sam: Got it—so beyond just explaining predictions, it’s also about making actionable recommendations. Switching gears a little, can you now walk me through how AI could enhance forecasting accuracy, especially when there’s limited or no historical data to work with?
Michael: Right now, FactoryView relies on statistical methods to make predictions based on historical data. That works well when we have a solid data foundation—but it becomes a challenge when the data is limited or unreliable, like with newly introduced devices in the factory. In those cases, traditional methods fall short because there just isn’t enough run history to make accurate forecasts.
That’s where AI can really add value. It can generate synthetic data by analyzing similar products, helping to fill those gaps and improve forecast accuracy. For example, in FactoryView, we have a chart that tracks each lot’s journey through the factory—from start to shipment. We can show the completed steps with real data but, for future steps, we currently rely on a basic prediction using historical averages. That approach breaks down for new devices with little to no history. AI could step in here to make smarter, more context-aware predictions—factoring in things like expected WIP, equipment performance, and patterns from similar products. That would make the system far more reliable, especially in dynamic or fast-changing production environments.
Sam: I see; let me play the skeptic for a moment. What would you say to someone who thinks they don’t need AI, just better tools to build reports? How do we make the case that AI adds something fundamentally different?
Michael: I’d say, in a semiconductor factory there are too many variables for humans to contemplate whether the decision they’re making is the best decision. What often happens when people make what they think is an optimal decision in a semiconductor factory is that they overlook a number of variables; they’re only looking at a subset of all the variables in play. Even if there were a report that could provide them with all the necessary variables, I think it would take a human a very long time to make that determination, if they could do it at all.
Sam: This is great insight! I would love to continue but let’s end on the trust issue. If users already struggle to trust manual decisions, how can we help them feel confident in AI-driven recommendations?
Michael: To me, it would be a stepwise approach at first, where it starts by just suggesting and explaining its rationale for the suggestion. I think it would go through some level of scrutiny and training from the manufacturing operations team, because there would be things the AI isn’t aware of yet and needs feedback from that team to learn. Once the manufacturing team starts to trust these more informed suggestions, then I envision a factory would start to allow it to not just suggest, but to act. This could be making MES changes, handling certain alerts in an automated fab, sending material handling systems to move material to certain areas, and such.
### Conclusion
FactoryView is a decision support system for daily operations that helps semiconductor organizations effectively utilize their resources and address areas that are impacting the fab. With the benefit of AI technology, FactoryView would be able to not only identify issues affecting the fab, but provide suggestions for optimization and, possibly, take action to remedy problems before they occur.
## About the Authors
Samantha Duchscherer, Global Product Manager
Samantha is the Global Product Manager overseeing SmartFactory AI™ Productivity, Simulation AutoSched® and Simulation AutoMod®. Prior to joining Applied Materials Automation Product Group Samantha was Manager of Industry 4.0 at Bosch, where she also was previously a Data Scientist. She also has experience as a Research Associate for the Geographic Information Science and Technology Group of Oak Ridge National Laboratory. She holds a M.S. in Mathematics from the University of Tennessee, Knoxville, and a B.S. in Mathematics from University of North Georgia, Dahlonega.
Michael Frenna, Global Product Manager, Workflow Automation and Factory Analytics
In his current role, Michael drives road map initiatives for Workflow Automation and Factory Analytics offerings to meet the growing needs of Semiconductor customers worldwide. Prior to his current role, Michael honed his expertise as an Industrial Engineer in the semiconductor industry, where he helped drive digital transformation and I4.0 initiatives for a 150mm/200mm front-end fab. With a passion for technology and a commitment to driving innovation, Michael continues to work with customers from around the world in advancing manufacturing capabilities and operational efficiencies.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Advantages of decision-tree models](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/tree-based-models/)
**Published:** January 23, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Research demonstrates decision trees outperform deep learning with tabular data.
**Content:**
In our recent customer use case, “[Achieve accurate lot cycle time predictions for more on-time deliveries](/blog/achieve-accurate-lot-time),” we noted we determined the most appropriate ML model for the customer’s needs was a gradient boosted tree-based machine learning model, particularly the Light Gradient Boosted Machine implementation. This decision is supported by recent research conducted by Léo Grinsztajn, Edouard Oyallon, and Gaël Varoquaux at Inria Saclay Centre and Sorbonne University, whose work concluded decision trees outperform deep learning on medium-size tabular data.
Noting that deep learning has “enabled tremendous progress on text and image datasets,”1 researchers stated it had not been proven to be superior at processing these datasets. To compare the performance of the models, they collected 45 tabular datasets, each comprised of more than 3,000 real-world examples. They then trained standard and novel deep learning methods such as vanilla neural network, ResNet, and two Transformer-based models, as well as tree-based models including XGBoost, gradient boosting machines and Random Forests, among others. Each model was trained 400 times, searching randomly through a predefined hyperparameter space.
In assessing the models’ performance, the best tree-based models performed 20 to 30 percent better than the best deep learning models, when averaged across all tasks. They also found neural networks to be much more susceptible to random or less important data features than decision trees. When the authors removed uninformative features, the performance of the two models was more similar. When adding random features to the datasets, the neural networks showed a sharp decline.
The authors concluded, “Results show that tree-based models remain state-of-the-art on medium-sized data (∼10K samples) even without accounting for their superior speed.”
**REFERENCE**
1\. Grinsztajn, L., Oyallon, E., Varoquaux, G. Why do tree-based models still outperform deep learning on tabular data? NeurIPS22 Datasets and Benchmarks Track, Nov 22, New Orleans, United States. hal-03723551v2
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [突破壁垒：实现半导体行业更高水平的自动化](https://appliedsmartfactory.com/semiconductor-blog/productivity/removing-barriers-in-semiconductor-industry/)
**Published:** October 9, 2024
**Author:** Michael Frenna, Global Product Manager, Workflow Automation and Factory Analytics
**Excerpt:** 行业技术进步正助力传统晶圆厂部署自动化解决方案
**Content:**
## 内容概览
- [ 自动化需求的驱动因素是什么？ ](#index1)
- [ 传统晶圆厂面临的障碍 ](#index2)
- [ 战略与技术解决方案 ](#index3)
- [ 机器人技术应用 ](#index4)
- [ MES系统技术进步 ](#index5)
- [ 结论 ](#index6)
应用材料公司自动化产品事业部为全球客户提供自动化软件解决方案。根据我们的部署经验，传统晶圆厂（主要针对仍大量依赖人工操作的 150mm/200mm 前道晶圆厂）与运行全自动化“无人化”生产的 300mm 晶圆厂之间，存在显著的自动化成熟度差距。
### 自动化需求的驱动因素使什么？
近年来，市场对需要更高性能芯片的新技术需求呈现持续增长态势，促使半导体制造商在扩大产量的同时，还需应对日益复杂的制造工艺。为了生产这些高性能芯片，所需的工序和人力投入显著增加，尤其是在仍采用人工操作的传统晶圆厂中，给直接劳动生产力带来了巨大压力。制造商们意识到，面对制造过程中不断增长的需求和复杂性，必须采用自动化解决方案，因为仅靠增加人力来解决问题成本过高。
### 传统晶圆厂面临的障碍
我们已经确定有三个主要领域，对传统工厂实施自动化构成了关键障碍。首先是拥有成本 (Cost of Ownership) 问题。传统制造商通常规模较小，预算有限，难以承担重大基础设施改造费用。这些工厂大多建于20世纪80年代至90年代初，早于 300mm 制造时代，因此厂房设计未考虑天车运输系统 (OHT)。存在厂房高度不足，设备间距不符合自动化物料搬运 (AMHS) 要求等结构局限，使其处于明显劣势。相比之下，300mm 晶圆厂在设计之初就配备了自动化物料搬运系统 (AMHS)，采用前开式统一晶圆盒 (FOUPs) 并适配 300mm 大尺寸载具运输，使其在自动化应用方面具有先天优势。
对未在初期建设时规划自动化物料搬运系统的传统晶圆厂进行改造，可能面临极高的成本压力。这类设施改造涉及多项复杂工程：需要搬迁高价值的工艺设备、实施大规模基建工程、并对现有操作人员进行再培训——所有这些都必须在不中断当前生产的情况下完成。此外，运行半导体制造自动化软件所需的高性能服务器，其高昂的前期投入成本也属于成本过高的范畴。
制约传统晶圆厂提升自动化水平的另一关键因素在于专业技术人才的短缺。自动化系统的集成与维护需要配备大规模的 IT 团队，而传统晶圆厂通常预算有限，IT 团队规模较小，这使得他们在维护制造执行系统 (MES) 及其他关键 IT 基础设施之外，无力承担自动化系统的额外运维工作。
最后，传统系统通常由各自独立的单点解决方案构成，缺乏全自动化工厂所必须的功能整合。许多传统晶圆厂的自动化架构中存在多种自研解决方案和/或来自不同供应商的商业解决方案，这些系统若未经大量开发工作便无法实现完全集成。这种集成缺失问题如下图 1 所示。制造商们深知，要实现全自动化工厂就必须整合这些系统，但所需的开发工作量巨大，这对于 IT 团队规模较小的制造商构成了重大挑战。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/integration-pyramid.png) 图 1：制造商在实现从企业层到生产层的数据交换自动化方面面临挑战
### 战略合作与开箱即用解决方案
尽管传统制造商面临资金和运营方面的障碍，但目前已有解决方案能助力其向高度自动化生产环境平稳过渡。商业供应商已开始建立战略合作伙伴关系，共同为客户开发低成本“开箱即用” (out of box) 或预集成自动化解决方案。这些方案通过大幅降低开发与维护所需的 IT 资源开销，有效减少了客户的总体拥有成本。
此外，硬件和软件供应商正逐步推出模块化解决方案，这些方案能够与现有量产晶圆厂的系统共存。典型的例子包括与 MES 系统无关的解决方案——这些方案不依赖特定制造执行系统，而是 能够兼容任何类型的 MES 系统解决方案，甚至包括客户自主开发的系统。
### 机器人技术应用
移动机器人技术（如自动搬运车 ARV、自动导引车 AGV 和协作机器人 co-bot）的进步，正在满足传统晶圆厂的独特需求，且无需对现有设备进行彻底改造。现有工厂的基础设施和系统往往难以适配传统自动化物料搬运系统 (AMHS)，例如天车运输系统 (OHT)。OHT 系统需要特定的厂房高度，且安装配置导轨系统通常需要耗时数年进行建设，不仅成本高昂，还会对现有产线运营造成严重干扰。相比之下，移动机器人可直接部署在车间特定区域，无需半导体制造商一次性完成全面改造或部署。传统晶圆厂已成功在空间狭窄、高度不足的区域部署移动机器人，且未对生产造成重大影响。
### MES 系统技术进步
制造执行系统（Manufacturing Execution System，简称 MES 系统）是一款监控和管理制造运营的核心软件。当前许多客户使用的 MES 系统主要存在两类问题：或是采用已有数十年历史的商业系统，或是使用十年前甚至更早自主开发的 MES 系统，这些系统已无法适应现代制造工艺的复杂需求。随着生产流程要求的不断提升，企业往往通过在 MES 系统外围构建单点解决方案来填补功能缺口，这种做法正是导致前文所述系统集成问题的根源。
现代制造执行系统的技术进步使其能够应对当前复杂的半导体工艺流程，同时也降低了自动化实施门槛。低代码和无代码开发工具的应用显著提升了开发效率，减少了对 IT 资源的依赖。制造商们现在拥有了支持自动化工厂系统集成的工具，能够更高效地维护各类自动化软件解决方案。
### 结论
尽管制造商深知自动化的重要性，但传统晶圆厂在实施过程中始终面临诸多挑战。由于这些障碍的存在，他们难以跟上行业 领导者的发展步伐。值得关注的是，通过降低成本与提供更强大的技术资源，行业近年来在解决这些问题方案已取得重大进展。我们正在推动半导体行业迈向一个更具普惠性的自动化新时代。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [运用人工智能解决方案提升半导体运营效率](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/semiconductor-business-enhancement-with-ai/)
**Published:** March 10, 2025
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** 助力质量与生产力提升，保持市场领先地位。
**Content:**
## 内容概览
- [ 人工智能系统的核心能力 ](#index1)
- [ 人工智能技术如何赋能制造业 ](#index2)
- [ 提升生产力与质量 ](#index3)
- [ 增强运营效率 ](#index4)
- [ 人工智能在制造业的实际应用 ](#index5)
- [ 人工智能在制造业的未来发展趋势 ](#index6)
人工智能 (AI) 是指对计算机系统或机器进行编程，使其能够消化数据，并基于这些数据执行决策的过程。当拥有足够的数据、算力和上下文时，人工智能便能做出人类智能前所未见的决策。这种能力使得人工智能能够提供创新的解决方案与洞察，从而显著提升企业运营效率与生产力。
### 人工智能系统的核心能力
人工智能系统通常具备四项基本能力：
- 借助摄像头、麦克风或传感器感知周围环境。
- 通过模式检测与上下文识别，从这些输入中提取有用信息。
- 基于所理解的信息采取行动。
- 通过对过往行动的评估结果，持续优化未来行为。
### 人工智能如何赋能制造业
人工智能技术正为制造业创造多重效益。它不仅能够有效提升产品良率与生产速度，还能显著降低运营成本、改善产品质量。更值得关注的是，基于人工智能的系统能够预测设备故障、安排维护计划、优化供应链管理，从而最大限度减少生产中断，实现运营效率的全面提升。这些智能系统通过整合传感器、机器及人员数据，帮助制造企业实现数据驱动的运营，持续优化生产与维护流程，在提升产品品质的同时积极应对可持续发展挑战。
以我们的 SmartFactory 产品组合为例，这套人工智能驱动的自动化软件解决方案能够协同优化良率与生产周期，并为制造运营赋能。
### 提升生产力与质量
人工智能驱动的自动化技术通过让机器比人类更快速、更精准地执行任务，显著提升生产力，从而实现更高的产出。人工智能还能实时监控生产线，检测缺陷并确保只有高质量产品才能进入市场。
人工智能还能为制造运营提供智能化、实时化的流程协同与优化，这一能力不仅局限于单个工厂内部，更可延伸至整个供应链体系。具体表现为：改进质量保证与质量控制 (QA/QC) 的测试检验流程，合理优化 QA/QC 检测项目数量，并更深入地洞察故障产生的根本原因。
### 增强运营效率
人工智能解决方案可以通过自动化日常任务与优化工作流程，显著提升运营效率。例如，人工智能可分析生产数据以定位瓶颈环节并提出优化建议，从而确保制造流程稳定、高效地运行。
人工智能驱动的制造方式通过生产精密部件来提升产品安全性与可靠性，进而增强性能与系统安全。它还有助于最大程度减少生产错误、改进产品设计，并加速产品上市时间。
### 人工智能在制造业的实际应用
在实际生产中，人工智能正通过多种方式推动制造业升级。例如，基于人工智能的预测性维护系统能够预判设备故障发生时间，实现及时维修，有效减少意外停机。人工智能还被应用于质量控制领域，能够比人工检验员更准确地检测产品缺陷。
我们的 SmartFactory AI 解决方案提供集成式自动化软件，旨在实现效率最大化并赋能制造运营。这些解决方案涵盖生产力提升、流程质量改进、MES 系统集成以及供应链管理，覆盖从企业计划到生产控制的各个环节。
### 人工智能在制造业的未来发展趋势
人工智能在制造业的应用前景广阔。随着技术的持续进步，人工智能将带来更高的生产效率和更多的创新突破。在其不断演进的过程中，人工智能将在助力制造商保持竞争力、满足日益增长的市场需求方面，扮演越来越关键的角色。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [制造自动化软件助力实现效率与可持续发展目标](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/achieve-efficiency-and-sustainability-goals/)
**Published:** September 12, 2024
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** 推进工厂自动化，优化制造流程并减少资源浪费。
**Content:**
## 内容概览
- [ 提升生产效率 ](#index1)
- [ 运用仿真技术实现流程最优化 ](#index2)
- [ 优化资源配置 ](#index3)
- [ 达成质量目标并避免返工 ](#index4)
- [ 实现全方位可持续化发展 ](#index5)
从电动汽车到可再生能源系统，半导体是实现其碳中和目标所需技术的关键组件，这些技术的蓬勃发展不仅推动了芯片设计的进步，也对半导体制造商提出了更高的产能要求。然而具有讽刺意味的是，对更高复杂度芯片的需求增长，反而增加了半导体生产的能耗。面对全球可持续发展目标，这一挑战看似令人望而生畏，但半导体制造商仍可采取有效措施，在提升产品质量与良率的同时实现更高效的生产。
根据[《福布斯》](https://www.forbes.com/councils/forbesbusinessdevelopmentcouncil/2023/09/08/the-future-of-renewable-energy-is-built-on-semiconductors/)杂志刊载的一篇文章指出：“预计到 2027 年，全球可再生能源市场应用的功率半导体数量将以 8% 至 10% 的复合年增长率持续增长。”为可持续地满足这些需求，半导体行业可采用集成多种工厂系统的自动化制造解决方案——通过提升生产效率与产品质量，降低能耗与浪费，同时避免代价高昂的返工。
### 提升生产效率
制造商需要提升生产效率以实现晶圆厂更高运营效能，而自动化软件可通过多种方式助其达成目标。该软件可部署于多种生产流程，例如批次追踪、排程与分配，并能对数据进行集成与处理。自动化软件能管理供应链用以识别并减少瓶颈、缩短规划时间、提升计划人员工作效率，同时改善按时交付率与产能利用率。此外，它还能促进工厂内不同岗位间的沟通协作，加速决策流程。
此外，半导体制造商通过部署具备先进智能算法的人工智能 (AI) 与机器学习 (ML) 技术,能够有效解决质量、生产效率及供应链方面的难题，从而实现更高效的生产。
### 运用仿真技术实现流程最优化
制造仿真软件可在生产环境实际部署前，预测特定工艺变更将产生的影响。这有助于在实施前识别潜在问题来处理，同时辅助制造商找到最优解决方案。例如，[SmartFactory Simulation AutoSched™](/zh-hans/semiconductor-blog/use-cases-zh-hans/avalign-technologies-case-study/) 是一个产能规划系统，其可对复杂工作流程进行仿真模拟来识别被隐藏或浪费的工厂产能。该系统支持用户构建晶圆厂虚拟模型，用以分析、预测和优化生产运营，支持在离线状态下对排程规则、设备配置及操作员周期进行模拟实验。
### 优化资源配置
当制造商能够充分发挥设备效能时，可持续发展目标的达成将事半功倍。若设备利用率未达最优，不仅会造成能源浪费，企业还需承担高昂的维修与备件更换成本。此外，故障设备更可能引起产品缺陷与生产返工等问题。
制造[排程系统能](/zh-hans/scheduling-faqs/)帮助半导体制造商充分利用设备和人力资源。优质的工厂排程解决方案可提升设备效率、提高产品质量与订单按时交付率。
此外，[自动化维护管理](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/using-plug-play-spares-and-erp-modules/)有助于更高效地管理晶圆厂的高价值资产，同时降低维修成本、备件成本以及因等待设备维修而造成的停机成本。
预测性维护能确保工艺流程、设备及检测系统始终保持在最佳效能状态运行，从而降低高能耗故障的发生风险。
### 达成质量目标并避免返工
材料浪费会对制造商的碳足迹产生负面影响，既体现在制造替代品所需的能源消耗，也体现在废弃物在填埋场占据的空间上。值得庆幸的是，目前已有诸多自动化解决方案能有效提升产品质量并减少浪费。
例如，[统计过程控制 (SPC)](/zh-hans/webinars/semiconductor-zh-hans/smartfactory-spc-mastering-quality/) 工具可帮助制造商从基于检测的质量控制方法，转向基于预防的方法。通过早期识别问题，制造商能在产品受到影响前及时采取纠正措施，避免工艺或质量问题的发生。这些工具还能提供宝贵数据，助力企业制定整体工艺优化策略。
配方管理系统将工艺配方存储于安全的中央存储库，可减少差错、提升效率、增加晶圆产出，并提供完整的可追溯性。
### 实现全方位可持续化发展
最终来看，半导体对减少全球碳足迹至关重要，对其在这些领域的需求预计将持续增长。随着该技术被广泛应用于解决全球性难题的创新方案，制造商拥有众多先进的自动化方案可选，能够以更可持续的方式生产半导体。
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [製造自動化ソフトウェアは、効率化とサステナビリティ目標を実現](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/achieve-efficiency-and-sustainability-goals/)
**Published:** September 12, 2024
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** 製造プロセスを最適化し、無駄を削減するために工場の自動化を高度化する
**Content:**
## 内容
- [ 生産性の向上 ](#index1)
- [ シミュレーション活用によるプロセス最適化 ](#index2)
- [ リソース活用の最適化 ](#index3)
- [ 品質目標の達成と再生産の回避 ](#index4)
- [ 完全な循環型サステナビリティを目指す ](#index5)
半導体は、電気自動車から再生可能エネルギーシステムまで、カーボンニュートラルを実現するために欠かせない技術の重要な要素です。これらの技術の進展によりチップ設計が高度化し、半導体メーカーには大量生産が求められるようになっています。皮肉なことに、より複雑なチップへの需要の高まりは、半導体製造に必要なエネルギーを増加させています。世界的な持続可能性目標を前にすると困難な課題のように思えるかもしれませんが、半導体メーカーは、品質と歩留まりを向上させながら、生産効率を高めるための対策を講じることができます。
Forbes誌の記事によると、「世界の再生可能エネルギー市場で使用されるパワー半導体の総数は、現在から2027年までの間に年平均8〜10％の成長が予想されている」とのことです。半導体業界は、複数の工場システムを統合した自動化製造ソリューションを導入することで、効率と品質を高めながらこれらの需要に持続的に対応し、エネルギー消費や廃棄物、そしてコストのかかる再生産を削減することができます。
### 生産性の向上
製造業者は、工場の効率を高めるために生産性を向上させる必要があり、自動化ソフトウェアはその実現を多方面から支援します。このソフトウェアは、ロット追跡やスケジューリング、物流・配送機能など複数の生産プロセスに対応し、データを統合して処理することができます。また、サプライチェーンの管理を支援し、ボトルネックの特定と解消、計画時間の短縮、プランナーの生産性向上、納期遵守や生産能力の改善にも貢献します。さらに、工場内の関係者同士のコミュニケーションを円滑化し、意思決定のスピードを高めます。
さらに、半導体メーカーは、高度で知的なアルゴリズムを備えたAIやML技術を導入し、品質・生産性・サプライチェーンの課題を解決することで、より効率的な生産を実現しています。
### シミュレーション活用によるプロセス最適化
製造シミュレーションソフトウェアを活用すれば、生産環境に変更を加える前に、その変更が製造プロセスに与える影響を予測できます。これにより、実装前に潜在的な問題を把握して対策を講じられるだけでなく、最も効果的な解決策を見つけることも可能になります。例えば、SmartFactory Simulation AutoSched®は、複雑なワークフローをシミュレーションして、隠れた無駄な工場生産能力を特定できるキャパシティプランニング(生産能力計画)システムです。ユーザーはこのシステムを使用して工場の仮想モデルを作成し、運用を分析・予測・最適化できるため、スケジューリングルールや設備、オペレーターサイクルをオフラインで試すことが可能になります。
### リソース活用の最適化
製造業者が装置を最大限に活用すれば、持続可能性の目標達成は容易になります。一方、装置の利用が最適化されていないと、エネルギーが無駄になり、高額な修理代や部品交換が必要になることがあります。また、装置の故障は不良製品の発生や生産のやり直しにつながる可能性もあります。
製造スケジューリングシステムは、半導体メーカーが設備や人材を最大限に活用するのに役立ちます。質の高い工場スケジューリングソリューションは、設備の稼働効率を高め、製品の品質や納期の遵守率を向上させます。
さらに、メンテナンス管理を自動化することで、工場の高価な資産を効率的に管理しながら、修理費や部品費、装置修理待ちのダウンタイムを削減できます。
予測メンテナンスを導入すれば、プロセスや装置、検査システムが常に最適な状態で稼働するため、エネルギーを多く消費する故障のリスクを低減できます。
### 品質目標の達成と再生産の回避
廃棄された材料は、代替製品の製造に使用されるエネルギーと埋め立て地のスペースの両方において、製造業者の二酸化炭素排出量に悪影響を及ぼします。幸いなことに、品質向上と廃棄物削減に役立つ自動化された製造ソリューションが数多く存在します。
例えば、統計的プロセス制御（SPC）ツールを使えば、問題が起きてから対応する検出型の品質管理から、事前に防ぐ予防型の管理へ移行できます。問題を早期に把握することで、製品に影響が出る前にプロセスや品質の問題を修正・防止することが可能です。これらのツールはプロセス全体の改善戦略を策定する上で重要な情報も提供します。
レシピ管理システムは、レシピを安全な中央リポジトリに保存し、エラーを削減し、効率を向上させ、ウエハーの生産量を増やすとともに、トレーサビリティも可能にします。
### 完全な循環型サステナビリティを目指す
半導体は地球規模での二酸化炭素削減に欠かせない存在であり、こうした用途における半導体の需要は今後さらに増えると予想されます。この技術が世界の課題に対する革新的な解決策をもたらすために活用されるにつれ、メーカーは半導体をより持続可能な方法で生産するための高度な自動化オプションを数多く利用できるようになります。
## About Cindy McVey
Cindy McVey, Contributor to the SmartFactory Blog for Semiconductor and Pharmaceutical Manufacturers
Cindy is an essential writer for our SmartFactory Blog, focusing on feature stories that highlight automation experts and their contributions to helping semiconductor and pharmaceutical manufacturers stay ahead. Her engaging content explores how these experts navigate market dynamics, technology, and people to deploy innovative factory automation solutions. Cindy's insightful writing showcases the valuable insights and expertise these professionals bring to the semiconductor and pharmaceutical manufacturing industry.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [半导体封装测试的全自动化之路——克服障碍（第3篇，共3篇）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-3/)
**Published:** March 15, 2022
**Author:** Joe Napiah
**Excerpt:** 公司准备工作、数据设备、工厂布局、物料搬运……这些障碍听起来熟悉吗？观看这个视频（第3篇，共3篇），从专家那里获得有关如何实现全自动的建议。
**Content:**
[ 第2篇：SmartFactory 路线图 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/assembly-test-part-2/)
通过本系列视频（第3篇，共3篇），了解通往半导体封装测试的全自动化之路上应对障碍的策略。
## 文稿
欢迎观看我们在半导体封装/测试领域实现全自动的主题网络研讨会的第三个视频。在本期视频中，我们将讨论实现“全自动”过程中遇到的障碍以及应对之策。所以，实现全自动的障碍有哪些？首先，如果组织本身缺乏对“全自动“的愿景和管理层的支持，那么组织本身可能是一个障碍。
其次，数据可能是也给障碍，这既可能是数据不足又或是数据过多。
第三，旧设备可能是一个障碍。
正如我们在第一个视频中提到的。接下来，工厂布局可能是一个障碍，它要么过于复杂又或是不适合全自动化。最后，是来自物料搬运的挑战。
现在让我们更深入地讨论这些障碍。您的公司需要对实现全自动制造的需求和期望以及如何实施具有一定的远见。哪些流程可以通过自动执行来处理？又有哪些流程确实需要人工操作？您的设备现在可能是在加工什么样的批次？您将如何管理设备配方？您是否定义了设备的控制规格以及 KPI 超出这些规格时应采取的纠正措施？考虑如何在全自动化的环境中改善您的供应系统。
如果您使用或实施了数字孪生系统，需要考虑如何变更或改善其使用。考虑全自动制造和正确的数据如何实现自我学些。这些只是您的组织在规划全自动化愿景中需考虑的几个示例。
但没有获得管理层的支持，这个愿景可能永远不会实现。很重要的一点是，贵司的管理层对全自动愿景的支持并给予了预算。数据方面的障碍是什么呢？数据赋能智能制造——正确的数据。
您需要哪些数据来实现设备和制程的自动化？什么是衡量 KPI 的正确数据？是否需要对旧设备进行改造以实现集成？也许通过添加传感器和像 Raspberry Pi 这样的小型计算机？集成企业级的应用程序需要哪些数据？您的网络基础设施能否处理所有这些数据？如果不能，需要升级什么？考虑低成本存储（如本地或外部云）和高性能（如适当的固态 SAN）之间的权衡。再次强调一下，确定哪些数据对于自动化和监控制造过程是至关重要，以及如何捕获这些数据、如何存储这些数据（平衡成本和性能 ）等等。我们在之前的视频中提到，对封装/测试工厂而言，旧设备带来了一定的挑战。
我们希望设备集成不仅可以实现有价值数据的捕获，还可以自动化许多生产作业活动，例如配方选择、批次进出设备以及加工作业。在理想情况下，所有工厂设备都将与 SECS/GEM 标准协议兼容。但我们并不是生活在理想世界中的。您拥有的部分关键设备可能必须通过 OPC/UA、TCP/IP 或 Web 服务等协议进行集成。SmartFactory Equipment Automation（或简称“EA”）解决方案可以解决此类问题。
EA 拥有各种适配器，使我们能够集成这种旧设备，帮助您的工厂实现更高水平的自动化。工厂布局。模拟工厂布局可以带来很多好处，尤其是在建造新工厂时。
使用 SmartFactory Simulation 仿真软件，你的组织可以在工厂破土动工之前，就做好计划以便最大程度地提升工厂的生产效率。优化新工厂布局，探索假设场景，了解和可视化各组件之间的依赖关系，确定可变性和不可预见事件的影响，确定系统要求并识别约束，测量两次并切割一次。如有疑问，再次模拟。
我们在之前的视频中曾提到，非标准化是封装/测试工厂实现自动化的一大障碍。半导体行业协会有一个工作组来解决这个问题。SEMI ABFI 是半导体先进后道工厂集成工作组。
该小组的任务是为封装/测试工厂制定新标准，以帮助开辟通往全自动化的道路。搜索“半导体智能制造标准”和“SEMI ABFI”了解更多信息。物料处理可以说是实现封装/测试完全自动化的最后一个也是最大的障碍。
在300毫米晶圆厂中，我们受益于用于处理晶圆的标准 FOUP 和 FOSB。在左上角，我们看到一些在晶圆厂和凸块厂中使用的载具。在半导体后道，标准化则要少得多。
从中期和长期来看，SEMI ABFI 工作组应该建立标准以解决此类问题。在短期内，您的工厂应尽可能确定在所有的站点使用的标准弹夹、托盘和托板。标准化越多，自动化障碍就越低。
现在如何将这些标准托盘从 A 点移动到 B 点？这就是自动化运输和自动化物料搬运系统（AMHS）发挥作用的地方。
它们可能是以这些形式出现：自动导引车（AGV）、轨道导引车（RGV）和天车系统（OHT）。这些选项中的每一个都有自己的优点和缺点。
OHT 通常最快且不占用地面空间——前提是您的工厂有足够的高度来容纳它们。AGV 和 RGV 可能是一个不错的选择，但会占用宝贵的地面空间。潜在的投资汇报可能会迫使您的组织实施自动化运输。
考虑工厂产量和良率的潜在提升，以及劳动力成本和人为错误的减少。最后，要管理所有这些自动化运输系统和材料类型，如托盘和弹夹，请使用应用材料公司 SmartFactory Material Control 套件，也称为 CLASS MCS 5。该解决方案能将多个 AMHS 提供商集成到一个解决方案中。一旦实施，就不需要工厂停机来实施改造。
我们现在来到了关于半导体封装/测试全自动化三部曲的尾声了。在第一个视频中，我们讨论了当前生产制造面临的挑战，在第二个视频中，我们诠释了“全自动”的定义及其在应对这些挑战中的作用。
在最后这个视频中，我们讨论了“全自动”遇到的障碍以及如何解决它们。让我们总结一下。需要全自动才能在封装/测试领域保持竞争力。领先的封装/测试公司已经意识到了这一点，并朝着全自动化方向迈出了一大步。明智的资本投资可以减少全自动的障碍和差距。正式的行业标准和合作可以降低成本并加速通往全自动化的道路。最后——是时候迈出步伐了。联系我们，详细了解应用材料公司 SmartFactory 解决方案如何助力您解决高价值问题。感谢观看！
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** The Road to Full Auto in Semiconductor Assembly Test Manufacturing, Bingeworthy, Semi
---
### [半导体封装测试的全自动化之路——新兴挑战（第1篇，共3篇）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
**Published:** March 17, 2022
**Author:** Joe Napiah
**Excerpt:** 了解专家在应对半导体后道制造的新兴挑战和复杂性时最关注的内容。
**Content:**
[ 第2篇：SmartFactory 路线图 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/assembly-test-part-1/)
了解专家在应对半导体后道制造的新兴挑战和复杂性时最关注的内容。本视频系列（第1篇，共3篇）涵盖的关键领域包括供应链、技术和产品、材料、设备和人力资源。
## 文稿
欢迎观看我们关于半导体封装/测试领域全自动的主题网络研讨会的第一个视频。在本期视频中，我们将探讨当今封装/测试/包装行业面临的挑战。那么，在封装/测试行业中，生产制造面临的挑战是什么？这些挑战对哪些 KPI 会产生影响？首先是供应链的复杂性，它会影响生产周期、按时交付，当然还有 “成本” 。
其次是技术和产品的复杂性，它主要影响生产周期，以及技术开发的速度或“学习周期”。技术和产品的复杂性与我们的下一个挑战密切相关：物料的复杂性及其可追溯性。在封装测试领域中，我们看到了从简单的单芯片引线框架包装转向单个包装（甚至多个包装）中包含多个芯片的变化，与此同时，2.5D 或 3D 封装技术也在不断进步。
这些复杂性会对 OEE、可追溯性分析的易用性和可追溯性粒度产生影响。下一个挑战，设备和工艺的复杂性对 OEE 和良率产生的影响。最后一个挑战是人力资源的复杂性，这些在一定程度上可通过生产效率、报废率和按时交付来衡量。
让我们来更深入地了解一下供应链的复杂性。在后道，我们可以看到从硅片到最终产品的整个半导体供应链，从原始硅片到晶圆厂中使用的硅片，再到封装/测试，最终到客户手中的成品。供应链面临的主要挑战有哪些？首先是多样性。
供应链的垂直整合方式因公司类型而异，譬如外包供应链中各个环节的无晶圆厂的设计公司与趋向于越来越多内部制造的集成制造商之间的管理模式会有很大的差异。下一个挑战是动态订单模式。我相信你们都已经很了解因新冠疫情带来的库存挑战，零部件已经缺货数月，一些代工厂未来几年的产能已被预订了等等。
多种封装技术和新兴技术（2.5D，3D，晶圆级封装）导致零部件所需数量的激增，进而引发对库存更进一步的依赖。与这种供应链复杂性相关的生产制造面临的主要挑战是什么？技术周期短，总有一些小零部件的新版本需要购买。
投资回报率要求及其高额的资本投入。紧迫的交货时间和按时交付的压力。良率和报废的成本。
芯片进行到封装/测试的阶段时，已经花费了大量的时间和金钱。通常，供应链越到下游，可能造成的损失就会越大。当然，还包括所有这些工厂之间的集成和互操作性。
这会对优化供应链规划、故障模式分析等产生影响。现在让我们聊聊物料的复杂性及其可追溯性。正如我们之前提到的，存在从单芯片封装到多芯片 3D 封装的转变。
这种转变使得单个组件变得更为复杂，因为这些新的封装技术需要越来越多的不同零部件。那么这些复杂性如何影响生产效率和质量？再强调一下，更多的物料意味着更多的依赖性。因此，由于库存不足，我们可能会遭遇到更多的“停产”情况。
如果原材料质量很差，我们也会遇到越来越多的潜在故障点。最后也是最重要的是良率。我们需要持续获得一份不断增长的优质原材料供应清单，以便能获得高良率。
接着让我们讨论一下产品和技术的复杂性。在这里，我们看到了几个关键的技术趋势——物联网和自动驾驶汽车。
这些趋势中的每一个技术都导致对各种电子产品的需求激增，包括但肯定不限于各种传感器、处理器和显示器。随着物联网的发展，我们看到越来越多的设备连接到 Wi-Fi，从闹钟到浴室秤再到冰箱。可以想象，尽管汽车行业的电子产品质量标准已经很高了，但随着自动驾驶汽车的出现，我们应预计到这些标准将变得更加严格。
下一个挑战——设备和工艺的复杂性。首先，考虑到我们新兴的封装技术，这当然会带来越来越多的产品组合和越来越复杂的制造工艺。
这些新的封装技术包含了更复杂的工艺，我们将看到使用的工艺设备也会越来越多。在很多封装测试的工厂中，可能拥有一些陈旧的设备，它们不符合 SEMI 标准，如 SECS-GEM 和接口 A，这给我们从该设备中获取数据带来了挑战。考虑到不断增加的数据量和种类，这一切都导致了大数据的挑战。
这不仅仅是关于数据的获取，还包括有效地利用这些数据。下一个挑战，让我们讨论一下人力资源的复杂性。考虑到大多数封装/测试工厂都高度依赖手动生产。
如果不能借助全自动的系统，人们往往就会直接做出影响（并可能损害）生产效率和质量的重要决策。接下来应该在哪些设备上处理哪些批次？手头有足够的原料吗？设备是否可用或逾期维护？是否有任何基于制程阈值时间或设备认证的限制需要考虑？在我们的下一个视频中，我们将展示应用材料公司 SmartFactory 解决方案如何应对这些挑战解决问题。现在我们已经深入了解了生产制造面临的挑战，接下来让我们看看从行业中了解到的信息。
首先，第一要务是保证质量，当然还要解决良率问题。第二，按时交付。客户希望看到快速交货和承诺日期。
所以这里的重点是中长期规划、短期调度和实时派工。第三，过渡到先进封装。在这里，我们指的是晶圆级封装和面板级封装等类似的工艺。
第四，数据基础设施。这部分是为了提供对客户的直接访问，也是为了提供先进的数据分析。如果设备符合标准协议，那么就可以直接收集数据，但对于旧的传统设备，那么数据的可用性肯定会变得更加困难。
生产效率，包含人力和设备。这部分是指自动化物料处理（可能使用 AGV 和/或天车）以及最大限度地减少错误，我们将在下一个视频中更深入地介绍这两个方面的情况。最后，加速问题解决。
学习周期必须很快，因此解决问题也需要非常快。客户将继续施加成本压力并要求更多的可追溯性。这六点是我们从封装测试的客户那里听到的关键内容。
观看我们的下一个视频，我们将诠释“全自动“的定义以及它如何应对这些挑战。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** The Road to Full Auto in Semiconductor Assembly Test Manufacturing, Bingeworthy, Semi
---
### [Predict, don’t react](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/predictive-monitoring-for-semiconductor-manufacturing-uptime/)
**Published:** March 10, 2026
**Author:** Yoram Barak, Global Product Manager
**Excerpt:** Why predictive monitoring is essential for maximizing uptime in semiconductor manufacturing
**Content:**
## What’s Inside
- [ Cost of downtime related to IT systems ](#index1)
- [ From monitoring to observability ](#index2)
- [ AI/LLM in observability: assistive RCA ](#index3)
- [ How does SmartFactory Monitor tackle manufacturing systems monitoring issues? ](#index4)
- [ Conclusion ](#index5)
### Cost of downtime related to IT systems
Semiconductor manufacturing is complex; it requires the delicate orchestration of automation systems in support of significant hardware, operating systems, memory and applications. The capital cost of building and operating a fab and margin pressure in the industry are very high and, as such, any unplanned downtime is very costly. A single unplanned stop can ripple through wafer starts, WIP, and yield curves, burning cash and deoptimizing schedules. Manufacturers express common problems and needs, including:
- Manufacturing software systems are great until something stops working.
- Unplanned downtime has a significant business impact.
- System downtime affects production.
- There is a need for forecasting systems to anticipate and alert to problems.
- A system that can rapidly address problems as they occur is highly desired.
There are several studies indicating the impact of unplanned downtime based on fab volume (Figure 1).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2026/03/figure-1-the-cost-of-downtime-based-on-fab-volume-1.webp) Figure 1: The cost of downtime based on fab volume.
The following real-world use case demonstrates the type of financial impact possible: - **The situation** – A bumping site using automation apps connected to 270 tools crashed and operation stopped for six hours.
- **The outcome** – The economic cost of downtime for bumping tools based on industry standards is ~$500/hour. Just six hours of downtime resulted in a loss of $810,000.
- **The solution** – This crash and resulting economic loss could have been prevented if the site had implemented a reliable and cost-effective alert system to warn of impending issues.
### From monitoring to observability
Modern tools extend beyond metrics, logs, and traces. OpenTelemetry has added continuous profiling and is stabilizing semantic conventions so teams can correlate signals consistently across diverse stacks. AI/ML can be very valuable in the future. Rather than replacing existing capabilities, it will help accelerate Root Cause Analysis (RCA) and provide intelligent alerting amid cost pressures and the need to prove ROI.
For OpenTelemetry success, it is critical that apps follow core OpenTelemetry standards. This includes:
**1. Signals Supported**
- **Metrics:** Quantitative measurements (e.g., CPU usage, latency, and throughput).
- **Logs:** Event records with context.
- **Traces:** Distributed transaction spans for request flows.
- **Profiles:** Continuous profiling for CPU/memory usage.
**2. Semantic Conventions**
- Standardized naming and attributes for telemetry data (e.g., http.method, db.system).
- Ensure consistency across vendors and tools.
**3. OTLP (OpenTelemetry Protocol)**
- A vendor-neutral protocol for exporting telemetry data.
- Supports gRPC and HTTP for efficient transport.
In fabs, IT focuses on security, standardization, and scale. Convergence with OT brings rich process data to enterprise systems and modern tools down to the floor, improving visibility and responsiveness to avoid unplanned downtime. However, cultural and tooling gaps persist in siloed data, legacy protocols, and finger-pointing during incidents. Teams need a universal translator—shared telemetry and standardized events—to unify workflows.
Modern observability should deal with modern streams of data within various logs, traces, and process metrics. The ability to ingest these from an integrated automation stack with pre-defined rule-based knowledge is of immense value.
### AI/LLM in observability: assistive RCA
GenAI is filling gaps by enabling natural language queries (“What changed before the spike?”), accelerating RCA, and helping teams manage cost/complexity—but it remains an assistant, not a replacement for engineers. If your automation stack application errors are well known and defined, an opportunity to accelerate RCA significantly is at reach. Standardizing log format, ingestion, and shipping from unstructured to structured data will accelerate it further.
### How does SmartFactory Monitor tackle manufacturing systems monitoring issues?
SmartFactory Monitor is real-time monitoring software that helps detect issues and act before they affect production systems. It offers a customizable dashboard for viewing system status, quick notifications for problems, and options to display performance trends. With built-in predictive analytics, it can identify anomalies early. The software runs efficiently on modest hardware, supports various operating systems, and integrates with other SmartFactory products. Furthermore, an adapter exists to connect with third party applications, allowing any enterprise level monitoring system or connecting other apps of choice directly to SmartFactory Monitor.
In the not-too-distant future, SmartFactory Monitor will be able to integrate OpenTelemetry data from various SmartFactory apps and provide a unified monitoring approach for both legacy and containerized environments. This will ensure customers experience a seamless transition without losing access to familiar data. Aggregating telemetry from multiple sources (e.g., OpenTelemetry, Prometheus, Zabbix) minimizes the need for customers to adopt new tools or interfaces, which in turn improves usability and accelerates adoption.
### Conclusion
Fabs are becoming observable systems: every state transition, network timing window, and microservice span contributes to the overall indication of reliability of IT systems. Unifying IT and OT telemetry aided by assistive AI will likely improve uptime even further, making the process intentional—not incidental. SmartFactory Monitor is well positioned to address these challenges with run-time monitoring for real time alerting, so IT personnel can take appropriate corrective actions. It is also enabling better planning of the IT systems needed to support high-volume and high-fidelity manufacturing in the semiconductor industry.
If you’re ready to rethink how your fab handles monitoring and observability, [reach out](https://appliedsmartfactory.com/connect/?page_source=https://appliedsmartfactory.com/semiconductor/manufacturing-execution-solutions/alarmmanagement/).
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular, Semi
---
### [半导体封装测试的全自动化之路——SmartFactory 路线图（第2篇，共3篇）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
**Published:** March 16, 2022
**Author:** Joe Napiah
**Excerpt:** 实现半导体后道制造全自动的路线图。
**Content:**
[ 第1篇：新兴挑战 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/assembly-test-part-1/)
[ 第3篇：克服障碍 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/assembly-test-part-3/)
在迈向全自动化的征程中，您的工厂处于哪个阶段？在本系列视频中（第2篇，共3篇），您将了解全自动在半导体后道封装测试中的作用，并探索其路线图，及如何使用 SmartFactory 解决方案实现全自动。
## 文稿
欢迎观看我们在半导体封装/测试领域实现全自动的主题网络研讨会的第二个视频。在本期视频中，我们将诠释“全自动”的定义并展示其在应对生产制造挑战方面的作用。首先，简要回顾一下工业发展的历史。
当我们回顾工业1.0时，共同的主题一直是使用现代技术来提高生产效率。到了工业4.0，这一趋势仍在继续，随着工业物联网、高级分析和机器学习的发展，生产效率不断提高。当然，不同的人对于工业4.0和智能制造的理解可能不尽相同。
它可能意味着：自组织制造、自动化物料搬运、工业计算、计划/调度和派工、质量管理和端到端的供应链管理。智能制造包含了上述的所有功能，可分为自动化决策、自动化执行和自动化物料处理三大部分。但是，当我们说“全自动”时，又指的是什么呢？我们将“全自动”定义为：无需人工干预即可搬送、加工和交付物料的能力。
实现全自动需要使用和集成 CIM 软件和硬件系统；CIM软件系统也就是俗称的计算机集成制造系统。我们在全自动生产制造方面有三个主要目标：自动化决策、自动化执行和自动化物料处理。
让我们更深入地研究每一个目标。第一，自动化决策。在这里，我们看到了应用材料公司 SmartFactory CIM 解决方案以及它们是如何融入到制造的生态系统中的。
每一块拼图都是用于实现或提供自动化决策的。例如，在工厂生产效率领域，Scheduling 和 Dispatching 套件使用来自 MES 系统和其他来源的数据以确定最佳的排程方案，在恰当的时间使用最合适的设备来加工批次。Maintenance Management 解决方案可以用于确定设备维修时间何时到期或是否已逾期，并自动采取适当的措施，例如通知设备工程师同时将设备转成计划停机状态。
在工艺质量方面，当收集的数据超出配置的控制范围时，SPC 套件将自动出发适当的纠正措施。Run-to-Run 解决方案将会自动优化设备的配方参数，以提高 CPK 并减少报废率。下一步，自动化执行。
这可以通过应用材料公司 SmartFactory FullAuto 解决方案来实现。SmartFactory FullAuto 是一种自动化执行系统，通过执行基于事件的先进的工厂自动化工作流，来提高工厂的生产效率并消除设备的空窗期。这些工作流根据工厂的作业规范来进行客制化，可同时考虑多个标准，并处理许多异常情况。
SmartFactory FullAuto 缩短了生产周期、降低了可变性并减少了所需的专业操作员数量，不仅提高了工厂生产效率，也使得工厂获利增多。最后，让我们聊聊自动化物料搬运。
诚然，对于300毫米晶圆厂来说，这个目标更为直接，这里只有一种类型的物料：晶圆——以及装载晶圆的标准化载具 FOSB 和 FOUP，还有在设备和存储位置之间移动这些标准化载具的天车系统。在封装测试工厂，我们遇到的情况将会更为复杂，这是因为在从来料（晶圆）到成品（一卷封装 IC 或最终封装模块）的生产过程中，在制品的形状及其物料载体会发生多次改变。图的左上角是在半导体晶圆厂中使用的物理载具，在图的右边，我们可以看到在封装/测试工厂中使用的许多物料。
各种非标准化的载具给自动化物料处理带来了很大的挑战——但这是一个值得解决的问题，特别是那些产能巨大的工厂，考虑潜在投资回报因素：增加产量、降低成本、提高良率等。在下一个视频中，我们将更多地讨论如何应对这一挑战。让我们分阶段来逐步实现全自动。
在接下来的几张幻灯片中，您将看到从全手动流程（蓝色）到半自动流程（黄色），再到全自动化流程（绿色）的升级过程。
起初，您可能只是在手动模式下运行 MES 系统，即便如此，无纸化也能让您感受到 MES 系统的好处。
接下来，您的公司要对全自动的愿景和计划达成一致。
第三，接下来部署 Maintenance Management、Durables Management 和 Recipe Management 等解决方案。这些解决方案当然是很有价值的，它们为未来的自动化奠定了基础。
在第4步，实施 SmartFactory Equipment Automation。导入这个系统后，我们可以在设备上自动收集数据和进行一些基本功能的操作，如配方选择、入机台和出机台。
接下来，我们关注载具的可追溯性，例如 SmartFactory Material Control 以及为载具和设备添加载具存储和 RFID 标签——这当然会提升自动化的能力。
在第6步，部署 SmartFactory Dispatching。它使用来自 MES 系统和其他系统的数据来决定批次下一步去哪里以及设备加工哪个批次，从而最大限度地提高生产效率。迈向全自动的最后一步。
在第7步，我们部署 Advanced Process Control 解决方案，包括：SPC、Fault Detection 和 Run-to-Run 套件。我们在前面已经讨论了 SPC 和 Run-to-Run 的价值，除此之外，Fault Detection 套件能够在设备生产过程影响产品质量之前就对设备问题进行快速响应。
接下来在第8步，部署 SmartFactory FullAuto，几分钟前我们在自动化执行的目标中已经对它做了简要的介绍。
在第9步中，管理层将能看到全自动的投资回报潜力，可以通过使用 SmartFactory Simulation 来做部分地展现。
接下来的第10步和第11步，我们关注设备基础设施的变化，为实施自动化物料搬运系统（如天车系统和自动导引运输车）铺平道路。当然，在封装/测试工厂中，非标准化的物料处理将会给全自动带来一些障碍。
我们将在下一个视频中进一步讨论这个问题。在第11步，我们实现了 “全自动” 制造和三个主要目标：自动化决策、自动化执行和自动化物料处理。当然，总是有改进的余地，因此我们总是提倡持续改进。
请观看下一个视频，我们将讨论实现“全自动“过程中遇到的障碍以及应对之策。感谢观看。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** The Road to Full Auto in Semiconductor Assembly Test Manufacturing, Bingeworthy, Semi
---
### [FactoryViewとAIによるレポート変革の可能性（パート2/2）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
**Published:** June 25, 2025
**Author:** Samantha Duchscherer and Michael Frenna
**Excerpt:** AIでユーザー体験と工場の成果を向上
**Content:**
[ パート1：FactoryViewとAI ](/ja/semiconductor-blog/ai-ml-ja/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
## 目次
- [ FactoryViewエクスペリエンスの現状 ](#index1)
- [ リアルタイムのインサイトと推奨事項 ](#index2)
- [ 合成データを活用した精度向上 ](#index3)
- [ ばらつきの低減 ](#index4)
- [ 段階的な導入アプローチ ](#index5)
- [ まとめ ](#index6)
FactoryViewの紹介に続く本記事では、AIによってこのツールがリアルタイムモニターからインテリジェントアシスタントへと進化する可能性を、SamとMichaelが探ります。AIがどのように予測精度を高め、実行可能な提案を行うか（特に複雑で変化の激しい製造環境において重要なポイント）、そしてより自律的な運用へ移行する中でチームがどのように信頼を築いていけるかを議論します。
Sam: FactoryViewについて理解が深まったところで、AIについても話しましょう。現在、FactoryViewはどのように使用されているのか、そしてAIがインテリジェントな提案を提供できるようになった場合、ユーザーの体験や結果はどのように変化するのでしょうか？
Michael: 現在、ユーザーは工場のKPIを監視し、分析しています。アプリケーションで表示されている情報をもとに、どの領域に重点を置くか、またその都度リソースをどこに投入するかを決定します。意思決定は現在、手作業で行われています。私たちは単に意思決定支援システムを提供しているだけに過ぎません。
AIが大きな価値を付加するのは、意思決定そのものの質においてです。人間が意思決定を行う場合、工場の全体的なダイナミクスを理解していないため、より大きなばらつきが生じることがよくあります。特定の領域の特定の問題に非常に強く集中しているかもしれませんが、局所的な最適化が工場全体のパフォーマンスにどのような影響を及ぼすかは理解できていないのです。代わりに、AIを活用して工場全体を俯瞰し、最適な行動を判断できれば理想的です。これにより、工場全体の効率を低下させかねない局所的な最適化を避けることができます。
Sam: つまり、AIがリアルタイムのインサイトと推奨事項でユーザーを積極的に先導することが望ましいということですね？
Michael: はい、最初は「このエリアのツール1がダウンしています。これを復旧させれば工場のスループットがX％向上します」といった提案から始まるかもしれません。また、その決定には根拠も示されるでしょう。例えば「今後数時間に受け取る予定のWIP量と、過去1週間のこの設備の稼働状況に基づき、このマシンを復旧すれば工場のスループットはX向上すると予想されます」といった形です。
Sam: なるほど。予測を説明するだけでなく、実行可能な推奨事項を提供することも重要なのですね。少し話題を変えて、特に利用できる過去データが限られている場合や全くない場合に、AIがどのように予測の精度を高められるか、ご説明いただけますか？
Michael: 現在、FactoryViewは統計的手法を用いて、過去のデータに基づき予測を行っています。これは、十分なデータ基盤がある場合にはうまく機能しますが、工場に新しく導入されたデバイスのように、データが限られていたり、信頼性が低かったりする場合には課題となります。このような場合、正確な予測を行うための十分な稼働履歴がないため、従来の方法では対応できません。
そこでAIが真価を発揮できます。類似製品を分析して合成データを生成し、ギャップを補うことで、予測精度を向上させることができます。例えばFactoryViewには、投入から出荷までの各ロットの工場内での動きを追跡するチャートがあります。完了したステップは実際のデータで表示できますが、将来のステップについては現状、過去の平均値に基づく基本的な予測に頼っています。この方法は、履歴がほとんどまたは全くない新しいデバイスでは機能しません。ここでAIが介入することで、予想されるWIP、機器の性能、類似製品のパターンなどを考慮し、よりスマートに、状況に応じた予測を行うことが可能になります。これにより、特に変化の激しい生産環境において、システムの信頼性が大幅に向上します。
Sam: なるほど。少し懐疑的な立場をとってみます。AIは必要なく、レポート作成のためのより優れたツールだけで十分だと考えている人には、どのように説明しますか？AIが根本的に異なる価値を提供するということを、どう示すべきでしょうか？
Michael: 半導体工場にはあまりにも多くの変数があり、人間が自分の下す判断が最善かどうかを検討することは困難です。半導体工場で、人が自分では最適だと思って判断を下すとき、多くの変数を見落としてしまうことがよくあります。実際に関係している変数のうち一部しか見ていないということです。たとえ必要な変数をすべて示すレポートがあったとしても、人間がその判断を下すには、たとえ可能だとしても非常に時間がかかるでしょう。
Sam: これは非常に素晴らしい洞察ですね！もっと続けたいところですが、信頼の問題で締めくくりましょう。ユーザーがすでに手動での判断を信頼しにくい場合、AIによる推奨事項を信頼してもらうにはどうすればよいのでしょうか？
Michael: まずは段階的なアプローチが良いと思います。最初は提案を行い、その提案の根拠を説明することから始めるのです。製造運用チームによる一定レベルの精査とトレーニングが必要になるでしょう。AIがまだ認識していない点があり、それを学習するにはチームからのフィードバックが必要だからです。製造チームがこれらのより情報に基づいた提案を信頼し始めると、工場はAIに提案だけでなく、実行も任せるようになると考えています。具体的には、MESの設定変更、自動化されたファブでの特定アラートの処理、搬送システムへの指令による特定エリアへの資材移動などが挙げられます。
### まとめ
FactoryViewは、半導体企業がリソースを効果的に活用し、ファブに影響を与える課題に対応できるよう支援する、日常業務向けの意思決定支援システムです。AI技術を活用することで、FactoryViewはファブに影響を与える問題を特定するだけでなく、最適化のための提案を行い、さらには問題が発生する前に対処することも可能になります。
## 筆者について
Samantha Duchscherer （グローバルプロダクトマネージャー）
Samanthaは、SmartFactory AI™ Productivity、Simulation AutoSched®、Simulation AutoMod®を統括するグローバルプロダクトマネージャーです。Applied MaterialsのAutomation Product Groupに加わる前は、BoschでIndustry 4.0のマネージャーを務めており、同社ではデータサイエンティストとしても活躍していました。さらに、オークリッジ国立研究所の地理情報科学・技術グループでリサーチアソシエイトとしての経験もあります。彼女はテネシー大学ノックスビル校で数学の修士号（M.S.）を、ノースジョージア大学ダロネガ校で数学の学士号（B.S.）を取得しています。
Michael Frenna（ワークフロー自動化および工場分析担当グローバルプロダクトマネージャー）
現在の役割において、Michaelは世界中の半導体顧客の増大するニーズに応えるため、ワークフロー自動化および工場分析サービスのロードマップ施策を推進しています。現在の役職に就く前、Michaelは半導体業界で産業エンジニアとして専門性を磨き、150mm/200mmフロントエンドファブにおけるデジタルトランスフォーメーションおよびI4.0イニシアティブの推進に貢献しました。Michaelは、テクノロジーへの情熱とイノベーション推進への意欲を持ち、世界中の顧客と協力しながら、製造能力と業務効率の向上に取り組んでいます。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [FactoryViewとAIによるレポート変革の可能性（パート1/2）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-1/)
**Published:** June 25, 2025
**Author:** Samantha Duchscherer and Michael Frenna
**Excerpt:** 高度な意思決定支援システムで、工場オペレーションを次のレベルへ
**Content:**
[ パート2：FactoryViewとAI ](/ja/semiconductor-blog/ai-ml/how-factoryview-ai-improve-factory-operations-reporting-part-2/)
## 目次
- [ FactoryViewの定義 ](#index1)
- [ リアルタイムのモニタリング ](#index2)
- [ コーディング不要で作成できる新しいレポート ](#index3)
- [ ベスト・ノウン・メソッド（BKM）へのアクセス ](#index4)
- [ 変更管理 ](#index5)
- [ 導入および統合 ](#index6)
本ブログでは、SamがMichaelと対談し、FactoryViewがリアルタイムのモニタリング、標準化されたレポーティング、そして実行可能なインサイトを通じて、どのように工場オペレーションを変革するのかを探ります。意思決定の簡素化から、既存のAPF製品やソリューションとのシームレスな統合準備まで、この対話を通じて、FactoryViewが単なるレポーティングツールではなく、よりスマートで迅速、かつ組織全体の整合性を高める製造オペレーションを実現するための“触媒”である理由が明らかになります。
Sam: いつものようにAIの話もしたいところですが、まずはFactoryViewとは何か、そして製造業にどのようなメリットをもたらすのかを説明してもらえますか。
Michael: もちろんです。FactoryViewは、当社のSmartFactory Reporting Solutionの一部で、工場オペレーションやKPIをリアルタイムに可視化するソリューションです。製造部門が重視している重要な指標を監視し、組織全体で計画やスケジューリングの目標を整合させるために使用されます。
理想的には、日々のオペレーションにおける意思決定支援システムとして機能し、リソースが効果的に活用されているか、ファブに影響を与えている課題は何か、またボトルネックがどこにあるのかを把握できるようにすることを目的としています。
Sam: なるほど。これはあらかじめ定義されたレポートソリューションなのでしょうか。それとも、ユーザーが表示内容を定義するのですか。
Michael: 基本的な表示内容はあらかじめ定義されています。ただし、工場内のどこにボトルネックがあるかといった、事前に定めたロジックに基づいて、各シフトでどの領域を重点的に見るかはお客様自身が定義します。ボトルネックの特定方法は、工場ごとに異なります。
また、このレポーティングはユーザーの役割を意識して設計されています。全体を俯瞰するハイレベルなビューは製造マネージャーやディレクター向けで、各モジュールの画面はセクションマネージャー向けです。
Sam:「リアルタイム」とは、このアプリケーションでは具体的にどういう意味なのでしょうか。
Michael: 「リアルタイム」とは、工場のMESでトランザクションが発生すると同時に、その情報が複製され、FactoryView上に表示されるということです。それに紐づくKPIも、MES上でトランザクションが発生するたびに更新されます。
例えば、ロットが次の工程へ移動すること、装置のダウンを記録すること、装置の復旧を記録すること、これらはいずれもトランザクションです。
装置のリアルタイムな状況や、工場内の材料移動に関する指標を扱うレポートは、このリアルタイム性によって大きな影響を受けます。
Sam: 非常に有用だと感じますが、正直なところ、製造業やIE（インダストリアルエンジニア）が他のソフトウェアで作成しているカスタムレポートと、実際にはどのように違うのでしょうか。
Michael: とても良い質問ですね。重要な点は、ダッシュボードの作成や保守にIEやIT担当者、開発者を必要としないことです。FactoryViewはすでに完成された形で提供されているため、IEやIT担当者はレポートを作る作業ではなく、その情報を活用して意思決定や組織の整合に集中できます。
多くのお客様はすでに何らかの工場レポートを持っていますが、それらの作成や保守には多くの時間と労力がかかります。また、レポートが組織ごとにサイロ化し、同じKPIでも算出方法が異なるケースも少なくありません。FactoryViewには、従来は存在しなかったレポートも含まれており、工場オペレーションにおける「単一の信頼できる情報源（Single Source of Truth）」を持てる点が大きなメリットです。
Sam: 標準化とスケール、そしてこれまでになかったレポートを提供するわけですね。ではもう一歩踏み込んで、既存ツールや自作ダッシュボードでは得られない、FactoryViewならではの価値は何でしょうか。
Michael: このソリューションは、長年にわたるカスタムレポーティング導入の経験を基に構築されており、半導体業界特有の要件が数多く反映されています。実際にお客様にご紹介すると、他社のベスト・ノウン・メソッド（BKM）に由来するKPIなど、これまで意識していなかった新たな指標から洞察を得られるケースがよくあります。
このレポーティングソリューションのロードマップに参加することで、従来使ってきた指標だけに頼るのではなく、業界全体で培われたBKMを取り入れることができます。
Sam: FactoryViewの価値はよく分かりました。では実運用の観点で、導入にあたって最も難しい点は何でしょうか。成功のために事前にどのような点を考慮しておくべきでしょうか？
Michael: まず重要なのは変更管理です。製造部門は長年にわたり独自の方法で指標を見てきましたが、FactoryViewの導入によってその見方が変わる可能性があります。日々のスタンドアップミーティングにこのレポートを取り入れることで、進め方が多少変わるため、アプリケーションの使い方を学ぶ期間が必要になります。
もう一つ重要なのが、指標の検証です。MESデータを収集し、各KPIが顧客の定義と一致しているかを確認することが、導入初期の大切なステップになります。
Sam: 最後に、既存システムとの統合のしやすさも、変更管理を成功させる大きな要因だと言えるでしょうか。
Michael: その通りです。FactoryViewは、EngineeredWorksソリューション群と共通のデータモデル上に構築されています。そのため、このソリューションで生成される入力データや工場KPIの多くは、他のソリューションとも共有されます。例えば、スケジューリングで使用するスループット指標は、FactoryViewでも同じ計算ロジックが使われます。また、FactoryViewでツールが稼働中であれば、スケジューリングソリューションでも同様に稼働中として扱われ、同じツールリストが参照されます。
レポーティングソリューションを導入することで、スケジューリングソリューション導入に必要な主要データもすでに整っているため、導入期間の短縮にもつながります。
### 次回予告
次回の記事では、AI技術がFactoryViewにもたらすさらなる付加価値について、SamとMichaelが議論します。
## 筆者について
Samantha Duchscherer （グローバルプロダクトマネージャー）
Samanthaは、SmartFactory AI™ Productivity、Simulation AutoSched®、Simulation AutoMod®を統括するグローバルプロダクトマネージャーです。Applied MaterialsのAutomation Product Groupに加わる前は、BoschでIndustry 4.0のマネージャーを務めており、同社ではデータサイエンティストとしても活躍していました。さらに、オークリッジ国立研究所の地理情報科学・技術グループでリサーチアソシエイトとしての経験もあります。彼女はテネシー大学ノックスビル校で数学の修士号（M.S.）を、ノースジョージア大学ダロネガ校で数学の学士号（B.S.）を取得しています。
Michael Frenna（ワークフロー自動化および工場分析担当グローバルプロダクトマネージャー）
現在の役割において、Michaelは世界中の半導体顧客の増大するニーズに応えるため、ワークフロー自動化および工場分析サービスのロードマップ施策を推進しています。現在の役職に就く前、Michaelは半導体業界で産業エンジニアとして専門性を磨き、150mm/200mmフロントエンドファブにおけるデジタルトランスフォーメーションおよびI4.0イニシアティブの推進に貢献しました。Michaelは、テクノロジーへの情熱とイノベーション推進への意欲を持ち、世界中の顧客と協力しながら、製造能力と業務効率の向上に取り組んでいます。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [James Moyne 博士与 Samantha Duchscherer 探讨数据在实时排程中的关键作用](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/relevance-of-data-in-real-time-scheduling/)
**Published:** April 12, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 本系列文章聚焦如何通过数据驱动进一步提升生产效率与质量。
**Content:**
#### 文本
Sam: Moyne 博士，感谢您抽出时间，我非常期待聆听您的见解和专业分析。
James: 请叫我 James 就好。
Sam: 谢谢，James。让我们首先探讨工业4. 0对半导体制造业的意义。总的来说，数据在排程与派工方面究竟有何联系？
James: 好的。智能制造其实是一个涵盖面很广的领域，不仅涉及排程与派工，还包括先进工艺控制、预测性维护、虚拟量测等当今半导体制造中的诸多高科技应用。这种趋势甚至开始渗透到供应链领域，我们不仅要管理上游供应链，还要确保向客户交付产品，甚至可能需要采取诸如潜在良率分析等措施来发现问题。假设在某汽车制造厂，车辆在运输过程中出现故障，我们必须追溯到芯片生产环节来查明问题根源。所有这些都属于智能制造范畴，而机器学习、人工智能和数据分析等技术正是实现这些应用的重要推动力。
排程派工只是其中的一个领域，但智能制造的核心在于纵向与横向的深度集成，这将为排程派工带来巨大裨益。纵向集成是指从传感器、设备、工站控制器，一直延伸到制造执行系统 (MES) 乃至企业资源计划 (ERP) 的全方位贯通；横向集成则涵盖从上游供应链，晶圆厂内部，再延伸到下游客户端的全链路协同。
因此，仔细想想，传统的排程派工系统基本上是从 ERP 系统接收订单，然后传递到制造执行系统 (MES)。它会计算如何分配资源来完成订单，对吧？接着进行排程派工。系统还包含规则，比如当某台设备性能下降时，就切换到其他设备。或者当某台机器的队列长度超过某个阈值时，就需要进行调整。
这主要是基于规则驱动并且很大程度上将工厂视为内部规则集合。它不会太多关注设备在运行控制或故障检测方面的表现，也不会考虑上游供应链的情况——比如某种特定组件是否会短缺，如果我们过度使用某台设备，是否会导致该设备突然不可用？更不会关注下游客户端的反馈，比如客户是否因零件质量不佳而要求减产。
因此，展望未来的智能制造，所有这些要素都将通过驱动数据和数据接口实现横向与纵向的全面整合。当然，这其中还有许多问题需要解决。
先说数据这件事：你得把数据拿到，而且得把它们整到一起。因为很多时候，设备层面用于故障检测的数据，不能只看设备本身；它往往还要和供应链那边的数据合并起来一起分析——这样你才能解决那些会进一步影响计划排程的问题。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [高度な次世代型自動化ソリューション](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/advanced-automation-solutions/)
**Published:** March 13, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 半導体メーカー向けのApplied SmartFactory統合自動化ソリューションにより、あらゆる規模の工場品質と生産性を向上させることができます。
**Content:**
#### 字幕（全文）
シンプルな家電、オンライン請求から、ロボット工学や自動運転のような高度なシステムまで、自動化はあらゆる分野に浸透し、生活の利便性の向上や職場の安定化、そして生産性の向上を実現しています。この自動化を支えるコンピューターチップは、想像を絶するほど複雑な環境で製造されています。環境が高度化するにつれて生成されるデータ量は増え、各工程でより多くの意思決定が求められる中で自動化システムはより高速で高性能な処理能力を必要としています。
空港での手荷物受取ターンテーブルの運用と、空港全体とそのオペレーションを管理することの複雑さを比べてみてください。今日の半導体工場を稼働させるために必要な再入可能プロセス(プロセス多重起動でも安定したシステム)に対応するためには、価値の高い問題をリアルタイムで予測・解決できる高度で包括的な自動化ソリューションと、そのソリューションを導入する専門チームが不可欠です。そこで、半導体業界向けの自動化ソフトウェア、サービス、装置におけるグローバルリーダー、Applied Materials の登場です。
急速な生産量増加、仕様への準拠、新製品の導入、設備条件の変化など、さまざまな要因が絡み合う中、顧客への納期遵守は容易ではありません。だからこそApplied SmartFactoryソリューションは、工場内でシームレスに連携するよう設計されています。それは業務を改善し、収益を高め、利益を伸ばす統合システムです。
実証されたSmartFactory自動化ソリューションは、工場のライフサイクルのあらゆる段階でKPIを向上させます。SmartFactoryのソリューションは高品質、歩留まり向上、サイクルタイム短縮を実現し、工場の生産性目標の達成を可能にします。だからこそ、世界中のほぼすべての半導体工場でApplied SmartFactoryが採用されています。さあ、今すぐ始めましょう。
までご連絡ください。世界クラスの工場作りへの第一歩を踏み出しましょう。
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [強化学習がもたらす優位性とは？](https://appliedsmartfactory.com/semiconductor-blog/productivity/advantages-of-reinforcement-learning/)
**Published:** February 9, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 強化学習が実データを活用して、半導体製造における複雑なスケジュールとディスパチングの課題をどのように解決するかを見ていきましょう。
**Content:**
## 内容
- [ 仕組み ](#index1)
- [ 報酬とペナルティの定義 ](#index2)
- [ 適応性 ](#index3)
- [ 最適な意思決定 ](#index4)
- [ スピード ](#index5)
- [ まとめ ](#index6)
強化学習（RL）は、アルゴリズムが自らの経験から学習できる強力な手法として注目されています。RLは、アルゴリズムが環境とやり取りし、報酬やペナルティというフィードバックを受けながら、時間をかけて累積報酬を最大化することで最適な意思決定の方法を学ぶ機械学習手法です。
このAI手法は、ロボット工学、ゲーム、自律システムなど、さまざまな分野に革命的な変化をもたらしています。ここでは、RLの強みを探り、半導体製造におけるスケジュールとディスパチングプロセスで直面する重要な課題への取り組みにおける有効性を分析します。
### 仕組み
アルゴリズムの目的は、時間の経過とともに受け取る累積報酬を最大化することです。アルゴリズムにとって報酬とは、望ましい行動や状態（RLの目標に近いもの、または目標を達成するもの）を指します。例えば、特定のKPIを改善したり、プロセス内のセットアップ回数を制限したりすることが報酬となります。
同時にアルゴリズムは、受け取ったペナルティからも学習します。これらのペナルティ（または負の報酬）は、望ましくない行動や状態を示します。望ましくない結果を受けると、アルゴリズムは同じ行動を繰り返さないように学習します。ペナルティはアルゴリズムへのフィードバックとなり、最適でない行動や誤った動作を避けるよう誘導します。
### 報酬とペナルティの定義
アルゴリズムが報酬とペナルティをどのように扱うかを理解するために、次の例を見てみましょう（当社ホワイトペーパー「半導体製造におけるキュー時間管理のための深層強化学習（RL）」より抜粋）。
半導体製造では、キュー時間制約（QTC）がフロー内の2つのプロセスステップ間でロットが待機できる時間の上限を定めます。QTCを超えると、歩留まり損失（部品の腐食など）を起こすキュー時間違反が発生します。ルート内の任意のステップの組み合わせにQTCを設定することができ、図1の例にその設定方法が示されています。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/02/qtc-between-step-A-and-step-B.jpg) 図1：ステップAとステップBの間にQTCが設定されており、ロットがステップAに到達した後、800分以内にステップBで処理される必要があることを示しています。
この例では、QTCの下でロットをいつリリースすべきかをRLアルゴリズムに学習させることが目標です。アルゴリズムは、キュー時間違反を最小化しスループットを最大化することを報酬とみなし、その結果につながる行動を継続的に取ろうとします。一方、ペナルティはキュー時間違反となるため、違反を引き起こす行動を避けるよう学習します。
RLの実際の応用例のひとつとして、「SmartFactory AI™ Productivity tunes dispatching rule parameters automatically, in less time（SmartFactory AI™ Productivityがディスパッチルールのパラメーターを短時間で自動的に調整する）」をご覧ください。
以下に、現実世界のデータをこのように活用することで得られる利点の一部を示します。
### 適応性
RLは、変化の激しい環境でも適応し学習できる能力を備えています。シミュレーションに依存する手法とは異なり、RLは現実世界のデータから直接学習し、複雑で不確実な状況にも柔軟に対応できます。アルゴリズムは環境と直接やり取りし、フィードバックを活用して意思決定を改善することで、変動の多い環境でも高いパフォーマンスを発揮します。
スケジュールとディスパチングにおいて、この適応力は特に重要です。新規注文や機械の故障、その他予期せぬ事象がスケジュールと作業配分の判断に影響を与えるため、RLの迅速な対応能力は不可欠です。さらに、半導体製造では複数の機械や処理時間、依存関係を伴う複雑なワークフローが存在し、その管理は非常に難しいものです。RLはこれらのワークフローを理解し最適化する能力を持つため、最適な意思決定を実現できます。
### 最適な意思決定
人間の介入に頼らない自律的な意思決定は、スケジュールとディスパチングの生産性において非常に重要な役割を果たします。従来、半導体工場では機器の制約を管理し生産フローを最適化するにあたり、領域ごとに異なる複数のディスパッチルールやスケジューラに依存していました。これらのルールはたいてい複数のパラメータを含み、ユーザーが定期的に手動で調整する必要があります。
対照的に、RLはオフラインの学習環境で累積報酬を最大化することを学ぶことで、自律的な意思決定を可能にします。探索と活用を通じて、RLアルゴリズムはオンラインの生産環境で望ましい結果をもたらす最適な戦略を学習します。手動でのパラメータ調整に頼る代わりに、RLアルゴリズムはシステムの性能を自律的に適応・最適化できるようになります。これにより頻繁な手動介入が不要となり、時間・労力・コストの削減につながります。
### スピード
リアルタイムのスケジューリングとディスパチングシステムは、顧客納期など時間に敏感な要件を満たす製造業務に欠かせません。リアルタイムシステムは、ボトルネックの発見、作業負荷の分散、リソースの効率的な割り当てを支援し、効率やスループットの向上につながります。RLアルゴリズムはリアルタイムで学習し、環境に応じて瞬時に意思決定を行うことができます。この特性により、変化する環境にすばやく対応し、生産性を最大化することができます。
さらに、RLは転移学習にも対応しており、あるタスクや環境で得た知識を別のタスクや環境に応用できます。この機能により、RLはこれまでの知識を活用して、より高い熟練度で作業を開始できるようになります。学習した知識を転用することで、異なるディスパチングエリアへの移行時の適応を加速することも可能です。
### まとめ
RLには多くの利点があります。自律的な意思決定、リアルタイム学習機能、そして継続的な進化能力により、非常に有望な手法です。このAI手法の進化は、現実の半導体のスケジュールやディスパチングにおける複雑な課題への対応に大きな可能性をもたらします。
RLアルゴリズムを活用することで、半導体メーカーは生産リードタイムの短縮、スループットの向上、そして全体的な生産性向上を実現できます。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [半導体業界での高度な自動化を実現するための障壁を取り除く](https://appliedsmartfactory.com/semiconductor-blog/productivity/removing-barriers-in-semiconductor-industry/)
**Published:** October 9, 2024
**Author:** Michael Frenna, Global Product Manager, Workflow Automation and Factory Analytics
**Excerpt:** 技術の進展により、従来の工場でも自動化ソリューションを導入しやすくなりつつある
**Content:**
## 内容
- [ 自動化需要を押し上げる要因 ](#index1)
- [ 従来型ファブが直面する障壁 ](#index2)
- [ 戦略的・技術的ソリューション ](#index3)
- [ ロボティクス ](#index4)
- [ MES（製造実行システム）の進化 ](#index5)
- [ まとめ ](#index6)
Applied Materials Automation Products Groupは、世界中の顧客に自動化ソフトウェアソリューションをご提供しています。これらのソリューションを導入した経験から、手作業が多い150mm/200mmの従来型フロントエンドファブと、完全自動化された「ライトアウト」運用を行う新しい300mmファブとの間には、自動化の成熟度に大きな差があることがわかりました。これは主に、従来型製造業者がこれまでより高度な自動化を実現する際に直面してきた大きな障壁によるものです。この記事では、時代の変化と、業界が現在これらの障壁にどのように対応しているかを見ていきます。
### 自動化の需要を促している要因は何か？
より高性能なチップを必要とする新しいテクノロジーへの需要は年々高まっています。その結果、半導体メーカーは生産量の増加に直面すると同時に、より複雑な製造プロセスを導入するようになりました。このような高性能チップを生産するために必要な追加工程と労力は、特に手作業の多い従来型工場では、直接労働生産性に大きな負担を課しています。製造業者は、需要増と製造プロセスの複雑化に対応するには自動化が不可欠であり、単に労働力を増やすだけではコストがかかりすぎることを理解しています。
### 従来型ファブにおける障壁
自動化の導入を目指す従来型工場にとって、大きな障壁となる領域は主な3つあります。1つ目は所有コストです。従来型メーカーは業界の大手に比べて予算が限られた小規模な場合が多く、大規模なインフラ変更には多額の費用がかかります。多くの施設は300mm製造が始まる前の1980～90年代前半に建設されたため、オーバーヘッド搬送システムを備えていません。このような施設は、天井が低く、機器の間隔も狭いため、自動化された資材搬送を導入するのが難しく、不利な状況にあります。対照的に、300 mmセグメントの施設は、大型のフロントオープニングユニファイドポッド(FOUP)で運ぶ大型300mmキャリアに対応するため、最初から自動化された資材搬送システムを備えて建設されました。そのため、より高度な自動化を導入する上で有利な立場にあります。
建設当初から自動化搬送システムを備えていない従来型工場を改修するには、多額の費用がかかります。既存施設を再構成するには、高価な処理機械の移動、大規模な建設工事、既存スタッフの再教育が必要であり、これらすべてを、進行中の生産を中断することなく行わねばなりません。また、半導体製造でソフトウェアを稼働させるために必要な高性能サーバーの初期費用も、費用面で大きな障壁となります。
従来型工場が高度な自動化を実現できないもう一つの理由は、こうした堅牢なシステムを維持できる人材の確保です。自動化システムをインテグレーション・保守するには、大規模なITチームが必要です。しかし、多くの従来型工場では予算が限られ、ITチームも非常に小規模です。そのため、MESやその他の重要なITインフラの維持に加えて、自動化システムまで管理することは困難です。
さらに、従来型システムは通常サイロ化されたポイントソリューションで構成されており、完全自動化工場に必要な機能のインテグレーションが不足しています。多くの従来型工場では、自社開発のソリューションと複数のベンダー製商用ソリューションが混在しており、大幅な開発作業を行わない限り、互いに完全にインテグレーションすることはできません。下の図1は、このインテグレーション不足の状況を示しています。完全自動化工場を実現するにはこれらのシステムをインテグレーションする必要があることを、製造業者は理解していますが、そのためには大規模な開発作業が必要であり、小規模なITチームにとっては大きな課題となっています。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/integration-pyramid.png) 図1：製造業者は、企業レベルから現場までのデータ交換の自動化に課題を抱えています。
### 戦略的パートナーシップとすぐに使えるソリューション
従来型製造業者が直面する財務的・物流的な障壁にもかかわらず、より高度に自動化された製造環境への移行を支援するソリューションが登場しています。商業ベンダーは、低コストの「すぐに使える」または事前インテグレーション済み自動化ソリューションを顧客向けに共同開発するため、戦略的パートナーシップを結び始めています。これらのソリューションにより、開発や保守にかかるIT負荷が軽減され、顧客の所有コストを大幅に削減できます。
さらに、ハードウェアやソフトウェアの提供者は、稼働中の工場内の既存システムと共存できるモジュール式ソリューションの提供も開始しています。例えば、特定のMESに依存せず、顧客が独自に開発したものも含め、あらゆるMESで動作する非依存型ソリューションがあります。
### ロボティクス
モバイルロボット（ARV、AGV、コボットなど）の進化により、従来型工場でも施設を大幅に作り替えることなく、固有のニーズに対応できるようになっています。既存の工場には、オーバーヘッドホイスト搬送システム（OHT）などの従来型自動資材搬送システム（AMHS）を追加するには適さないインフラとシステムが既に整っています。OHTを導入するには、特定の天井高が必要であり、工場内にガイドレールシステムを設置・構築するには数年単位の建設工事が必要です。これにより多大なコストがかかるだけでなく、稼働中の工場運用にも支障をきたします。一方、モバイルロボットは工場全体を一度に改造したり導入したりする必要がなく、特定のエリアに順次展開することができます。従来型工場では、狭く天井が低いエリアでも生産に大きな支障をきたさずにモバイルロボットを導入することに成功しています。
### 製造実行システム（MES）の進歩
製造実行システム（MES）は、製造工程の監視と制御を担う重要なソフトウェアです。多くの工場では、数十年前の商用MESや、10年以上前に開発され、現在の複雑な製造プロセスに対応しきれていない自社製MESが使われています。製造プロセスに新たな要件が加わるたびに、そのギャップを埋めるためMESの周囲にポイントソリューションを構築しますが、これが前述のインテグレーションの問題を引き起こす要因となっています。
一方、近年のMESの進化により、現在の複雑な半導体プロセスにも対応できるようになり、自動化への障壁は着実に下がっています。ローコード／ノーコード開発ツールの普及によって開発効率が向上し、ITリソースへの依存も減少しました。これにより、製造業者は自動化工場におけるインテグレーション作業を支援するツールを活用し、自動化ソフトウェアの保守をより効率的に進められるようになっています。
### まとめ
製造業者は自動化の重要性を理解していますが、従来型の工場ではその導入に多くの課題がありました。こうした障壁のため、業界の先進工場に追いつくのは容易ではありませんでした。しかし近年では、コストの低減や技術リソースの拡充によって、こうした課題の解消に大きな進展が見られます。業界としては、半導体分野における自動化をより広く実現できる環境づくりを進めています。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [The Road to Full Auto in Semiconductor Assembly Test Manufacturing – SmartFactory Roadmap (Part 2 of 3)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-2/)
**Published:** February 16, 2022
**Author:** Joe Napiah
**Excerpt:** Roadmap to achieve full automation in semiconductor backend manufacturing.
**Content:**
[ Part 1: Emerging Challenges ](/blog/assembly-test-part-1/)
[ Part 3: Overcoming Roadblocks ](/blog/assembly-test-part-3)
Where is your manufacturing facility on its journey to full automation? In this video series (part 2 of 3), you will learn the role of full auto in semiconductor backend assembly test and explore the roadmap, taking you through the phases of how to use SmartFactory solutions to achieve full automation.
## Transcript
Welcome to the second video in our series on Full Auto and semiconductor assembly test. In this video, we will define Full Auto and show its role in addressing manufacturing challenges. First, a brief look at industrial advances through history.
As we look back all the way to industry 1.0, the common theme has always been usage of modern technologies to increase factory productivity. With industry 4.0, the trend continues as we see productivity advancing with the industrial internet of things, advanced analytics, and machine learning. Certainly, industry 4.0 and smart manufacturing can mean different things to different people.
It can mean self-organized manufacturing, automated material handling, industrial computing, planning, scheduling, dispatching, quality management, end-to-end supply chain management. Smart manufacturing is all of the above with automated decision making, automated execution, and automated material handling. But what do we mean when we say Full Auto? We define Full Auto as the ability to route, deliver, and process material without human intervention.
Full auto is achieved by the use in integration of a Computer-Integrated Manufacturing or CIM system and hardware systems. And we have three main goals in Full Auto manufacturing. Automated decision making, automated execution, and automated material handling.
Let’s take a deeper look at each of these goals. First, automated decision making. Here we see the Applied SmartFactory CIM solutions and where they fit into the manufacturing ecosystem.
Each of these puzzle pieces enables or provides some amounts of automated decision making. For example, in the factory productivity area, the scheduling and dispatching modules use data from the MES and other sources to determine an optimal schedule for processing what lots on what tools and exactly when. Our maintenance management solution can determine when a tool is coming due or is overdue for maintenance and automatically take appropriate actions like notifying the tool engineers and moving the tool to a scheduled downstate.
In process quality, the SPC module will automatically trigger appropriate corrective actions when data is collected out of configured control limits. Our Run-to-Run solution will automatically optimize tool recipe parameters to improve CPK and reduce scrap. Next, automated execution.
This can be achieved with the Applied SmartFactory Full Auto solution. SmartFactory Full Auto is an automated execution system that improves factory productivity and eliminates white space by executing advanced real-time event-based factory automation workflows. These workflows can be customized per factory specifications, consider multiple criteria, and handle many exception scenarios.
SmartFactory Full Auto improves factory productivity by lowering cycle time and reducing variability as well as reduces the number of expert operators needed. This means a more profitable factory. Finally, the goal of automated material handling.
Admittedly, this goal is more straightforward for 300 millimeter fabs wherein we have essentially one form factor, a wafer, and the benefit of standardized FOSBs and FOUPs to handle those wafers and overhead transports to move those standardized carriers between tools and storage locations. In assembly test, we have a lot more complexity as the work in process form factors and their physical carriers change many times between the original input, a wafer, to a roll of packaged ICs or a final packaged module. In the top left, we see the various physical carriers used in semiconductor wafer fabs and to the right many examples of material handling used in assembly test.
This variety of unstandardized carriers presents a significant challenge for automated material handling, but it is a problem worth solving, especially in high volume facilities considering the potential return on investment factors, increased output, reduction in cost, increased yield, and more. In our next video, we will discuss more about mitigating this challenge. Let’s get into a stepwise approach to achieving Full Auto.
What you will see over the next couple of slides is a gradual migration from a fully manual process in blue with manual decision making and manual transport to Semi Auto in yellow to a Full Auto process in green with automated decisions and automated transport.
At first, you may just have an MES but running in manual mode. Even in manual operation, getting away from paper and using an MES provides its own benefits.
Next, your organization aligns on a vision and plan towards Full Auto.
Third, it is common to then implement our solutions for maintenance management, durables management, and recipe management. These solutions, of course, provide their own value and lay the foundation to take advantage of automation in the future.
At step four, we see SmartFactory equipment automation. With this in place, we can automate data collection and basic operator functions like recipe select, track in, and track out.
Next, we see some additions for carrier traceability such as SmartFactory material control as well as adding carrier storage and RFID tags to carriers and equipment, which of course allows additional automation capabilities.
At step six, we see SmartFactory Dispatching. Using data from the MES and other systems, it decides what next and where next, taking the guesswork out of maximizing productivity. Moving on to the final steps towards Full Auto.
At step seven, we implement solutions for advanced process control including SPC, Fault Detection, and Run-to-Run. Adding to our earlier comments about the value of SPC and Run-to-Run, the fault detection module will provide rapid response to equipment issues before they affect process quality.
Next, at step eight, we see implementation of SmartFactory Full Auto, which we covered a couple minutes ago in our goal of automated execution.
In step nine, management sees the full ROI potential of Full Auto in part by using SmartFactory simulation.
Next, on steps 10 and 11, we see some equipment infrastructure changes to pave the way for implementing automated material handling systems like overhead transports and automated guided vehicles. Again, here we have a roadblock in assembly test due to unstandardized material handling.
We will discuss this roadblock further in our next video. At step 11, we have achieved lights out Full Auto manufacturing and our three main goals, automated decision making, automated execution, and finally automated material handling. Of course, there is always room for improvement, so in the last step, we call out continuous improvement.
Join us in our next and final video of the series, where we will discuss the roadblocks to achieving Full Auto and strategies to mitigate them. Thanks for tuning in.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, The Road to Full Auto in Semiconductor Assembly Test Manufacturing
---
### [将生成式人工智能融入工业工程工作流程](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/integrating-generative-ai-into-industrial-engineering-workflow/)
**Published:** August 13, 2025
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 对于肩负复杂数据管理任务的工业工程师而言，这种将复杂性转化为清晰洞察的潜力，或将彻底改变行业游戏规则。
**Content:**
## 内容概览
- [ 与数据对话 ](#index1)
- [ 执行操作 ](#index2)
- [ 自主洞察 ](#index3)
- [ 结论 ](#index4)
半导体制造堪称一座数据金矿——每台设备、每个工序、每项生产计划都在持续生成海量复杂信息。在当今环境下，数据采集已非难点，真正挑战在于如何快速解读这些数据。工业工程师尤其面临严峻考验——他们每日需要处理数十项甚至上百项任务，从排程分析到产能规划评估，海量数据与决策需求足以令人应接不暇。现有工具和系统虽然为数据分析提供了支持，但动态变化的晶圆厂环境中永不停歇的节奏和持续不断的任务需求，往往令他们疲于奔命。
试想，如果工业工程师能够直接与数据对话，通过交谈即可执行操作，进而实现流程自主化——由大预言模型驱动的对话式辅助系统，或将重新定义工业工程师与数据的交互方式。
### 与数据对话
工业工程师时常会陷入各种紧急状况，必须迅速解决突发问题。这些状况每天可能五花八门——设备故障、生产瓶颈、供应链中断，或是质量控制问题。这种被动应对模式常被称为“救火式工作”，往往需要耗费大量时间和精力。尽管现有报表系统能提供支持，但有时层层嵌套的报表反而让人陷入 “用报表解释报表” 的循环。面对琳琅满目的数据看板，工程师真正需要的往往只是对直接问题的简明解答。他们既不想费心编写查询语句，也不愿耗时分析模型，更担心误读数据——他们只希望快速获得答案，例如：“数据集中有多少台设备？” 或是 “每日晶圆批次的投产量是多少？”
与数据对话以加深理解——这种通过自然对话进行探索性数据分析 (Exploratory Data Analysis) 的方式，本质上是个非常简单的概念。然而，仅仅通过提出清晰直接的问题，往往能显著提升工作效率。
此外，这种对话能力并不局限于简单提问。工业工程师可能同样需要验证假设或核查数据质量。例如，他们可能会提出这样的质询：“数据中是否存在负值的加工时间？” 确保数据的准确性和可靠性是持续存在的挑战，而标准化验证流程更是难上加难。面对不同情境，工程专家通常清楚需要排查哪些关键点——无论是可能预示深层问题的异常值、缺失数据，还是逻辑矛盾。精简数据质量核查流程，对保障决策效率具有至关重要的意义。
### 执行操作
虽然对话式辅助为数据交互提供了强大支持，但仅靠对话往往不够。工业工程师不仅需要获取答案，更需要触发实际行动。他们往往希望突破对话层面，直接通过交谈来推动成果实现。
试想通过简单指令即可更新数据：“将 UID: X 修改 UID:Y ”，或轻松生成分析视图：“创建柱状图显示各设备认证状态”。还能随时切换数据呈现方式：“以表格形式展示这部分数据”。更可便捷执行场景推演：“将 X 区域的预防性维护计划推送至 Y 日期”。
工业工程师无需依赖深厚的软件知识，也不必记住特定的操作步骤，只需与系统对话即可完成任务。当对话能够直接驱动行动时，对话式人工智能的价值就已超越操作便利性，真正产生运营层面的影响。
### 自主洞察
那么，如果人工智能不仅能响应问题和指令，还能主动预判日常工作需求呢？试想这样的场景：工业工程师开始一天的工作，就已经清楚知道当天必须完成的任务及截止时间——不是因为看了任务清单，而是因为人工智能系统已主动推送了最关键事项。
工程师无需再询问“今天最需要修复哪些关键设备？”，人工智能会自动给出答案：“以下是今日亟需修复的设备清单。“
工业工程师还可以更进一步，再次回到“与数据对话“的环节。他们可以询问：”为什么这些设备被视为关键？“并得到清晰的解释。此时系统不仅呈现优先级排序，更揭示了背后的决策依据；工程师既能知悉”何事紧要“，更能理解”为何紧要“。这种透明度至关重要：既建立了对自动化的人工智能驱动系统的信任，更在推动有效变革管理方面发挥关键作用，使工程师能够自信地拥抱新型工作模式。
### 结论
随着工厂日益追求更敏捷、响应更迅速的运营模式，人工智能驱动的对话界面和自主智能体正逐步融入半导体制造工作流程。然而，维持高质量数据基石、完善详细文档体系、整合专家知识与最佳实践，这些基础要素依然至关重要。再先进的系统，其效能终究取决于所依托的信息质量。唯有夯实这些基础，生成式人工智能才能真正持续演进，并加速决策过程。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [The Road to Full Auto in Semiconductor Assembly Test Manufacturing – Emerging Challenges (Part 1 of 3)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/assembly-test-part-1/)
**Published:** February 17, 2022
**Author:** Joe Napiah
**Excerpt:** Learn what matters most to experts as they address emerging challenges and complexities in semiconductor backend manufacturing.
**Content:**
[ Part 2: SmartFactory Roadmap ](/blog/assembly-test-part-2)
Learn what matters most to experts as they address emerging challenges and complexities in semiconductor backend manufacturing. Key areas covered in this video series (part 1 of 3) include supply chain, technology and products, materials, equipment, and human resources.
## Transcript
Welcome to our first video in our on-demand webinar series on full auto and semiconductor assembly tests. In this video, we’ll talk about challenges in today’s assembly and test manufacturing. So what are the manufacturing challenges in assembly tests and what are the KPIs those challenges impact? First, supply chain complexity, which impacts cycle time, on-time delivery, and of course cost.
Next, technology and product complexity, which primarily impacts cycle time and the speed of technology development or the cycle of learning. Technology and product complexity is very related to our next challenge, materials complexity and traceability. Consider that in assembly test, we see a transition from simple single die lead frame packages to multiple chips in a single package or even multiple packages with 2.5D or 3D packaging advances as well.
These complexities impact OEE, ease of traceability analytics, and traceability granularity. Next, equipment and process complexity, which impacts OEE and yield. Finally, human resource complexities, which are measured in part by productivity, scrap, and on-time delivery.
Let’s dive a little deeper into supply chain complexity. In the back, we see the whole semiconductor supply chain from silicon to final product, starting from raw silicon to silicon wafers used in the fabs to assembly test and ultimately to a final product in the customer’s hands. What are the key challenges in the supply chain? Of course, diversity.
Vertical integration in the supply chain can vary anywhere from a wholly fabulous company that outsources every link in the chain to integrated device manufacturers trending to more and more internal manufacturing. Next, dynamic ordering patterns. I’m sure you are all familiar with the inventory challenges caused by COVID with parts on backorder for several months and some foundry capacity booked for the next couple years.
Multiple packaging technologies and emerging technologies, 2.5D, 3D, wafer-level packaging is causing an explosion in part numbers and thus additional inventory dependencies. What are the key manufacturing challenges related to the supply chain complexity? Short technology cycles. There’s always a new version of some widget to buy.
ROI requirements and their high capital investments. Tight lead times and on-time delivery. The cost of yield and scrap.
By the time an IC makes it to assembly test, a lot of time and money has already been invested. The further down the supply chain, the higher the potential losses. And of course, integration and interoperability between all of these facilities.
This can impact the ability to optimize supply chain planning, failure mode analysis, and much more. Now let’s look at materials complexity and traceability. As we mentioned earlier, there’s a transition from single chip packages to multiple chip 3D packages.
This transition directly causes a complexity of individual components as more and more different parts are needed for these more complex packages. So how do these complexities impact productivity and quality? Again, more materials means more critical dependencies. So we can potentially have more lined down situations due to short inventory.
There are more and more potential points of failure if we have poor quality source materials. And finally, the all-important yield. We need a constant supply of an ever-growing list of high quality source materials to get high yield.
Product and technology complexity. Here we see a couple of key technology trends. The internet of things and autonomous vehicles.
Each of these trends is causing an explosion in the demand for various electronics, including but certainly not limited to various sensors, processors, and displays. With the internet of things, we see more and more devices connecting to Wi-Fi from alarm clocks to bathroom scales to refrigerators. As you can imagine, the quality standards for electronics in the automotive industry is already high, and with the advents of autonomous vehicles, we should certainly expect these standards to get ever more stringent.
Next, equipment and process complexity. First, consider we have new emerging packaging technologies. This leads to, of course, an increasing high product mix and increasing counts of manufacturing processes.
These new packaging technologies also have more complex processes, and we see an increasing mix of process equipment used. In most assembly test facilities, we have legacy equipment, which may not conform to semi-standards like SECS/GEM and Interface A, which causes challenges in retrieving data from that equipment. This all leads to a big data challenge, considering the increasing volumes and variety of data.
And it’s not just about capturing the data, but also modeling and effectively using that data. Next, let’s discuss human resources complexity. Consider that most assembly test facilities are executing highly manual processes.
Without the benefit of full auto process enablers, people are making important decisions that directly impact and potentially harm productivity and quality. What lots should be processed next and on what equipment? Are there enough materials on hand? Is the equipment available or overdue for maintenance? Are there any restrictions based on process queue times or equipment certifications to consider? In our next video, we will show how Applied SmartFactory can mitigate these challenges. Now that we’ve had a deeper dive into the manufacturing challenges, let’s consider what we are hearing from the industry.
First, the number one priority is quality and, of course, addressing yield issues. Secondly, on-time delivery. Customers want to see prompt deliveries and committed dates held.
So the focus here is on mid-term, long-term planning, short-term scheduling, and real-time dispatch. Next, the transition to advanced packaging. By this, we mean fab-like processes like wafer-level packaging and panel-level packaging.
Next, data infrastructure. This is in part to provide direct access to customers, but also advanced analysis. More modern equipment can make gathering data straightforward if compliance with standard protocols, but old legacy equipment, as we mentioned, certainly can make data availability more difficult.
Productivity, both human and equipment. In part, this is referring to automated material handling, perhaps with AGVs or overhead transports, as well as minimizing human errors, both of which we cover in more depth in the next video. Finally, accelerated issue resolution.
The cycle of learning has to be quick and thus problem-solving needs to be very fast as well. Customers will continue to apply cost pressures and demand more traceability. These six points are the key items we hear from our assembly test customers.
Join us in our next video where we define full auto and how we can address these challenges. Thanks for tuning in.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, The Road to Full Auto in Semiconductor Assembly Test Manufacturing
---
### [Achieve critical factory KPIs with industry-proven turnkey CIM solution](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
**Published:** June 17, 2022
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** Integrate automation capabilities across your entire factory domain with our SmartFactory CIM solution.
**Content:**
### Interview
Bing Wang, Director of CIM Solution, discusses how to achieve critical factory KPIs with an industry-proven turnkey solution: Applied Smartfactory® CIM solution.
Our Insights blogger sat down with Bing Wang to find out how a turnkey CIM solution can accelerate a semiconductor fab’s yield and product output, and at the same time reduce cycle time and costs. What’s the recipe for successfully deploying such a turnkey solution?
Insights: First, in the context of semiconductor, how would you define “computer integrated manufacturing”?
Bing: It’s simply the approach of using computer software applications to control, automate and document the entire semiconductor manufacturing process—from front end wafer fabrication to assembly, test, and packaging on the back end.
Insights: And what value does—or can—a CIM solution provide?
Bing: When properly implemented, a turnkey CIM system can help manufacturers achieve rapid system deployment and faster productivity gains, which is especially important not only for those companies with existing factories that are competing harder on cost, quality, and cycle time, but also for new companies with limited prior experience building their first fabs. For new fabs time is incredibly valuable; deploying a fully integrated CIM is an avenue for helping such fabs achieve first silicon and volume production targets earlier, to meet technology and commercial requirements (see [Bringing production reality closer to target](/blog/bringing-production-reality-closer-to-target/?hilite=driving+curve)).
Insights: In your view, apart from deployment and speed, what other challenges do semiconductor fabs often have to address when adopting a CIM?
Bing: For today’s semi fabs, we typically see manufacturing automation spread across four main areas, including manufacturing execution, process quality control, productivity efficiency, and supply chain integration. Connecting and integrating all these manufacturing domains across the many areas of a fab—and doing it in a cohesive manner—is one of the most time-consuming aspects of deployment. It can take anywhere from 6 to 12 months because every fab and its products are different, which requires significant customization from one factory to another. A considerable amount of time also must be spent validating the extremely complex manufacturing processes needed for a fab’s products.
Another big challenge semi fabs face with implementing and operating a CIM relates to data consumption. Semiconductor automation systems rely on massive amounts of data integrated from different CIM components—data related to orders, products, process steps, equipment sensors, and operators to drive the business decision making process. This data typically resides in disparate CIM applications with their own integration methods. In some cases, data does not exist, is incomplete, or is manually maintained on an operator’s laptop.
Insights: What is Applied Materials doing to address this gap?
Bing: We’ve developed our SmartFactory CIM solution—a one-stop, turnkey, fully automated solution that integrates Applied Materials automation products across four essential factory domains, including [manufacturing execution](/semiconductor/manufacturing-execution-solutions/), [process quality](/semiconductor/process-quality-solutions/), [factory productivity](/semiconductor/productivity-solutions/), and [supply chain](/semiconductor/supply-chain-solutions/). The underlying systems for each of these domains are connected through a message bus (see Figure 1). This out-of-box integration provides synchronized real-time communication to enable seamless decision-making logic flow that controls the complex manufacturing operations in a fab. The off-the-shelf capabilities make it possible to ramp up a new semiconductor factory in less than 6 months.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/fig-1-cim-diagram.jpg) Figure 1. The Applied SmartFactory CIM solution integrates automation products across four factory domains: manufacturing execution, process quality, factory productivity, and supply chain management
Insights: In your view, what are the key performance indicators addressed by your CIM solution? Or those key areas of the solution worth highlighting?
Bing:I’d say accelerated time to market, reduced cycle time and better factory monitoring. More specifically, I’d say five key areas are worth noting here:
**Full-automation of manufacturing operations**
[SmartFactory MES 300Works® Full-Auto](/semiconductor/manufacturing-execution-solutions/300works-full-auto/) offers an MES framework and solution for integrating factory operations, such as [material control](/semiconductor/manufacturing-execution-solutions/material-control/), [factory events](/semiconductor/productivity-solutions/activity-manager/), [planning](/semiconductor/productivity-solutions/simulation-autosched/) and [scheduling](/semiconductor/productivity-solutions/scheduling/), and [equipment maintenance management](/semiconductor/manufacturing-execution-solutions/maintenance-management/) and all in full automation mode.
**Process quality and yield**
Our Applied E3® process control framework provides industry leading applications for [fault detection](/semiconductor/process-quality-solutions/fault-detection/), [run-to-run control](/semiconductor/process-quality-solutions/run-to-run-control/), [SPC](/semiconductor/process-quality-solutions/spc/), [equipment automation, ](/semiconductor/process-quality-solutions/equipment-automation/)[recipe management](/semiconductor/process-quality-solutions/recipe-management/), yield management, and defect management, all of which are used on various manufacturing processes across multiple fabs to generate process quality results and maximize yield.
**Factory productivity**
Our SmartFactory APF productivity framework includes [scheduling](/semiconductor/productivity-solutions/scheduling/), [dispatching and reporting](/semiconductor/productivity-solutions/dispatching-and-reporting/), [simulation](/semiconductor/productivity-solutions/simulation-autosched/) and prediction, which are integrated with [enterprise planning](/semiconductor/supply-chain-solutions/enterprise-planning/), [equipment automation](/semiconductor/process-quality-solutions/equipment-automation/), [maintenance management](/semiconductor/manufacturing-execution-solutions/maintenance-management/), and advanced process control to maximize equipment uptime for productivity gains. Full automation capability in the productivity domain reduces white space and wasted tool time to maximize factory output.
**Time to market and cycle time**
Our SmartFactory workflow engine, empowered by production simulation, provides intelligence in workload prediction and reduces material wait time, resulting in shorter cycle times and overall time to market.
**Factory monitoring**
Worth mentioning here is our SmartFactory [monitor](/semiconductor/manufacturing-execution-solutions/monitor/) solution, which patrols all CIM solution components, as well as enhances and protects factory operations. Its automated installers and easy-to-use features enable customers with lower cost of support and ownership.
Insights: Finally, what would you say is unique about Applied’s CIM offering?
Bing: Definitely experience. What I mean is that our SmartFactory CIM solution has been built with the best industrial expertise and knowledge in the industry. As the largest deployed CIM solution in the global semiconductor industry, it has been “hardened” (or developed over time) with each successive factory install. I think the key differentiators of our solution include:
**Largest deployed CIM solution**
Applied Materials is the leading semiconductor industry automation solution provider, with a team of nearly 1000 experts and three decades of experience automating semiconductor fabs.
**Low or no customization requirements for integration**
Most manufacturing operation management vendors own only a subset of capabilities in semi factory full auto needs, which requires significant customization to integrate various vendor products to cover full factory needs. In contrast, our SmartFactory CIM solution includes a comprehensive suite of SmartFactory solutions that are pre-integrated to cover semi factory full auto needs with low or no customization requirements.
**Off-the-shelf capabilities**
Applied SmartFactory EngineeredWorks® provides the pre-composed dispatching rules, MES automation rules, and R2R controllers that support over 90% of factory full auto operation scenarios. These off-the-shelf capabilities enable fast deployment for new fab startups and speed to market.
**Powerful self-service platforms**
The APF platform allows factory industrial engineers or planners to program customized dispatching rules for specific dispatching situations without having to involve IT resources. Similarly, our Applied E3 platform enables factory process engineers to create run-to-run process controllers to tune their specific process parameters. These platforms empower users to control fab behavior.
**Conclusion**
Applied’s fully integrated SmartFactory CIM solution includes a wide breadth of mature capabilities, spanning manufacturing execution, process quality, factory productivity, and supply chain management. The semiconductor industry is using this automation suite to attain predictable yield and output results.
Ready to contact us to learn more about our SmartFactory CIM or other solutions?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular, Semi
---
### [Unveiling the Advantages of Reinforcement Learning](https://appliedsmartfactory.com/semiconductor-blog/productivity/advantages-of-reinforcement-learning/)
**Published:** February 9, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** Explore how reinforcement learning offers a revolutionary approach to using real world data to solve complex scheduling and dispatching challenges in semiconductor manufacturing.
**Content:**
## What’s Inside
- [ How it works ](#index1)
- [ Defining reward and penalties ](#index2)
- [ Adaptability ](#index3)
- [ Optimal decision making ](#index4)
- [ Speed ](#index5)
- [ Conclusion ](#index6)
Reinforcement Learning (RL) has emerged as a powerful technique that enables an algorithm to learn from its own experiences. RL is a machine learning approach where an algorithm learns to make decisions by interacting with an environment, receiving feedback in the form of rewards or penalties, and maximizing cumulative rewards over time.
This AI approach has revolutionized various fields, including robotics, gaming, and autonomous systems. Here, we will explore the strengths of RL and analyze its effectiveness in tackling critical challenges found in the scheduling and dispatching processes of semiconductor manufacturing.
### How it works
The algorithm’s objective is to maximize the cumulative reward it receives over time. To the algorithm, a reward is a desired action or state—something that either is close to or achieves the RL’s goal. A rewarding outcome can be improving a particular KPI or limiting the number of setups in a process, for example.
The algorithm also learns from penalties it receives. These punishments, or negative rewards, are undesirable actions or states. Receiving an undesirable result discourages the algorithm from taking this type of action again. Punishments provide feedback to the algorithm, guiding it away from suboptimal or incorrect behavior.
### Defining reward and penalties
To better understand how an algorithm views rewards and penalties, consider this example, (derived from our whitepaper, [“Deep reinforcement learning (RL) for Queue-time management in semiconductor manufacturing”](/semiconductor-blog/deep-reinforcement-learning/)):
In semiconductor manufacturing, queue-time constraints (QTC) set the limit for how long a lot can wait between two process steps in its flow. Exceeding QTC results in queue-time violations that represent yield loss (i.e., corrosion of a part). Any pair of steps in a route can have a QTC between them, as seen in the example in figure 1, below.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/02/qtc-between-step-A-and-step-B.jpg) Figure 1: Shows a QTC between Step A and Step B indicating that, after lots go to Step A, they must be processed on Step B within 800 minutes.
For our example, the goal would be to set up an RL algorithm to learn when to release lots in this QTC. The algorithm would see minimized que time violations and maximized throughput as a reward and would try to continue to take the actions that led to that. The penalty would be que time violations, so it would learn to avoid taking the steps that resulted in violations.
For another example of a practical application of RL, visit [ “SmartFactory AI™ Productivity tunes dispatching rule parameters automatically, in less time.”](/semiconductor-blog/smartfactory-ai-productivity)
The following are some of the many advantages to using real world data in this way.
### Adaptability
RL offers adaptability and learning capabilities in a dynamic environment. Unlike simulation-based methods that rely on assumptions, RL can directly learn from real-world data and effectively handle complex and uncertain scenarios. It excels in active environments by learning from direct interactions and using feedback to improve its decision-making.
For scheduling and dispatching, this adaptability is crucial. With new orders, machine failures, and various other unexpected events impacting scheduling and dispatching decisions, RL’s ability to quickly adapt becomes essential. Moreover, semiconductor manufacturing involves intricate workflows with multiple machines, various processing times, and dependencies, adding to the complexity. RL’s capabilities to adjust allows it to understand and optimize these workflows, ensuring optimal decision making.
### Optimal Decision-Making
Autonomous decision-making, independent of human intervention, plays a pivotal role in productivity for scheduling and dispatching. Traditionally, semiconductor facilities rely on multiple dispatching rules and schedulers specific to different areas to manage equipment constraints and optimize production flow. These rules often involve several parameters which require manual adjustments by users on a regular basis.
In contrast, RL enables autonomous decision-making by learning to maximize cumulative rewards in an offline training environment. Therefore, through exploration and exploitation, RL algorithms learn and uncover optimal strategies to achieve desired outcomes in an online production environment. Instead of relying on manual parameter adjustments, RL algorithms can autonomously adapt and optimize system performance. This reduces the need for frequent manual intervention, saving time, effort, and cost.
### Speed
Real-time scheduling and dispatching systems are essential for manufacturing operations to meet time-sensitive requirements, such as customer delivery deadlines. Real-time systems facilitate the detection of bottlenecks, the distribution of workloads, and the effective allocation of resources, resulting in improved efficiency and increased throughput. RL algorithms, known for their real-time learning capabilities, adapt and make instantaneous decisions. This advantage empowers RL algorithms to promptly respond to a changing environment, ultimately maximizing productivity.
Furthermore, RL has the potential for transfer learning, allowing knowledge gained from one task or environment to be applied to another. This capability enables RL to leverage prior knowledge and start with a higher level of proficiency. By transferring learned knowledge, RL can accelerate the adaptation process when transitioning to different dispatching areas.
### Conclusion
RL presents a multitude of benefits. Its capacity for autonomous decision-making, real-time learning abilities, and ongoing evolution makes it a promising approach. The continuous advancement of this AI approach holds immense potential for effectively addressing complex challenges in real-world semiconductor scheduling and dispatching scenarios.
By leveraging RL algorithms, semiconductor manufacturers can achieve a reduction in production lead times, an improvement in throughput, and an overall increase in productivity.
## FAQs
#### Why is data preparation for AI considered a challenge in semiconductor manufacturing?
Data preparation for AI can be expensive in terms of time and resources, making it a barrier, especially for smaller companies. Historical data may also be insufficient due to evolving environments.
#### How does simulation help overcome data collection challenges for AI deployment?
Simulation allows for the creation of synthetic data, eliminating the need for extensive data cleaning. It provides an efficient way to generate diverse and high-quality data for AI training.
#### What are some practical benefits of using simulation in AI deployment?
Simulation enables the exploration of AI in essential use cases without resource limitations. It accelerates projects, reduces costs, and quantifies the impact of changes before implementation, reducing risks.
#### What role does simulation play in scenarios like Reinforcement Learning (RL) and Machine Learning (ML) in semiconductor manufacturing?
Simulation plays a crucial role in RL by providing a detailed environment for agents to learn and make decisions. In ML, it allows models to be trained on rich datasets, leading to operational efficiency gains and KPI comparisons.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [优化系统性能，检测和预测系统故障](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
**Published:** November 25, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 使用运行时监控和预测分析算法，助力您的工厂保持稳定运营。
**Content:**
使用运行时监控和预测分析算法，助力您的工厂保持稳定运营。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Newly Released
---
### [准备好优化您的封装解决方案了吗？](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
**Published:** November 25, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 借助最新的技术趋势，我们可以助您应对封装行业面临的挑战。
**Content:**
借助最新的技术趋势，我们可以助您应对封装行业面临的挑战。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Newly Released, Popular
---
### [Moving toward zero-defects manufacturing with gusto to make your factories smarter](https://appliedsmartfactory.com/semiconductor-blog/quality/moving-toward-zero-defects/)
**Published:** July 18, 2023
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** This blog series discusses strategies, priorities, and challenges manufacturers face to automate factories of any size to move the needle towards zero defects manufacturing
**Content:**
### What does zero defects strategy mean in smart manufacturing?
A [ zero-defects strategy](/blog/automotive-manufacturing/) is not a new concept; most companies have been working on developing one for many years. However, the approach to building such a strategy in smart manufacturing is an evolving concept. Technology has changed, expectations have changed, there are more extensive possibilities, and even what we’re expected to do from an automation and quality perspective has evolved. It’s important to look at some of the challenges we face in developing a zero-defects strategy, and how we may go about mitigating them.
### What are some of the challenges we face?
We’ll use the automotive industry as an example many people are familiar with. Vehicles have considerably more sensors, automated driving systems, safety systems, and features on board. As a result, there has been increased pressure on the industry to build more chip driven subassemblies.
However, the industry is experiencing a problem from the latent failure perspective. This is when a factory manufactures a component that makes its way through the supply chain and fails in the field. Ultimately, it becomes a challenge to determine what caused the failure. This has become particularly difficult as 22% of warranty failures are electronic components related. Furthermore, they fail within the warranty period of an automobile. The industry faces a daunting task to track the geneology of parts manufactured in a factory. 85% of the automotive parts are made in 150mm and 200mm facilities that are not as well equipped to track the history of parts. This history needs to span several years. This challenge is significant. Think about what’s involved in accurately collecting, reconciliating, and tracking mounds of data. This task is so big and important that IATF standards (IATF 16949 Standards) were developed to assess the ability to meet the manufacturing practices required to minimize the risk. The challenge comes from the reality that legacy facilities were not designed to track to this extent of granularity. The desire to resolve discrepancies in the data exists, but to figure out how and the time it requires to do this efficiently and meet quality standards consistently is daunting (figure 1).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/streamline-quality-standards.jpg) Figure 1: Shows the baker’s dilemma in how to streamline quality standards.
Figure 1: Highlights the importance of precision required to streamline quality standards.
### Identifying the Cause
Beyond following the standards, it’s important to ask, “How are we doing this today?” The first step in answering these questions is to look at the anatomy of failures. This anatomy of failures is broken into three categories to be considered at the macro level:
- **Systemic:** Where the factory had a parametric test for something and yet there was still the opportunity to send something out the door that would have been caught by that test. For some reason, they failed to identify the problem. This is the most common cause of latent failure.
- **Test coverage:** This is the cause for one-third of the cases of latent failure. It occurs when a factory designs something new, or something with a new characteristic that warranted a new parametric test that is missing. This is because they didn’t know they needed it or didn’t have it.
- **Random:** In this instance there is an inability to classify where the failure came from and therefore it is deemed a random failure. These are some of the more disturbing problems because they point to a much more systemic gap in the automation capabilities.
The anatomy of the latent failures lends insight into the type of automation deficiencies that a factory may have (Figure 2).
Figure 2: Anatomy of Latent Failures
In our next segment in this blog series, **Moving toward zero-defects with gusto to make your factories smarter**, we’ll discuss how to identify types of missing automation CIM components. Stay tuned.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Retrieval-Augmented Generation in semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/retrieval-augmented-generation-in-semiconductor-manufacturing/)
**Published:** January 16, 2026
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** Understanding the importance and evolution of RAG
**Content:**
## What’s Inside
- [ What is Retrieval-Augmented Generation? ](#index1)
- [ Example of retrieval-based techniques for semiconductor manufacturing ](#index2)
- [ Advantages and limitations of RAG ](#index3)
- [ RAG is evolving ](#index4)
- [ What is Agentic AI? ](#index5)
- [ Securing a competitive advantage ](#index6)
Artificial intelligence (AI) is often used as a blanket term in everyday conversation, but the reality is far more nuanced. Recent advancements have produced sophisticated models and architectures, each with distinct mechanisms, strengths, and limitations. Some excel at creative tasks, while others serve as analytical powerhouses or autonomous decision-makers. In semiconductor manufacturing, this evolution comes at a critical time—fabs are grappling with unprecedented complexity, skyrocketing data volumes, and accelerating automation, where every second of downtime can cost millions. To stay competitive, manufacturers need AI systems that go beyond answering questions—they must anticipate issues and act proactively. Thus, this article explores Retrieval-Augmented Generation (RAG), its benefits and constraints, and the industry’s shift toward Agentic AI—a paradigm that focuses on fusing dynamic knowledge retrieval with autonomous decision-making.
### What is Retrieval-Augmented Generation?
RAG is a hybrid approach that combines the generative capabilities of large language models (LLMs) with the precision and relevance of document retrieval systems. Specifically designed for synthesizing information, it is, as the name suggests, comprised of both a retriever and a generator. The system first searches a large knowledge base to find relevant data for its query, then synthesizes and contextualizes the retrieved information to generate a natural language response.
### Example of retrieval-based techniques for semiconductor manufacturing
Consider [SmartFactory Genie](/ai), which leverages LLMs and retrieval-based techniques, to simplify and accelerate how you use Applied SmartFactory® software products.
Imagine an engineer facing an unexpected slowdown in a dispatcher rule—a critical issue for fab operations. Instead of wading through lengthy manuals or waiting for expert assistance, the engineer simply asks Genie: “What could be the possible root cause for sudden slowness in Dispatcher rule execution?” Here RAG makes the difference because it retrieves the most relevant help documentation, then uses generative AI to synthesize context-aware insights. The engineer receives a concise explanation of potential causes along with actionable next steps—instantly.
Now picture a new engineer setting up their environment who asks: “How do I install Python and set it up for E3 Strategy Designer?” Instead of searching across multiple manuals or guessing configurations, Genie leverages RAG to pull accurate instructions and generate a clear, step-by-step guide tailored to the engineer’s scenario. By delivering this information in a contextual, conversational format, Genie removes friction from the learning process. New engineers can start experimenting and contributing faster—reducing onboarding time and training time.
### Advantages and limitations of RAG
RAG offers several advantages that make it highly valuable in semiconductor manufacturing. By relying on relevant sources, RAG helps reduce the risk of hallucinations and ensures responses reflect the latest information. Another key benefit is transparency—RAG can include references to specific documents in its answers, giving users confidence in the source and improving traceability. This built in transparency enhances user trust. In complex knowledge ecosystems like semiconductor fabs—where thousands of specifications, SOPs, engineering reports, and tool logs are constantly evolving—RAG excels at navigating large, intricate information landscapes to surface what matters most.
However, RAG is not without limitations. Because it must search before generating a response, it can be slower than purely generative models. Its performance also hinges on how well the retriever surfaces relevant information. If the system can’t locate accurate or useful documents, the model may respond that no suitable content exists. While RAG is strong at answering questions and summarizing source material, traditional RAG does not inherently support multistep reasoning or planning. It isn’t typically built for goal-oriented tasks that require coordinated steps, decision-making, or execution.
### RAG is evolving
For years, Retrieval-Augmented Generation (RAG) has set the benchmark for intelligent assistance—blending precise information retrieval with generative capabilities to deliver clear, context-rich answers to complex questions. Also, emerging innovations such as multimodal retrieval—integrating text, images, and sensor data—are poised to make RAG even more powerful. Personalized retrieval, tailored to a user’s role and historical queries, will further streamline interactions and boost efficiency. Yet, as fabs demand more than just answers, a new paradigm is taking shape: Agentic AI
### What is Agentic AI?
Agentic systems go beyond “find and summarize.” They plan, decide, and act autonomously in dynamic environments, transforming AI from a passive advisor into an active problem-solver. For example, a RAG-powered Genie helps an engineer diagnose a slowdown by retrieving relevant manuals and generating actionable insights, while an Agentic Genie takes it further—detecting anomalies, analyzing historical data, and orchestrating corrective actions across multiple systems.
Consider a fab facing sudden equipment failure. Here you can imagine an agentic system detecting the anomaly, analyzing the maintenance history, identifying the root cause, and then scheduling repairs, rerouting production, or even updating delivery forecasts—all without manual input. This shift from information to execution is a critical capability that ensures minimal downtime.
### Securing a competitive advantage
AI continues to advance in both technique and capability. RAG strengthens language models with external retrieval, delivering greater accuracy and relevance. Agentic AI takes the next step—bringing autonomy and the ability to act. As fabs move toward lights-out operations, this evolution will shape the future of intelligent manufacturing, where knowledge and action converge seamlessly. For semiconductor manufacturers, mastering these concepts is essential to harness AI’s full potential and secure a competitive edge.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [AI 与云技术的集成（下篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-2/)
**Published:** May 2, 2025
**Author:** Samantha Duchscherer and Emrah Zarifoglu
**Excerpt:** 根据可扩展性和灵活性决定何时及如何将 AI 迁移到云。
**Content:**
[ 上篇：AI 与云技术的集成 ](/zh-hans/semiconductor-blog/al-ml-zh-hans/ai-and-cloud-integration-part-1/)
## 内容概览
- [ AI 部署的阶段规划 ](#index1)
- [ 数据同步策略 ](#index2)
- [ AI 资源迁移路径 ](#index3)
- [ 边缘计算部署 ](#index4)
- [ 云端环境为 AI 开发者带来的优势 ](#index5)
全球产品经理Samantha Duchscherer 与云及AI/ML研发负责人Emrah Zarifoglu，是致力于将 AI 技术应用于 SmartFactory AI 解决方案的自动化专家。在这篇分为两部分的系列访谈的首篇中，他们界定了云的定义，并探讨了企业上云的决策流程。随着 AI 正在变革各行各业，理解其与云技术的关系变得至关重要；在第二篇讨论中，他们将深入分析向云端迁移将如何影响 AI 模型的部署。
Sam：现在我们可以开始将 AI 纳入讨论了，这让我非常兴奋。首先谈谈 AI 部署的不同阶段。
我认为 AI 部署主要分为三个阶段：数据准备、模型开发和模型部署。结合我们之前讨论的术语
【[参见上篇](/zh-hans/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-1/)】，这些术语与 AI 部署的不同阶段有何关联？
Emrah: 实际上，AI 部署的所有阶段都可以通过 Docker 容器完成。如果是生产级部署，就应该使用 Kubernetes，或者更理想的情况是通过 Helm 图表进行配置。这是我们在进行产品研发和团队合作时遵循的方法，代表了业内广泛认可的最佳实践。不过需要注意的是，这些并非唯一可行方案。
在决定将 AI 的哪些组件或阶段迁移到云端时，需要考虑可扩展性、灵活性和资源利用率在哪些环节最具价值。例如，数据流庞大且需要大量预处理的工作负载能极大受益于云的扩展能力。模型的反复训练和评估过程同样能从中获益。在部署期间，云能提供必要的可视化管理能力。
归根结底，在需要高度可扩展性和灵活性的 AI 应用场景中，云能带来最显著的优势。
Sam：确实，将部分迁移至云端而保留其他部分在本地是合理的方案。但在 AI 数据准备阶段该如何实施？我们如何解决在不同环境中同步数据和构建管道的挑战？
Emrah: 无论是数据还是应用，大多数企业实际上已经在采用混合云模式——部分数据和应用部署在云端，其余则保留在本地。由于技术和位置差异，要实现数据同步并构建统一管道始终存在挑战。虽然将所有数据迁移至一个云看似简单，但这往往不切实际。更务实的做法是，我们需要做好在混合环境中运作的准备，并解决随之而来的难题。
在这种混合环境中，最大的挑战之一是保障数据安全，防范恶意访问。从这个角度看，主要风险点并非基础设施本身，而是网络层面的安全隐患。另一方面，如果网络足够安全，那么各种技术的同步问题就可能成为另一个挑战。
尽管将所有资源集中部署是理想状态，但我们不会强制客户采用这种方案，而是帮助他们建立足够的能力和信心，使其能够从容管理所依赖的环境（无论是纯云还是混合架构)。
Sam: 将话题从 AI 阶段转移到 AI 资源，我认为资源方面也存在转型过程。对于已经在生产中使用 AI 的客户而言，迁移到云会如何影响数据工程师、数据科学家和工业工程师的职责？
Emrah: 影响的程度取决于他们的使用情况以及与基础设施的连接程度。数据工程师是最接近基础设施的群体，他们使用的工具直接受到基础设施相关技术选择的影响。他们需要能在任何环境中使用为其选定的技术进行操作。
相比之下，数据科学家是否受影响则不确定。他们与基础设施的接近程度取决于所用工具及其使用方式。
工业工程师作为最终用户，与基础设施的关联最弱。他们使用的应用程序即便底层基础设施发生变化，很可能也浑然不觉。
Sam: 我还能再问一百个问题，但为了简短起见，最后我想以一个质疑性的问题结束。对于那些认为延迟是云端 AI 应用重大缺陷的批评者，尤其是在某些需要实时决策的 AI 用例中，您会如何回应？
Emrah: 这个问题可以通过边缘计算 (Edge Computing) 这种混合架构来解决。虽然边缘计算仍然在本地运行，但它利用云技术来缓解延迟问题。企业可以自主决定哪些组件在云端运行，哪些组件在边缘端运行。只要二者之间实现无缝集成，延迟问题就能降到最低。
### 云端环境为 AI 开发者带来的优势
正如我们此前讨论的，选择云端还是本地基础建设，通常取决于灵活性、可扩展性和成本效益的需求。然而，云端环境的选用也深受数据需求的影响。在处理海量数据（无论是公共还是私有数据）时，云技术至关重要。这是因为容器化和 Kubernetes 等工具能简化任务流程，使 AI 开发者能更专注于开发，而非数据管理和基础设施配置。云提供多重优势，使其成为 AI 开发人员更理想的工作环境。
## 作者简介
Samantha Duchscherer, 全球产品经理
Samantha 是 SmartFactory AI™ Productivity、Simulation AutoSched™ 和 Simulation AutoMod™的全球产品经理。在加入应用材料公司自动化产品事业部之前，她曾担任博世工业4.0项目经理，并曾任数据科学家一职。早期她还曾作为研究助理任职于橡树岭国家实验室地理信息科学与技术组。Samantha 持有田纳西大学诺克斯维尔分校数学硕士学位，以及北乔治亚大学达洛尼加分校数学学士学位。
Emrah Zarifoglu 博士，云与 AI/ML 研发负责人
Emrah带领团队为半导体制造商提供 AI/ML 解决方案及自动化软件产品的云转型服务。他是 SaaS 应用开发、云转型实践以及云计算优化与分析框架构建领域的先驱，拥有半导体制造、云分析和零售科学领域的多项专利，并在半导体排程与规划领域拥有丰富的研究经验。他的研究成果发表在 IEEE 和 INFORMS 等国际期刊，并在 IERC 和 INFORMS 等会议上进行过展示。他获得德克萨斯大学奥斯汀分校运筹学与工业工程博士学位，还拥有土耳其比尔肯特大学工业工程学士学位和硕士学位。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Establishing a blueprint to optimize productivity with advanced factory automation](https://appliedsmartfactory.com/semiconductor-blog/productivity/factory-automation/)
**Published:** September 21, 2023
**Author:** Michael Frenna, Global Product Manager, Workflow Automation and Factory Analytics
**Excerpt:** Envisioning where you are and how to get there to ease deployment, ensuring smart manufacturing.
**Content:**
Semiconductors play a pivotal role in our ever-evolving technology landscape in how and where modern electronics are used. From smartphones to advanced medical devices, semiconductors are the driving force behind innovation for consumers and businesses alike. Increased demand for higher performance and greater efficiency has introduced a higher level of complexity into the smart manufacturing process, leading chip manufacturers to adopt advanced automation in their factories.
### Leading the way to higher yields, quality improvements, time-to-market acceleration
This paradigm shift has transformed production processes. The urgency to optimize productivity and increase the demand for zero defects manufacturing is enabling factory innovators to achieve higher yields, significantly improve production quality, and increase time-to-market.
Our Applied SmartFactory team of automation technology experts continues to partner with leading semiconductor manufacturers around the world to help enable smart and reliable factory automation. Our customers rely on our team to figure out the best way to meet business goals and move toward full automation.
### SmartFactory Pillars Leading to Full Factory Automation
- **Decision Making:** Automation of complex decisions in the fab. These include operational decisions such as what to run next and when to run it. There is a high level of complexity in semiconductor fabs with vast run requirements for each step in the process.
- **Transport:** Automation manages the movement of materials within the fabrication facility. This includes transporting wafers between processing steps, storing them in clean environments, and ensuring timely delivery to various workstations.
- **Exception Handling:** Automated reaction to unexpected events in the factory and resolution of those events. This replaces labor intensive manual intervention for factory floor exceptions and limits delays to resolve these issues.
- **Learning:** Automation in the semiconductor industry isn’t limited to physical tasks. Data analytics and artificial intelligence are employed to monitor equipment performance, predict maintenance needs, and optimize production processes in real-time, minimizing downtime and improving efficiency.
There are several benefits to achieving full factory automation. Among these, manufacturers can realize enhanced efficiency by minimizing human errors, reducing cycle times, and increasing throughput. Automation enables round-the-clock production without compromising quality. There are also benefits in consistency and quality. Automated processes deliver consistent results, leading to fewer defects and higher-quality products. This is crucial in an industry where even a minuscule flaw can render a chip useless. As the demand for semiconductor products continues to grow, automation also allows manufacturers to easily scale up production without significant adjustments to their infrastructure. Another important benefit is in the long-term costs. While initial setup costs can be significant, automation leads to long-term cost savings through reduced labor expenses, improved yield rates, and efficient resource utilization.
### Overcoming challenges to deployment
Despite its advantages, the implementation of factory automation in the semiconductor industry comes with challenges. Integrating diverse technologies, preparing the factory for automation, staffing the appropriate personnel, hardware/software purchasing, and configuration can all be significant roadblocks to overcome. Overcoming these challenges can be daunting, even discouraging some sites from adopting higher levels of automation. The challenges of smart manufacturing aren’t insurmountable, however, and can be overcome if manufacturers have a clear vision and pathway to meet timelines and goals.
Working with customers, we have found it is easier for manufacturers to execute their full automation plans once they can define each step that needs to be achieved to reach their goal. First, organizations need to define where they are on their automation journey, then establish where they want to be, and finally identify the steps required to get there.
In helping them define where they are, we classify manufacturing organizations into three distinct categories: Manual, Semi-Auto, and Full Auto factories. Each category represents the level of factory automation deployed. Figure 1 shows the levels of factory automation.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-1.png) Figure 1: Identifies levels of factory automation
Once an organization has identified their level of automation, then they can figure out what is next as seen in figure 2.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-2.png)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-3.png) Figure 2: Steps to self-identify stages of automation
### Future outlook
Factory automation is reshaping the semiconductor industry, enabling manufacturers to meet the growing demand for implementing advanced electronics. By harnessing the power of robotics, AI, and data analytics, automation has elevated efficiency, quality, and scalability to unprecedented levels. As technology continues to evolve, the marriage of automation and semiconductor production improvements promises to drive innovation, shaping the future of smart manufacturing.
Learn more about the move to full automation: [https://appliedsmartfactory.com/semiconductor-blog/move-to-full-automation/](/semiconductor-blog/move-to-full-automation/)
## What’s Inside
- [ Improving yield, quality and time-to-market ](#index1)
- [ SmartFactory pillars ](#index2)
- [ Benefits of full automation ](#index3)
- [ Overcoming challenges to deployment ](#index4)
- [ Future outlook ](#index5)
- [ FAQs ](#index6)
Semiconductors play a pivotal role in our ever-evolving technology landscape in how and where modern electronics are used. From smartphones to advanced medical devices, semiconductors are the driving force behind innovation for consumers and businesses alike. Increased demand for higher performance and greater efficiency has introduced a higher level of complexity into the smart manufacturing process, leading chip manufacturers to adopt advanced automation in their factories.
### Improving yield, quality and time-to-market
This paradigm shift has transformed production processes. The urgency to optimize productivity and increase the demand for zero defects manufacturing is enabling factory innovators to achieve higher yields, significantly improve production quality, and increase time-to-market.
Our Applied SmartFactory team of automation technology experts continues to partner with leading semiconductor manufacturers around the world to help enable smart and reliable factory automation. Our customers rely on our team to figure out the best way to meet business goals and move toward full automation.
### SmartFactory Pillars
There are four SmartFactory pillars that lead to full factory automation: - **Decision Making:** Automation of complex decisions in the fab. These include operational decisions such as what to run next and when to run it. There is a high level of complexity in semiconductor fabs with vast run requirements for each step in the process.
- **Transport:** Automation manages the movement of materials within the fabrication facility. This includes transporting wafers between processing steps, storing them in clean environments, and ensuring timely delivery to various workstations.
- **Exception Handling:** Automated reaction to unexpected events in the factory and resolution of those events. This replaces labor intensive manual intervention for factory floor exceptions and limits delays to resolve these issues.
- **Learning:**Automation in the semiconductor industry isn’t limited to physical tasks. Data analytics and artificial intelligence are employed to monitor equipment performance, predict maintenance needs, and optimize production processes in real-time, minimizing downtime and improving efficiency.
### Benefits of Full Automation
There are several benefits to achieving full factory automation. Among these, manufacturers can realize enhanced efficiency by minimizing human errors, reducing cycle times, and increasing throughput. Automation enables round-the-clock production without compromising quality. There are also benefits in consistency and quality. Automated processes deliver consistent results, leading to fewer defects and higher-quality products. This is crucial in an industry where even a minuscule flaw can render a chip useless. As the demand for semiconductor products continues to grow, automation also allows manufacturers to easily scale up production without significant adjustments to their infrastructure. Another important benefit is in the long-term costs. While initial setup costs can be significant, automation leads to long-term cost savings through reduced labor expenses, improved yield rates, and efficient resource utilization.
### Overcoming challenges to deployment
Despite its advantages, the implementation of factory automation in the semiconductor industry comes with challenges. Integrating diverse technologies, preparing the factory for automation, staffing the appropriate personnel, hardware/software purchasing, and configuration can all be significant roadblocks to overcome. Overcoming these challenges can be daunting, even discouraging some sites from adopting higher levels of automation. The challenges of smart manufacturing aren’t insurmountable, however, and can be overcome if manufacturers have a clear vision and pathway to meet timelines and goals.
Working with customers, we have found it is easier for manufacturers to execute their full automation plans once they can define each step that needs to be achieved to reach their goal. First, organizations need to define where they are on their automation journey, then establish where they want to be, and finally identify the steps required to get there.
In helping them define where they are, we classify manufacturing organizations into three distinct categories: Manual, Semi-Auto, and Full Auto factories. Each category represents the level of factory automation deployed. Figure 1 shows the levels of factory automation.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-1.png) Figure 1: Identifies levels of factory automation
Once an organization has identified their level of automation, then they can figure out what is next as seen in figure 2.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-2.png) Figure 2: Steps to self-identify stages of automation
### Future outlook
Factory automation is reshaping the semiconductor industry, enabling manufacturers to meet the growing demand for implementing advanced electronics. By harnessing the power of robotics, AI, and data analytics, automation has elevated efficiency, quality, and scalability to unprecedented levels. As technology continues to evolve, the marriage of automation and semiconductor production improvements promises to drive innovation, shaping the future of smart manufacturing.
Learn more about the move to full automation: [https://appliedsmartfactory.com/semiconductor-blog/move-to-full-automation/](semiconductor-blog/move-to-full-automation/)
## FAQs
#### How does advanced automation benefit semiconductor manufacturers?
Advanced automation helps semiconductor manufacturers achieve higher yields, improve production quality, and accelerate time-to-market by optimizing productivity and reducing defects.
#### What are the key pillars of SmartFactory leading to full factory automation?
The pillars include Decision Making (automating complex decisions), Transport (managing material movement), Exception Handling (automating reactions to unexpected events), and Learning (utilizing data analytics and AI for real-time optimization).
#### What are the benefits of achieving full factory automation in the semiconductor industry?
Full factory automation offers enhanced efficiency, reduced human errors, shorter cycle times, increased throughput, consistent product quality, scalability, and long-term cost savings.
#### What challenges are associated with implementing factory automation in semiconductors, and how can they be overcome?
Challenges include integrating diverse technologies, preparing the factory, staffing, hardware/software procurement, and configuration. Clear vision, step-by-step planning, and self-identification of automation stages can help overcome these challenges.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [Are you ready to achieve new levels of real-time decision intelligence in your factory?](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
**Published:** May 29, 2023
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** New SmartFactory message bus – critical to enable advanced automated manufacturing
**Content:**
## What’s Inside
- [ Next generation message bus ](#index1)
- [ Pain points ](#index2)
- [ SmartFactory Message Bus Pulsar ](#index3)
- [ Conclusion ](#index4)
The SmartFactory Computer Integrated Manufacturing (CIM) solution allows manufacturers to define, control, automate, monitor, and record the entire semiconductor manufacturing process from front-end wafer fabrication through back-end assembly, test, and packaging. It does so through a portfolio of integrated software products that share information with each other via a common message bus that enables communication between CIM systems and applications.
At the heart of the CIM is the Manufacturing Execution System (MES), which is the master coordinator of processing throughout manufacturing. The MES is the key integration point with all other CIM systems for product as it moves through manufacturing, and the message bus is central to that integration, enabling communication between systems and applications. As manufacturers have moved from a mix of manual control and low levels of automated manufacturing toward higher levels (see figure 1), greater demand has been placed on the message bus to do more, faster. The existing messaging bus is limited in that it doesn’t provide the features required to achieve the real-time decision making necessary to advance automation to its highest levels.
### Next generation message bus
To meet market demand and alleviate customer pain points with the existing message bus, we have developed a next generation solution built with distributed messaging architecture. The new solution addresses the shortcomings of the existing messaging system and allows for future expansion and technology modernization.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/05/Technology-Maturity-–-Manufacturing-Automation-Levels.png) Figure 1: Technology Maturity – Manufacturing Automation Levels
### Pain Points
The message bus must enable real-time intelligence (managing real-time decision making and real-time data transfer) to achieve high and full levels of automated manufacturing. With the combination of real-time transfer of data and the ability to stream events, such as data from a tool or sensor, AI can analyze data, decide and take actions (as shown in figure 2). A message bus that is too slow in transferring data causes a delay that makes it no longer a real time view.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/05/how-the-message-bus-enables-real-time-decision-intelligence.jpg) Figure 2: How the Message Bus Enables Real-time Decision Intelligence
Scalability is also required to keep up with current market demands. There is so much data coming from each tool, every nanosecond, that there needs to be a very big pipeline for processing that data. The message bus needs to handle high message throughput, be scalable in the number of topics it can handle and accommodate rapid growth with low latency.
Customers also cite a need for multi-tenancy— low operating and maintenance costs, efficient use of resources and larger computing capacity. It’s also critical that a message bus operating at such a high level be durable, with guaranteed message delivery, zero data loss and failure recovery.
The other two pain points we sought to address were the need for geo-replication, the easy replication of message data between different regions and across different private or public clouds; and the need for a unified messaging and streaming platform for publishing and subscribing, storing and processing streams of data at scale and in real-time.
### SmartFactory Message Bus Pulsar
In creating a next generation message bus solution, we leveraged Pulsar, an open-source software, and integrated it with our SmartFactory CIM through proprietary Pulsar adapters. We conducted a study two years ago comparing Pulsar to other similar types of message bus systems and Pulsar greatly outperformed the competition in the key areas we needed to address.
Our two-part solution of Pulsar and SmartFactory Message Bus Pulsar Adapter was designed with the capability to resolve customer pain points as well as meet future needs. It brings five major technological advances to our CIM messaging capabilities:
- Multi-Tenancy: Pulsar was designed for deployment as a hosted service for private and public cloud with multi-tenancy architecture.
- Scalability: Pulsar provides seamless scalability out to over a million topics with very low publish and end-to-end latency.
- Durability: Pulsar uses a modern architecture (brokers/bookies) for optimal performance and resiliency. It provides guaranteed message delivery with persistent message storage.
- Unified Messaging Model: Pulsar generalizes the two messaging concepts of queuing and publish-subscribe through one unified messaging API, enabling more use cases.
- Geo-replication: Pulsar offers geo-replication as a first-class feature, allows
organizations to deploy Pulsar across different cloud providers and replicate data across multi-cloud without locking in proprietary cloud provider APIs.
### Conclusion
This robust modern message bus solution within a highly automated CIM solution will sustain future technology advancement inside the semiconductor factory. It will enable factory real-time decision intelligence and allow customers to improve process efficiency. Ultimately, the solution will empower digital transformation from a low level of automation to self-actuating automation.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released, Popular, Semi
---
### [AI 与云技术的集成（上篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-and-cloud-integration-part-1/)
**Published:** May 2, 2025
**Author:** Samantha Duchscherer and Emrah Zarifoglu
**Excerpt:** 随着 AI 部署规模不断扩大，云技术或将铺就未来发展之路。
**Content:**
[ 下篇：AI 和云技术的集成 ](/zh-hans/semiconductor-blog/al-ml-zh-hans/ai-and-cloud-integration-part-2/)
## 内容概览
- [ 云的定义 ](#index1)
- [ 私有云与公有云 ](#index2)
- [ 容器化及相关概念 ](#index3)
- [ 成本考量因素 ](#index4)
- [ 行业现状分析 ](#index5)
- [ 云与 AI 部署 ](#index6)
全球产品经理 Samantha Duchscherer 与云及 AI/ML 研发负责人 Emrah Zarifoglu，是致力于将 AI 技术应用于 SmartFactory AI 解决方案的自动化专家。在这篇分为两部分的系列访谈中，他们将探讨云在 AI 训练与部署中的关键作用。由于在当今技术环境中，“云”的概念存在广泛差异，他们首先讨论了什么是云，以及企业在向云迁移过程中所面临的决策考量。
Sam：我想探讨 AI 及其与云技术的集成，但我认为，首先要确保我对 “云” 的含义有一个透彻的理解。您如何定义 “云” ？它是否可以简单理解为 “一个装满服务器、无需逐台登录即可调用的数据中心” ？
Emrah: 从某种程度上说是的。能够动态高效地扩展资源而无需逐台登录，确实是云的一个重要特性。但它不仅仅是装满服务器的数据中心。 “云”更像是一个统称，这个术语涵盖了多种技术，这些技术提供可扩展且灵活的算力、存储和网络基础设施。
Sam: 据我所知，云服务有私有云与公有云等选择。您能解释一下两者之间的主要区别吗？一家企业应该如何决定使用哪一种呢？
Emrah: 两者的本质区别在于基础设施的归属权。公有云的基础设施由第三方持有，并向客户提供服务与资源。其技术标准化程度高，对技术经验较少的客户更为友好。如果没有特殊顾虑，公有云是很好的选择，很多企业对此感到满意。
不过，当涉及定制化需求或需要使用特定技术时，公有云可能会带来挑战。若需要灵活性技术时，容器化、可迁移的技术方案更为合适。我的建议是在本地部署私有云，这样就能通过容器化和 Kubernetes 来编排工作负载，根据实际需求进行配置你的工作。
只要确保云端与本地基础设施之间的通信畅通，选择私有云还是公有云更多是企业偏好的问题。关键考量在于：是希望自主掌控基础设施及承担相应责任，还是选择外包以专注于核心业务。最终决策应当基于工厂的具体需求和使用场景来定。
Sam：说到云，像容器化、Docker、Kubernetes 和 Helm 图表这些新术语该如何理解？您会如何系统阐述这些技术？
Emrah: 我们现在所理解的云，大多源自2000年代初的云计算革命，那时引入了作为物理机虚拟化代表的虚拟机技术。
容器本质上是一种轻量级的虚拟机，而容器化则是将应用程序及其依赖项打包成独立单元的方法。Docker、Kubernetes 和 Helm 图表都属于容器管理工具。
Docker 是最常见的容器化平台，通过自动化流程实现容器封装。在开发阶段就会用到容器化和 Docker 工具。
而 Kubernetes 和 Helm 图表则用于部署阶段的大规模管理。Kubernetes 本质上是管理容器化应用的编排工具，Helm 图表则是预配置的 Kubernetes 资源包。
Sam: 我很好奇，企业在决定云基础设施时是否有明确的评估标准？还是完全取决于具体情况和实际需求？
Emrah: 成本是关键考量因素。举例来说，如果企业已拥有剩余寿命5-10年的服务器基础设施，可能未来五年内都不愿为新技术追加投资。除非云解决方案在扩展性或灵活性等方面具有显著优势，否则不会轻易迁移。但最终还是取决于具体业务场景。
比如运行 GPU 密集型应用时，采用本地部署方案通常比云解决方案更经济，因为云端 GPU 运算成本极高。如果需要长期持续使用 GPU 资源，自建或租赁专用 GPU 数据中心的成本可能仅为云端的一半。这类情况常见于训练大预言模型 (LLM) 等 AI 公司，他们通常会自建或租用专用数据中心进行模型训练。
Sam: 最后，在结束这段简短但富有洞察力的对话，并为接下来的讨论做个铺垫——我很好奇您如何看待当前行业发展现状？我们更接近 “AI 无法独立实现” 的观点，还是处于 “AI 爆发已至，但云技术尚未就绪” 的阶段？
Emrah: 首先，我们需要明确 “AI 爆发” 的具体含义。在大型语言模型训练等领域取得了重大突破，但这些进展主要依赖 GPU 等现有技术的规模化应用，而这不一定与云技术直接相关。
当我们讨论 AI 训练技术的革命性变革（如 Transformer 架构的出现）时，其实是在既有模型理解上的演进。这导致对算力资源的巨大需求，而当前 GPU 供给正满足这一需求。从这个角度看，云并非瓶颈，真正关键的是 GPU 等底层技术。
不过，如果出现 AI 不再依赖 GPU 或采用新型计算工具的转折点，云就需要适配新技术。届时，我们可以整合全球互联资源来优化训练流程。
云可能需要发展的另一个领域是Kubernetes。虽然 Kubernetes 可与 GPU 协同工作，但对大规模 AI 训练的效率仍不理想。因此许多重要 AI 训练任务仍采用非 Kubernetes 部署方式。就这点而言，云技术确实需要进化，但在其他领域则是另一回事。
### 云与 AI 部署
无论是公有云还是私有云，云基础设施对需要处理海量数据的企业都至关重要。随着 AI 部署规模扩大，市场对算力 (包括 GPU) 的需求激增，这一趋势尤为明显。在下一篇博客中，我们将深入探讨云与 AI 技术之间的关系。
## 作者简介
Samantha Duchscherer, 全球产品经理
Samantha 是 SmartFactory AI™ Productivity、Simulation AutoSched™ 和 Simulation AutoMod™的全球产品经理。在加入应用材料公司自动化产品事业部之前，她曾担任博世工业4.0项目经理，并曾任数据科学家一职。早期她还曾作为研究助理任职于橡树岭国家实验室地理信息科学与技术组。Samantha 持有田纳西大学诺克斯维尔分校数学硕士学位，以及北乔治亚大学达洛尼加分校数学学士学位。
Emrah Zarifoglu 博士，云与 AI/ML 研发负责人
Emrah带领团队为半导体制造商提供 AI/ML 解决方案及自动化软件产品的云转型服务。他是 SaaS 应用开发、云转型实践以及云计算优化与分析框架构建领域的先驱，拥有半导体制造、云分析和零售科学领域的多项专利，并在半导体排程与规划领域拥有丰富的研究经验。他的研究成果发表在 IEEE 和 INFORMS 等国际期刊，并在 IERC 和 INFORMS 等会议上进行过展示。他获得德克萨斯大学奥斯汀分校运筹学与工业工程博士学位，还拥有土耳其比尔肯特大学工业工程学士学位和硕士学位。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Ready to improve operations, increase yields and drive profits?](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
**Published:** November 18, 2021
**Author:** Wei Xiaowei, ChinaAET.com
**Excerpt:** Rely on our integrated solutions to prioritize quality and reliability across every stage of the manufacturing process.
**Content:**
Rely on our integrated solutions to prioritize quality and reliability across every stage of the manufacturing process.
\[pdf-embedder url=”/wp-content/uploads/2021/11/Applied-SmartFactory-China-Article-Eng.pdf”\]
[ Download this PDF ](/wp-content/uploads/2021/11/Applied-SmartFactory-China-Article-Eng.pdf)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular, Semi
---
### [您准备好在您的工厂实现自动化程度更高的实时的智能决策吗？](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/message-bus/)
**Published:** October 25, 2023
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** 我们新推出的 SmartFactory message bus对于实现先进自动化至关重要
**Content:**
SmartFactory计算机集成制造 (CIM) 解决方案可以帮助制造商实现从前道晶圆制造到后道封装、测试和包装的过程中定义、控制、自动化、监测和记录整个半导体的制造过程。 该解决方案通过一系列集成软件组合来实现上述功能，这些产品通过一个共同的消息总线 (message bus) 实现 CIM 系统与应用程序之间的信息交互。
CIM 的核心是制造执行系统 (MES), 该系统是整个制造过程的总协调者。 MES系统贯穿整个生产制造过程，因此是产品在制造过程中与其他 CIM 系统集成的关键点，而消息总线是集成的中心，能够使系统与应用程序之间进行通信。 随着制造商从手动控制、低自动化程度转向高自动化程度（见图1），对消息总线也提出了更高的要求，要求它做得更多、速度更快。 现有的消息总线的不足之处在于它不具备实现实时决策所需的必要功能，因此无法将自动化程度提升到更高等级。
为了满足市场需求并帮助客户缓解现有消息总线中的痛点，我们开发了分布式消息架构的下一代解决方案。 新的解决方案解决了现有消息系统的缺陷，并对将来的扩展和现代化技术予以支持。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/05/Technology-Maturity-–-Manufacturing-Automation-Levels.png) 图1：技术成熟度——制造自动化水平
### 痛点
消息总线必须支持实时智能化(管理实时决策和实时数据传输)来支持所有的自动化等级。 结合实时数据传输与流事件（如来自设备或传感器的数据），AI (人工智能)可以分析数据、做出决策并采取行动（如图2所示）。 过慢的消息总线传输速度会导致数据延迟，无法获取实时视图。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/05/how-the-message-bus-enables-real-time-decision-intelligence.jpg) 图2：消息总线如何实现实时的智能决策
为满足当前市场需求，扩展性必不可少。 每个设备每纳秒都会产生大量数据，因此需要一个功能强大的管道来处理这些数据。 消息总线需要处理高吞吐量的信息，支持扩展多种主题，并能以低延迟适应数据的快速增长。
客户还提及了对于多分租的需求，其运营和维护成本较低，资源利用率高，且计算容量较大。 在此类高级别的消息总线系统中，可靠性至关重要，需要保证消息送达和数据零丢失，支持故障恢复。
我们试图解决的另外两大痛点，一是跨区域数据复制的需求，即在不同区域之间以及不同私有云或公共云之间轻松复制消息数据；二是对统一的消息传递和数据流处理平台的需求，可以大规模的实时发布、订阅、存储及处理数据流。
### SmartFactory Message Bus Pulsar
在开发下一代消息总线解决方案时，我们利用开源软件 Pulsar，并通过专有的 Pulsar 适配器将该软件与我们的 SmartFactory CIM 集成。 我们在两年前开展了一项研究，将 Pulsar 与其他类似的消息总线系统进行比较，发现 Pulsar 在我们所需的关键领域中表现出色，远远超过同类竞品。
我们的“ Pulsar 和 SmartFactory Message Bus Pulsar 适配器”解决方案的设计，旨在解决客户痛点并满足未来需求。 它为我们的 CIM 消息交互功能带来五项重大技术进步：
- 多租户：Pulsar 旨在用于部署具有多租户架构的私有云和公共云托管服务。
- 可扩展性：Pulsar 可实现超过一百万个主题的无缝扩展，减少发布延迟和端到端延迟。
- 持久性：Pulsar 采用现代化架构（代理程序/存储节点），以实现最佳性能和弹性。 它通过持久化的消息存储保证消息传递效果。
- 统一消息模型：Pulsar 通过统一的消息 API将排队队列和发布-订阅的概念统一封装，可支持更多用例。
- 跨区域数据复制：Pulsar 提供一流的跨区域数据复制功能，允许企业跨越不同的云供应商部署 Pulsar，并且在无需锁定专有云供应商 API 的情况下支持数据在多个云之间进行复制。
在高度自动化的 CIM 解决方案中，这个强大的现代化消息总线解决方案将确保半导体工厂能够适应未来的技术进步要求。 该解决方案将实现工厂实时决策的智能化，并提高客户的生产效率。 最终，该解决方案将推动实现从低自动化程度到自驱动自动化程度的数字化转型。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, Newly Released, Popular
---
### [MES系统是什么？
来自工厂车间的高效管理视角 (第 1 篇，共 5 篇)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
**Published:** January 13, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** MES 系统是工厂的运营骨干，但它的作用还远不止如此！
**Content:**
[ 第 2 篇：关于流程配置 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-2/)
### 第 1 篇 - 首要原则
MES 系统是任何工厂的运营骨干，在日常运营中进行配置、维护和持续使用需要付出很大的精力。但是，制造商想要的不仅仅是将 MES 系统认证挂在墙上，表明他们已经满足了行业质量标准。在这个五部分系列的首篇中，我们将 MES 系统重塑为能够帮助制造商**业务**更上一层楼的工具，不仅仅是运营方面，还能够加速作出影响业务的决策，并在问题出现之前提前发出警报。
### 文稿
MES 系统是什么？这是一个好问题。但更好的问题是：MES 代表什么？MES 是制造执行系统 (Manufacturing Execution System) 的缩写，但等等，这只是我的叫法。有些人称之为制造运营管理系统，或 MOM。还有人称之为计算机集成制造系统 (CIM)，还有人叫它制造管理系统 (MMS)。
是不是感到困惑？是的，有点。不过，不管你叫它什么，千万别叫它“MESS”，因为我们可不希望工厂里一团乱。那么，MES 系统究竟是什么？在本系列的5个视频中，我们将对 MES 系统进行深入探讨。
首先，我们需要回到最初的原则。在最高层面上，MES 系统的目的是促进产品在生产过程中的移动。更具体地说，就是定义、指导和记录工厂的活动。首先，我们需要规划工厂的工作。
需要在何时完成哪些工作？具体怎么做？在此过程中需要哪些资源，如设备、零件或化学品？这就是 MES 系统的工艺配置过程，定义了工厂生产任何产品所需的所有资源、材料和制程。接下来，我们需要指导工厂的工作，确保在正确的时间做正确的事情，并在此工艺中使用正确的资源。此外，我们需要准确记录在此过程中所做的事情。除其他事项外，这样做可以确保每个人对我们工厂中制造的产品已经完成的工作达成共识。
我们绝对不想错误地重复同样的工作，也不想无意中跳过一个必要的步骤。制造完成后，我们需要证明在正确的时间完成了正确的工作。能够显示完整的加工历史不仅对内部质量验证很重要，而且对于外部标准认证也很重要。客户通常也会要求我们满足他们自己的监管要求。
事实证明，MES 系统的大部分功能都是由 ISO 9001 质量管理标准的关键要求驱动的。ISO 9001 的三个基本概念是：说你要做什么，做你说过要做的事，并证明你做了你说过要做的事。MES 系统的主要目标是与这些概念明确一致。
但有人会说这还不够。要将所有这些工艺定义配置到 MES 系统需要花费大量精力。此外，要持续、准确地记录工厂在整个生产过程中为所有产品所做的工作，需要付出更多的努力。
这需要持续不断的努力，而不仅仅是一次性的配置。MES 系统需要投入大量精力，制造商希望从中获得更多，而不仅仅是一张挂在墙上的证书，以表明他们已经达到了 ISO 9001 标准。这远远不够。制造商希望 MES 系统能够帮助推动他们的业务向前发展。他们需要一个能帮助他们回答业务问题的系统。例如，我们是否由足够的能力来服务新的大客户？或者，为了防止失去一位现有客户，我们能否缩短生产时间，确保订单不再延迟交货？或者，我们能否如期完成本季度的生产目标？他们想要一个能够回答操作问题的系统。例如，下一步应该处理哪个批次？这是一个很难回答的问题。或者客户的订单能否按时完成？或者我们有哪些方案可以缩短生产周期？他们想要一个能提供线索的系统来回答与工艺相关的问题，如制程是否稳定？或者我们该如何提升良率？或者所有的缺陷来自哪里？制造商希望将 MES 系统生成的数据用于两个简单的目的。
提供可行的见解，加快做出影响业务的决策；对即将出现的问题提供预先警告，最好在问题出现之前加以解决。简而言之，制造执行系统的工作不仅仅是定义和跟踪制造过程。
它还关系到所生成的数据，以及如何利用这些数据来推动工厂内部的持续改进，并实现底线结果。当我们谈论 MES 系统的功能时，重要的不是这些功能是什么，而是为什么需要这些功能，以及它们如何帮助解决生产中的问题。从高层次的角度来看，MES 系统包含三个基本组成部分。
工艺流程定义是所有配置发生的地方，提前规划工厂的工作。您可以将批量跟踪称为 MES 系统的运行，其中工艺流程定义用于确保在正确的时间、使用正确的资源进行正确的处理，并且在此过程中所发生的一切都会被记录下来。
报告采用批次跟踪生成的数据并对其进行整理，以可操作的形式展示工厂绩效的不同方面。分析功能使批次跟踪数据的访问民主化，最终用户可以根据自己的需要对数据进行切分，并在请求自定义报告所需的一小部分时间内创造新的见解。在第 2 篇中，我们将了解 MES 系统中的工艺流程定义，在这里，工厂的工作会提前进行详细规划。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [Move to full automation](https://appliedsmartfactory.com/semiconductor-blog/productivity/move-to-full-automation/)
**Published:** October 18, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Maximize the full potential of your factory: improve quality, cycle time, and asset utilization.
**Content:**
Maximize the full potential of your factory: improve quality, cycle time, and asset utilization.
#### Transcript
Factory automation at all levels, such as planning, scheduling, factory equipment and control, they can help significantly in reducing the waste and consequently, they can improve the cycle time, the factory output, cost and customer delivery. The first step is detection and there are sophisticated and mature systems for detection.
Those include statistical process control and fault detection systems.
And so one of the things that we are doing with our customers is working to help them do this electronically and it is reducing their mean time to resolution on the problems that they identify.
This results in an ability to look at factory resources at a holistic basis, disruption, delays and cost associated with having to analyze and validate changes to the WIP management policies such as dispatching and scheduling and to build realistic what-if models for capacity planning scenarios.
Certain product life cycle, customers have to produce the quality products at the right place, at the right time and at the right profit margin.
That success comes down to the initiative and drive of the engineering teams at the site. The best companies are those that empower those engineers and give them the tools that they need. Automation systems really are an extremely critical part of that whole picture.
These are some of the ways that Applied Materials is investing in our customer’s success.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [专题采访|应用材料公司：SmartFactory™助力制造商提升生产过程的质量和可靠性](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-improve-operations-increase-yields-and-drive-profits/)
**Published:** December 13, 2021
**Author:** Wei Xiaowei, ChinaAET.com
**Excerpt:** 依靠我们的集成解决方案，在生产过程的每个阶段都优先考虑质量和可靠性。
**Content:**
【编者按】
“十四五”时期，是工业互联网结合5G、大数据、人工智能等新一代信息技术，加速推进制造业转型升级的关键阶段。工业互联网正在重塑制造业生态，使之呈现一种万象更新的气派。这一次，《电子技术应用》杂志社以“自动化巨头拥抱工业互联网时代”为主题，邀请到全球六家自动化巨头：ABB、艾默生、施耐德电气、西门子、罗克韦尔自动化、费斯托，以及全球两家电子制造龙头公司：应用材料公司、环旭电子，针对企业在工业互联网时代的转型问题邀请嘉宾发表观点，共话智能制造新篇章。
工业互联网时代，工业自动化程度的提升对产业转型升级、工业结构调整以及企业竞争力提升都具有重要的意义。在应用材料公司自动化产品部营销总监David Hanny看来，企业的自动化水平很大程度上取决于制造业的环境和亟待解决的挑战。
 应用材料公司自动化产品部营销总监 David Hanny | 图 源：应用材料公司
当下，半导体行业日新月异，提高工厂生产效率已成为刻不容缓的任务。作为全球半导体行业自动化软件、服务和设备的领军企业，应用材料公司开发的 Applied SmartFactory™是制造业中全面的自动化软件解决方案。Applied SmartFactory™解决方案通过提高制造流程的效率并大幅减少手动操作，旨在与工厂中的集成系统无缝协作，以改善运营状况，提高产量和利润。
 图 源：应用材料公司
应用材料公司提供多元化的SmartFactory产品，在市场中处于领先地位。其集成能力包括过程质量、工厂生产率、生产执行以及贯穿供应链的计划和调度。“我们通过全面的制造执行系统（MES）、全自动物料处理系统（AMHS）控制、实时调度和短间隔调度、规格一致性(SPC)、设备维护策略和故障监测以及实时配方调整和耐用品管理实现工厂的全自动。” David Hanny在接受专访时如是回答。
传统设备公司通常专注于产品的研发和推出，然而在应用材料公司，“服务”与产品同等重要。一直以来，应用材料公司不只以“满足客户需求”为标准，更多的还会考虑如何“帮助客户创新”。“事实证明，应用材料公司可以在90天内将非常复杂、资产密集型的工厂实现全自动状态。我们的技术支持团队将全天候为工厂发生的问题提供解决方案。业务连续性对我们的SmartFactory客户至关重要，因此我们为客户提供自动化路线图、升级和补丁服务，以保持生产平稳运行。” David Hanny说道。
同时，多元化的SmartFactory产品组合使应用材料公司能够为客户提供全方位的一站式服务。David Hanny表示，应用材料公司有一个庞大的部署专家团队，在他看来，单一供应商责任制对公司客户来说更具成本效益，既能够加快成功部署的速度，又可以随时为他们提供服务以适应其制造流程的发展。另外值得一提的是，应用材料公司提供的EngineeredWorks™解决方案是公司预先构建的自动化逻辑，可以为客户快速部署成熟的业务规则。
传统制造业迈向智能制造的大前提，就是数据的采集和传输。“制造商总是希望更快地传输数据。”David Hanny说，“这其中包括5G高效的数据传输，还包括对存储更多数据、更快处理数据以及收集工厂行为分析的需求。”随着其它先进技术日趋成熟，如云、大数据、更快速的处理器（GPU等）和消息总线技术，5G技术的应用成为市场主流。David Hanny告诉我们，应用材料公司致力于将这些技术集成到公司的SmartFactory产品组合中，为离散式制造企业和流程式制造企业提供解决方案。
 图 源：应用材料公司
工业互联网想要稳固发展，安全风险问题不容小觑。在David Hanny看来，当客户进行数据迁移时，安全性是一个巨大的挑战。要克服的第一个障碍就是弄清收益会在何时或者以何种方式大于风险，这就要求各公司制定风险缓解策略。应用材料公司一直与客户保持密切合作，以了解这些使用实例。“我们将从客户对数据转移到异地的风险顾虑出发，有针对性地制定和管理安全路线图。”他讲道。
最后，当谈及工业互联网目前面临的挑战时，David Hanny表示工业4.0不是目标，而是一个关键的赋能因素。“成熟的自动化智能非常重要，先进技术在提高生产速度的同时还创造了一个学习的环境（例如机器学习、深度学习等），这反过来又允许概率智能的结果变得可预测，并可以将这些结果应用到人工智能领域。运用赋能技术需要安全可信度和强大的系统数据完整性。但我们认为，目前来讲最大的挑战在于客户对于其制造工厂拥抱变革的意愿。”他说。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Popular
---
### [Ready to keep pace with productivity demands in the market?](https://appliedsmartfactory.com/semiconductor-blog/productivity/ready-to-keep-pace-with-productivity-demands-in-the-market/)
**Published:** October 18, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Learn how to shorten cycle time, manage bottlenecks and react in real-time using integrated productivity solutions.
**Content:**
Learn how to shorten cycle time, manage bottlenecks and react in real-time using integrated productivity solutions.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [MES系统是什么？
报表和分析实现持续改进（第 5 集，共 5 集）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
**Published:** January 13, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** MES 系统的报表和分析功能，帮助您回答问题和解决问题的工具。
**Content:**
### 第 5 集：报表 & 分析
虽然 MES 系统在定义、指导和记录工厂事件方面发挥着重要作用，但最大的回报在于 MES 系统在此过程中生成的数据以及如何使用这些数据来回答问题并解决制造商每天遇到的问题。 在本系列视频的最后1集中，我们来了解 MES 系统生成的数据如何用于报表和分析。
[ 第 4 集：关键数据和指标 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-4/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Bingeworthy, Semi
---
### [MES系统是什么？
驱动工厂运行的数据和指标（第 4 集，共 5 集）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
**Published:** January 13, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** MES 系统的关键数据和指标，以及制造商如何使用它们。
**Content:**
### 第 4 集：关键数据和指标
虽然流程定义对于协调工厂正在完成的工作很重要，但在处理过程中创建的数据同样重要（却经常被忽视）。 在该 5 集系列视频的第 4 集中，我们来研究一下 MES 系统生成的一些数据以及可以从中得出的工厂指标。 我们还讨论了制造商如何使用这些信息来改进运营并保持工厂平稳运行。
[ 第 3 集：批次追踪 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-3/)
[ 第 5 集：报表 & 分析 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-5/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Bingeworthy, Semi
---
### [MES系统是什么？
批次追踪：运行时的 MES（第 3 集，共 5 集）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
**Published:** January 13, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** 通过批次追踪实现所有生产部件的信息追踪。
**Content:**
### 第 3 集：批次追踪
批次追踪可以被认为是“运行时”的 MES 系统。 在该 5 集系列视频的第 3 集中，我们来了解批次追踪如何代表工艺流程中批次和工厂设备的交集。 我们还研究了为什么MES 系统对批次和设备在批次追踪中起到非常不同的作用。
[ 第2集：关于流程的定义 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-2/)
[ 第 4 集：关键数据和指标 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-4/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Bingeworthy, Semi
---
### [MES系统是什么？
关于流程配置的一切（第 2 集，共 5 集）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
**Published:** January 13, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** 深入了解 MES 系统的配置。
**Content:**
### 第2集：关于流程的定义
在我们的工厂中找到生产产品的最佳方式已经够难了，但要传达这样的信息以便使说明清晰、结果符合预期、过程可重复，这是一个完全不同的挑战！ 在该 5 集系列视频的第 2 集中，我们从概念上了解如何在 MES 系统中定义工艺流程。 我们还深入探讨了 MES 系统的配置以及它们如何在 MES 系统中相互关联并有可能被重复使用。
[ 第 1 集 - 首要原则 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-1/)
[ 第 3 集：批次追踪 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/mes-part-3/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Bingeworthy, Semi
---
### [What is an MES?
An aspirational view from the factory floor (Part 1/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-1/)
**Published:** July 8, 2022
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** The MES is the operational backbone of the factory. But it should be so much more!
**Content:**
[ Part 2: Process Configurations ](/blog/mes-part-2/)
### Part 1 – First Principles
The MES is the operational backbone of any factory…and it requires a LOT of effort to configure, maintain, and consistently use in day-to-day operations. But manufacturers want more from their MES than just a certificate to hang on the wall showing they’ve complied with an industry quality standard. In the first part of this five-part series, we reframe the MES as a tool that can help move a manufacturer’s **business** forward – not just operationally, but also to speed business-impacting decisions and provide advance warning of problems ahead.
### Transcript
What is an MES? That’s a good question, but a better question to start with is, what does MES stand for? MES stands for Manufacturing Execution System, but hang on, that’s just what I call it. Some people call it a Manufacturing Operations Management System, or MOM. Others call it a Computer Integrated Manufacturing System, or CIM, and yet others call it a Manufacturing Management System, or MMS.
Confusing? Yeah, a bit. Whatever you call it, though, just don’t call it a MESS, because, well, none of us wants a mess inside our factory. Okay, so what is an MES? In this five-part series, we’ll take an aspirational look at what the MES is all about.
To begin, we’ll need to go back to first principles. At the highest level, the purpose of an MES is to facilitate the movement of product through manufacturing. More specifically to define, direct, and document a factory’s activities. First, we need to plan the work of the factory.
What is it that needs to be done and when? How specifically does it need to be done? And what resources are needed along the way, like equipment or parts or chemicals? This is the configuration process for the MES, defining all the resources, materials, and processes needed to build whatever it is the factory is building. Next, we need to direct the work of the factory to ensure that the right thing is done at the right time, and the right resources are used in the process. And we also need to document exactly what’s been done along the way. Among other things, this ensures everyone is on the same page about the work that has already been done to the things we’re building in the factory.
We definitely don’t want to mistakenly do the same work twice, nor do we want to inadvertently skip a necessary step. After manufacturing is finished, we need to show that the right work was done at the right time. Being able to show complete processing history is important not only for the internal quality verification, but it’s also important for external standards certification and often required by customers to meet their own regulatory requirements.
As it turns out, much of the functionality of the MES is driven by key requirements of the ISO 9001 quality management standard. Three of the fundamental concepts of ISO 9001 are to say what you’re going to do, do what you said you’d do, and show that you did what you said you do. The major objectives of the MES align clearly with these concepts.
But some would say that’s not enough. It takes a lot of effort to configure an MES with all those process definitions. And it takes even more to consistently and accurately document the work that’s been done throughout the manufacturing process for everything the factory is building.
And that’s a continuous effort not just a one-time configuration. An MES requires a lot of effort and manufacturers want to get more out of it than just a certificate to hang on the wall to show they’ve complied with the ISO 9001 standard. That’s just not enough.
Manufacturers want an MES that helps move their business forward. They want a system that helps them answer business questions like do we have enough capacity for a big new customer? Or can we reduce manufacturing time to prevent losing an existing customer whose orders have been consistently late? Or are we on track to hit our production targets for the quarter? They want a system that answers operational questions like what lot should be processed next? Which is a surprisingly difficult question to answer. Or will the customer’s order be finished on time? Or what are our options to improve cycle time? And they want a system that gives clues to answer process-related questions like, is the process stable? Or what can we do to improve yield? Or where are all the defects coming from? Manufacturers want to use the data generated by their MES for two simple purposes.
To provide actionable insights that speed business impacting decisions. And to provide advance warning of problems that lay ahead, preferably so they can be addressed before they become problems. In short, the job of the MES isn’t just procedural to define and track manufacturing processing.
It’s also about the data that’s generated and how that data can be used to drive continuous improvement within the factory, as well as bottom line results. As we talk about the capabilities of an MES, the important takeaway is less about what those capabilities are and more about why they’re needed and how they help solve problems in manufacturing. From a high-level perspective, there are three basic pieces to an MES.
Process definition is where all the configurations happen, where the work of the factory is planned in advance. You could call lot tracking the runtime of the MES, where process definitions are used to ensure the right processing occurs at the right time using the right resources. And everything that happens is documented along the way.
Reporting takes the data that’s generated in lot tracking and organizes it, presenting it in a form that provides actionable insights about different aspects of factory performance. Analytics democratizes access to lot tracking data, allowing end users to slice and dice data according to their own needs and create new insights in a fraction of the time it would take to request a custom report. In part two, we’ll take a look at process definitions within the MES, where the work of the factory is planned in advance in exhaustive detail.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [Improve Productivity in AI and ML Solutions Development & Deployment](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/improve-productivity/)
**Published:** March 25, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Experience an integrated way to develop an AI/ML module using our SmartFactory productivity AI/ML platform
**Content:**
For semiconductor fab managers who are considering artificial intelligence (AI) and machine learning (ML) technologies, here are some questions to consider: What’s the lifecycle of developing an AI/ML module for your specific problem? What’s an efficient way of implementing an AI/ML module with your current legacy system and production environments using SmartFactory productivity products, such as AutoSched®, Activity Manager® and APF Formatter? Are you aware of an integrated solution approach that covers the entire lifecycle of developing AI/ML modules?
Manufacturers relying on our SmartFactory Productivity AI/ML platform, which supports the entire AI/ML model development lifecycle are shortening development lead-time by more than 30%
### Standard Steps in AI/ML Module Development Lifecycle
The AI/ML module development lifecycle consists of four standard steps: preparing and acquiring data, defining and calculating features, training and evaluating the ML model, and deploying and monitoring the model (see Figure 1).
- **Step 1. Data preparation and acquisition.** If the historical fab or tool data is ready, then acquiring and cleaning data occurs first. If the historical data is not enough to represent future changes, then augmenting data is required.
- **Step 2. Feature definition/calculation.** After the fab or tool data is ready, the fab operation team should define key problem features to solve, including tool statistics and job attributes. After team defines the features, they are calculated automatically.
- **Step 3. ML model training and evaluation.** What’s the best ML algorithm for the problem? Lasso regression? Xgboost? The team defines the appropriate algorithm based on the type of problem. During this step, the team repeats training and evaluation as needed, and tunes features and parameters/hyper-parameters based on results.
- **Step 4. Deployment and monitoring.** During this final step, the model is deployed to production but note that this deployment does not impact the performance of the current production system. Deployment is easy and efficient. After the team implements the model, real-time monitoring highlights model performance and production impact.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-lifecycle.jpg) Figure 1.
### Fab manufacturers improve efficiency using SmartFactory Productivity Al/ML Platform
Fab manufacturers using our SmartFactory Productivity AI/ML Platform components, such as AutoSched, APF Formatter, Activity Manager, and Solution UI, can integrate these modules directly into their production environment and avoid the need to develop separate python programs typically required for each step in the AI/ML development lifecycle. Integrating these modules, enables manufacturers to reduce costs and avoid the need for additional development resources (see Figure 2).
- **Step 1. When preparing and acquiring data:** For fab managers who are required to augment data for the new fab or tool data, **AutoSched** offers a good simulation product to generate augmented data for new fab behavior or tool statistics.
- **Step 2. When defining and calculating features:** After defining a full set of features, feature calculation should be automatic. If new features are required, then adding new ones and modifying existing features should be easy in the current environment. **Activity Manager** performs this automation, and feature calculation is easily implemented using **APF Formatter**.
- **Step 3. When performing ML model training and evaluation:** During this step, the initial model training and evaluation will be done on the general python development environment. This platform will also provide ready-to-use ML models for solving common factory productivity and supply chain problems. These models serve as “baseline” models that manufacturers can freely modify and reuse as needed. Additionally, **Solution UI** provides various evaluation interfaces to speed up model training and evaluation.
- **Step 4. When deploying and monitoring the ML model:** Deploying a ML model into production should not burden the current production system and is better off done in the familiar environment of current rule developers. If these developers use **APF Formatter** not only as their rule development tool, but also as their deployment tool (see Figure 3), then this is optimal. And rule developers can simply use the Python block to deploy an ML model to production—same as the current way. The **Solution UI** provides a dashboard and real time monitoring for model performance and fab impact monitoring.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-resources.jpg) Figure 2.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-resources-fig.png) Figure 3.
### Integrating the AI/ML development Lifecycle using our Solution UI
Figure 4 shows how our Solution UI integrates with the entire AI/ML module development lifecycle. Using our Solution UI, manufacturers can configure parameters, check evaluation analytics, and perform real-time monitoring after deployment. Additionally, manufactures can learn specific tasks to execute next and identify potential problems by checking various analytics. This integration with each step of the lifecycle occurs efficiently and helps expedite the entire development process time by providing valuable information for each step.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-lifecycle-solution-ui.jpg) Figure 4.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Bridging the talent gap](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/how-semiconductor-industry-bridging-talent-gap/)
**Published:** December 5, 2025
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** How the semiconductor industry is responding to a design workforce crisis
**Content:**
## What’s Inside
- [ Ramifications across the value chain ](#index1)
- [ Multi-pronged industry response ](#index2)
- [ Leveraging GenAI and turnkey platforms ](#index3)
- [ Global collaboration and talent mobility ](#index4)
- [ Looking forward ](#index5)
While the semiconductor industry has seen exponential growth, the talent needed to fuel it has not kept pace. In fact, the industry is projected to face a 35% shortfall in design workers by 2030, particularly in areas critical to innovation and automation. If realized, this talent gap could slow technological progress, leave major infrastructure investments underutilized, and reduce the global competitiveness of companies and nations alike. Organizations are already taking steps to address these challenges, in part by forming partnerships with governments, educational institutions, and local communities. They also are increasingly adopting turnkey automation solutions to optimize their operations without the need to increase their technical workforce.
### Ramifications across the value chain
The consequences of this growing workforce gap are already being felt across the semiconductor value chain. Among the impacts are: - Innovation bottlenecks: With fewer qualified design engineers, companies are struggling to keep pace with the rapid evolution of AI workloads, heterogeneous computing architectures, and advanced packaging technologies. Projects are being delayed or shelved, and the pace of innovation is slowing.
- Underutilized infrastructure: Governments and corporations have committed billions to build new fabs and R&D centers, but without the talent to run them, these facilities risk becoming underutilized assets.
- Escalating costs and competition: Companies are offering premium compensation, relocation packages, and aggressive recruiting strategies to secure scarce expertise. This competition is driving up costs and creating instability in workforce planning.
- Delayed automation and AI integration: Ironically, AI and automation promise to streamline semiconductor operations, but implementing these solutions requires deep domain knowledge in both software and hardware, which is increasingly hard to find.
### Multi-pronged industry response
To mitigate current shortfalls and grow the workforce needed to scale, the semiconductor industry is deploying a range of strategies. These efforts span government policy, corporate initiatives, academic partnerships, and technological innovation.
Among the most well-known government efforts are funding and policy supports in the U.S. and Europe. The CHIPS and Science Act allocated $52.7 billion for domestic manufacturing and R&D, with a significant portion earmarked for workforce development. Similarly, the EU Chips Act included €43 billion to boost local production and talent pipelines.
Less visible initiatives are workforce development and education partnerships. Semiconductor companies are partnering with universities and technical schools to create new curricula focused on semiconductor design, AI, and automation. These partnerships often include:
- Apprenticeships and co-op programs: Providing hands-on experience for students and accelerating their readiness for industry roles.
- Industry-sponsored bootcamps: Fast-tracking the training of new graduates in critical technical skills.
- Curriculum development: Ensuring that academic programs align with the evolving needs of semiconductor companies.
### Leveraging GenAI and turnkey platforms
Many semi manufacturers are turning to turnkey platforms and low-code/no-code solutions. These technologies allow teams to deploy automation and analytics with minimal custom development.
To free up skilled engineers for more strategic tasks, the SmartFactory portfolio offers a suite of turnkey solutions tailored for semiconductor automation. These solutions enable manufacturers to achieve lights-out operations where facilities can run autonomously with minimal human intervention, enhancing efficiency and uptime. Real-time dispatching capabilities allow for dynamic allocation of resources and rapid response to production needs, while predictive analytics empower teams to anticipate maintenance requirements and optimize performance. SmartFactory’s pre-integrated functionality and scalable architecture eliminates the need for extensive in-house coding or IT support. As a result, fabs can accelerate deployment, reduce operational overhead, and maintain long-term supportability—even with lean technical teams. By leveraging these turnkey solutions, manufacturers not only streamline operations but also enable engineers to focus on innovation and strategic initiatives.
Turnkey platforms such as this reduce upfront development costs and ongoing IT overhead, making them attractive in a market where R&D spending exceeds 20% of annual revenue for leading firms.
Generative AI is also being used to streamline recruitment, workforce planning, and even design workflows. AI-driven tools can identify skill gaps, recommend training, and assist in chip design—augmenting human capabilities and accelerating time-to-market.
### Global collaboration and talent mobility
Some companies are exploring cross-border talent mobility, relocating engineers to regions with better infrastructure or lower costs. Others are forming global design teams that operate virtually, leveraging cloud-based tools and collaborative platforms. This approach not only expands access to talent but also builds resilience against geopolitical disruptions. However, it requires robust data security, IP protection, and regulatory compliance frameworks.
### Looking forward
Through proactive solutions such as partnerships, turnkey automation, and global collaboration, semiconductor organizations are bridging the talent gap and unlocking new opportunities for growth and innovation.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [Improve yield learning and accelerate yield ramp](https://appliedsmartfactory.com/semiconductor-blog/quality/improve-yield-learning/)
**Published:** March 7, 2022
**Author:** SJ Wang
**Excerpt:** Building a quality ecosystem in your fab with pre-integrated SmartFactory Yield and Defect Management solutions
**Content:**
To achieve yields near 100%, semiconductor manufacturers must master a procedure called yield learning. This consists of removing one source of faults after another until an overwhelming number of manufactured units work according to specification. In today’s fabs, better data collection, integration, and visibility are all needed to improve yield learning and accelerate ramp.
This blog illustrates the value of yield and defect management solutions capable of integrating with other fab systems to provide faster yield learning. It highlights Applied’s recently released yield and defect management solutions and includes two examples that show how these systems control Q-time and identify sources of defects using better visualization.
### The Value of Collaboration
To help customers with their yield learning, the Automation Products Group at Applied Materials recently partnered with XDMTech Inc., a Taiwan-based company specializing in yield and defect management.
The results of this partnership are recently released SmartFactory Yield and Defect Management solutions built on the XDMTech Vidas and xDMS technologies. SmartFactory Yield Management is an integrated, fab-wide yield data management and analysis system. It helps engineers improve yield learning and accelerate yield ramp. The complementary product, SmartFactory Defect Management, reduces the need for unreliable manual defect classifications, and it also reduces yield loss, time to identify yield limiters, and manufacturing costs.
The availability of these solutions enhances Applied’s CIM portfolio and creates a one-stop shop to help manufacturers with their yield learning efforts.
### What Makes These Solutions Different?
SmartFactory Yield Management eliminates **80%** of the time and effort required to load and pre-align data. Additionally, historical data from yield management implementations at customer sites have shown early root cause identification of parametric uniformity issues, resulting in significant savings.
Key differentiators of the SmartFactory Yield and Defect Management include:
1. **Simplified Database**. Yield and defect management are the only solutions offering a simplified and scalable database structure for single source of truth and faster root cause analysis. The result is improved profitability through increased product portfolios and cost reductions.
2. **Statistical Analysis Tools**. Unlike many defect management solutions, which rely only on business intelligence (BI) tools, SmartFactory Defect Management provides additional statistical analysis tools and a workflow engine for automatically generating analysis reports.
3. **Better Integration**. SmartFactory Yield Management is the only solution integrated to metrology and other data for advanced statistical and defect correlation analysis. It’s also the only process quality solution built on a common platform with integration to other quality systems, including MES, FDC, SPC, EDC, and APC. Such integration is critical because it enables information sharing across components, providing analysis of various data sources in a fab, as well as proven multi-fab data integration and traceability capability.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/smartFactory-yield-and-defect-management-value.png) Figure 1. SmartFactory Yield and Defect Management value and key differentiators
### Example 1: The Value of Integration in Resolving Q-time Issues
One of the key advantages of SmartFactory Yield Management is it enables **information sharing** across all process control elements. To illustrate, a large 300mm fab in Asia faced many yield challenges associated with its Q-time violations. Q-time refers to the defined limit on the total time between two or more consecutive steps. Wafers exceeding this time limit may be scrapped or result in potential yield loss.
To reduce the risk of scrapped wafers or lower yield, lots must **spend less time in the loop** than the Q-time limit. With this fab’s current in-house system, it was very difficult to integrate with SmartFactory Fault Detection to quickly access reports for showing Q-time violations. Furthermore, the fab had no automatic reporting tools or methods in place to control Q-time, resulting in slow response times and inaccuracies.
Applied Materials was able to resolve these challenges by integrating SmartFactory Yield Management and SmartFactory Fault Detection. This enabled the fab to set up alarms to notify engineers of any Q-time violations, as well as automatically generate hourly reports to clearly show violation trends in Yield Management (see Figure 2). By using SmartFactory Fault Detection modeling and yield management functions **together**, the fab was able to control and monitor wafer-level Q-time, resulting in faster yield learning.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/with-smartFactory-yield-management.png) Figure 2. With SmartFactory Yield Management, fabs can detect Q-time violations in SmartFactory Fault Detection and show these violations in the yield management interface
### Example 2: Identifying Defects with Better Visualization Tools
Wafer fabrication requires many tools and process steps, so conducting tool and robot induced defect analysis is time consuming. For manufacturers, it’s very difficult to determine the root cause of defects without adequate visualization and classifications tools.
With typical defect management systems, manufacturers can only define wafer zones according to pre-defined zones, such as “upper” and “lower” or “center” and “edge.” However, with SmartFactory Defect Management, manufacturers can conduct **contact pin** analysis, which is enabled by importing equipment CAD drawings into the application’s library. This allows manufacturers to complete their analysis with the help of an overlay CAD drawing, an example of which is shown in Figure 3.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/with-smartFactory-defect-management.png) Figure 3. With SmartFactory Defect Management, manufacturers can identify robot induced defects using imported CAD drawing overlays
SmartFactory Defect Management tracks and classifies sources of defects using tools to help identify possible trends. Its geometric visualization superimposes geometric equipment components that may release particles on wafers.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/how-smartFactory-defect-management-checks-repeated-defects.png) Figure 4. This example illustrates how SmartFactory Defect Management checks repeated defects within a slot. If manufacturers find several repeated defects, then it typically means that those defects could be introduced by a reticle set, and a reticle might need to be cleaned or the equipment leveling condition may need to be checked
### Conclusion
What types of yield issues impact your factory performance? Defects? Parametrics? Both? Do you need to analyze data from multiple factories? With a simplified and scalable database structure for a single source of truth, SmartFactory Yield and Defect Management solutions offer proven multi-fab data integration and traceability capability for building a quality ecosystem in your fab.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [マスクショップにおけるMES：マスクショップの経済性の概要（第2回 / 全4回）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/semiconductor-mask-shop-economics-overview/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** ウェーハ工場が完璧なレチクルを必要とすることが、マスクショップの独自のビジネスモデルを生み出します。
**Content:**
[ 第一回：ラウンドvs スクエア ](/ja/semiconductor-blog/manufacturing-execution/round-vs-square-differences-between-wafer-and-reticle-manufacturing/)
[ 第三回：主要なマイルストーン ](/ja/semiconductor-blog/manufacturing-execution/photomask-manufacturing-key-milestones/)
## 本ブログの内容
- [ 完璧さのコスト ](#index1)
- [ サイクルタイム ](#index2)
- [ 製品構成 ](#index3)
- [ 予測困難な需要 ](#index4)
- [ MES（製造実行システム）の役割 ](#index5)
マスクショップは半導体業界において極めて重要な役割を担っています。
フォトマスク（レチクル）の製造は、少量生産かつ職人的な工程であり、注文される各レチクルは固有の仕様を持ち、それぞれ異なる製造課題を抱えています。
大量生産される半導体デバイスとは異なり、マスクショップにはスケールメリットが存在せず、同一製品を繰り返し製造することで得られるプロセス学習も期待できません。
この「一品一様性」と「顧客からの完璧な品質要求」が、マスクショップのビジネスモデルを独特かつ予測困難なものにしています。（マスク製造とウェーハ製造の主な違いについては、[第一回の記事](/ja/semiconductor-blog/manufacturing-execution-ja/round-vs-square-differences-between-wafer-and-reticle-manufacturing/)をご覧ください。）
### 完璧さのコスト
マスクショップとウエハファブの両方において、高額な製造装置とそれに伴う減価償却費が主要なコスト要因です。
しかし、ウエハファブでは統計的サンプリング手法を用いることで、多くのロットが計測や検査工程を省略でき、高品質を維持しつつコストを抑えることが可能です。
一方、マスクショップでは、すべてのレチクルに対して寸法検査や欠陥検査を実施する必要があり、これが設備投資と減価償却費を増加させる要因となっています。
製造中に欠陥が見つかったレチクルは修復可能な場合もありますが、これには専用の修理装置が必要であり、コストとサイクルタイムが増加します。
修復不可能なレチクルは廃棄され、新たな製造を開始する必要があります。
この場合、追加のマスクブランク（未加工のフォトマスク基板）が必要となり、一般的なマスクで数百ドル、高度なEUV（極端紫外線）レチクルでは数万ドルの材料費が発生します。
### サイクルタイム
製造サイクルタイムもマスクショップのコストを左右する重要な要素です。同じ技術ノードであっても、各レチクルの仕様が異なるため、サイクルタイムには大きなばらつきがあります。
マスクショップは、過去の類似プロセスの履歴に基づいて見積もりサイクルタイムを提示できますが、実際のサイクルタイムは「完璧なレチクル」が完成するまでの試行回数によって大きく変動します。納期を超過した場合、顧客への遅延を最小限に抑えるために、迅速な配送費用を負担する必要が生じることもあります。
重要顧客からの緊急オーダーに対応するため、マスクショップは複数の製造試行を並行して開始するというリスクを取ることがあります。この方法は、どれか1つが早期に完成することを期待するものですが、材料費が増加し、装置の処理能力を圧迫するため、全体のキャパシティが低下します。
さらに、サイクルタイムには、マスクデータの転送時間、製造前のデータ準備時間、製造後の出荷遅延など、マスクショップの管理外にある要因も影響します。これらもサイクルタイムを大幅に延ばす可能性があります。
### 製品の構成
キャパシティは、歩留まり、装置数、処理時間、プロセスステップ数、ウエハファブではウエハあたりのダイ数など、複数の要因によって決まります。これらのパラメータを最適化することで、キャパシティと収益の向上が可能です。ウエハファブでは、製造数が多く製品種類が少ないため、この最適化が有効に機能します。
しかし、マスクショップでは「製造数」よりも「製造するレチクルの種類」がキャパシティに大きく影響します。一般的に、レチクルには「バイナリ型」と「位相シフト型」の2種類があります。バイナリレチクルは構造が単純で、プロセスステップが少なく（位相シフト型の1/3以下）、歩留まりも高いため、製造効率が良好です。
一方、位相シフトレチクルは複雑で、製造ステップが多く、歩留まりも低いですが、販売価格はバイナリ型の最大20倍にもなります。このため、収益性を考慮すると、位相シフト型のみを製造した方が利益が大きくなる可能性があります。
### 予測困難な需要
しかし、実際の注文構成は、バイナリ型と位相シフト型がランダムに混在しており、キャパシティと収益に影響を与えます。このランダム性はサイクルタイムのばらつきを増加させ、リードタイムの予測を困難にします。予測不可能な需要は、マスクショップにおけるキャパシティとサイクルタイムの管理を非常に繊細なバランス調整にします。
### MES（製造実行システム）の役割
製造実行システム（MES）は、マスクショップが求める高いパフォーマンスと効率性を達成するために不可欠です。MESはリアルタイムのデータとインサイトを提供し、意思決定の質を向上させ、製造プロセスの効率的な管理を可能にします。
高度なMESを活用することで、スケジューリングや装置の稼働率を最適化し、サイクルタイムを短縮し、歩留まりと効率を改善することができます。これにより、マスクショップは顧客の高い品質と納期要求に応える能力を強化できます。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [マスクショップにおけるMESの運用：協働的アプローチ（全４回の第４回）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimizing-reticle-delivery-wafer-manufacturing-collaborative-strategies/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** レチクルの納品をファブのウェーハスケジュールに合わせることは、購買主導の任意の締切よりもはるかに効果的です。
**Content:**
[ 第三回：主要なマイルストーン ](/ja/semiconductor-blog/manufacturing-execution-ja/photomask-manufacturing-key-milestones/)
## 本記事の内容
## 本ブログの内容
- [ 協業（コラボレーション） ](#index1)
- [ マスクショップの要件 ](#index2)
- [ 新しいアプローチ？ ](#index3)
- [ 柔軟性の欠如によるコスト ](#index4)
- [ MESによる調整役としての機能 ](#index5)
半導体業界におけるレチクルのタイムリーな納品は、ウェーハ製造にとって極めて重要です。従来、ウェーハ工場とフォトマスクベンダーの関係は、購買部門によって顧客とサプライヤーの関係として構築されており、主に価格と契約で定められたリードタイムに基づく納期遵守に焦点が置かれていました。しかしこの方法では、ファブのニーズとマスクショップの契約上の義務が一致せず、ファブが必要とするタイミングよりも遅れてレチクルが納品されることが多く、緊急輸送のために高額な追加費用が発生することがあります。
### 協業
ウェーハファブとマスクショップの緊密な協力により、緊急輸送や追加コストを発生させることなく、ファブのウェーハスケジュールに沿ったレチクル納入を大幅に改善できます。このアプローチは、新製品製造を支えるフルレチクルセットに特に有効です。この協調の鍵は、リードロット（新製品の最初のロット）のスケジュールを満たすために、製造でレチクルが必要となる日付（「必要日」）を共有し理解することです。
過去の類似レチクルの経験に基づき、顧客側のレチクル設計チームは、新製品に必要な各レチクルの製造にどれくらいの時間がかかるかを把握しています。また、各レチクルの設計プロセスを、リードロットがそのレチクルを使用する工程に到達する前に、マスクショップが製造・納品できる十分な時間を確保するために、期限内に完了させる必要があることも理解しています。設計チームは、新製品計画チームが作成したウェーハスケジュールから逆算することで、自分たちの締切を予測できます。
### マスクショップの要件
マスクショップの視点では、新製品のプロセスフローにおける各レチクルについて、事前に把握すべき重要な日付が3つあります。1つ目は「テープアウト予定日」で、これは顧客からレチクルの注文と設計データを受領する日です。2つ目と3つ目は、ファブの必要日と、完成したレチクルをファブに出荷するために必要な時間です。
これらの日付を基に、マスクショップはレチクル製造に利用可能なリードタイムを算出し、a）必要なリソースを動員して、ファブの必要日に間に合うように製造・出荷する、または b）顧客が提示したリードタイムが不十分な場合は、早期に調整を依頼します。ウェーハのプロセススケジュールが固定されている場合、リードタイムを延ばすには、テープアウト日を前倒しする必要があります。
この共有理解は、新製品の最初のレチクルがテープアウトする前に構築される必要があり、綿密な計画調整を伴います。これにより、マスクショップとファブの双方がタイミングを把握し、ニーズを予測し、必要なリソースを動員し、スケジュール変更に対して積極的に調整できるようになり、ファブが製品開発のコミットメントを確実に果たせます。
### 新しいアプローチ？
では、なぜこれが新しいアプローチなのでしょうか？このレベルの調整は、工業用薬品、予備部品、クリーンルーム用品など、他の製造資材と同様に、ファブが必要なものを必要なときに確実に入手するための標準的な慣行であると考えられます。ファブのサプライヤーの納品遅延によって工場の稼働が遅れる、あるいは影響を受けることは、ほとんど考えられません。
このパラドックスを生むのは、レチクルの特異性です。レチクルには、在庫が減ったら補充できるようなバルク供給は存在しません。また、在庫が少なくなったときに利用できる予備在庫もありません。各レチクルはユニークで、必要なときにのみ注文され、仕様に基づいて製造されます。前述のとおり、ウェーハファブとフォトマスクベンダーの関係は、ファブの購買チームによる顧客・サプライヤー関係であり、主に価格と契約で定義された納期に焦点が当てられています。この契約上の取り決めでは、ファブの必要日を考慮することはできません。
しかし、ファブのタイミングニーズを考慮できないことは、新製品開発のコミットメントに影響を与える遅延を引き起こすことがよくあります。図1に示すチャートを見てください。これは、ウェーハファブとマスクショップの間で調整が行われている場合です。このケースでは、レチクルは必要日より前に一貫してファブに納品されています。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/08/figure-1.webp) 図1 – 新製品向けレチクル製造計画スケジュール
### 柔軟性の欠如によるコスト
しかし、ファブの実際のニーズを無視した、典型的な契約で定義されたリードタイムを使用した場合、何が起こるでしょうか。テープアウト日が一定で、リードロットのプロセス進行も変わらないと仮定すると、図2に示すように、ほぼすべてのレチクル納品が遅れることが予想されます。
これにより、リードロットは待機を余儀なくされ、その結果、新製品開発が遅延します。これは、ファブの顧客にとって重大な影響を及ぼし、その中でも特に、新製品による収益の遅れが挙げられます。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/08/figure-2.webp) 図2 – 契約ベースのレチクル製造計画スケジュール
協調的なアプローチによって、レチクル納品をウェーハ製造と整合させることで、納期遵守率を大幅に改善し、コストを削減し、マスクショップとファブの双方のパフォーマンスを向上させることができます。
調整されたスケジュールに基づいてレチクル製造の進捗を追跡することで、マスクショップは納期を守るために必要なリソースを適切に配分でき、潜在的な問題を事前に特定することが可能になります。
### MESによる調整役としての機能
製造実行システム（MES）は、マスクショップの納期遵守目標を推進する上で重要な役割を果たします。MESの計画・スケジューリング情報を統合することで、リアルタイムデータが生産状況、装置稼働状況、プロセス性能に関するインサイトを提供します。これにより、マスクショップは情報に基づいた意思決定を行い、問題を迅速に解決し、リソース配分を最適化できます。
さらに、MESはマスクショップとウェーハファブ間のコミュニケーションと調整を促進し、ファブのスケジュール変更を迅速にマスクショップの生産計画に反映させます。この動的な調整機能により、ファブのニーズとの整合性を維持し、レチクル納品の信頼性を向上させます。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [マスクショップにおけるMESの運用：フォトマスク製造における主要なマイルストーン（全４回の第３回）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/photomask-manufacturing-key-milestones/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** 重要なマイルストーンは、マスクショップと顧客それぞれの懸念事項に対応するよう設計されています。
**Content:**
[ 第二回：マスクショップの経済性 ](/ja/semiconductor-blog/manufacturing-execution-ja/semiconductor-mask-shop-economics-overview/)
[ 第四回：協働的アプローチ ](/ja/semiconductor-blog/manufacturing-execution-ja/optimizing-reticle-delivery-wafer-manufacturing-collaborative-strategies/)
## 本ブログの内容
- [ 注文中心型マイルストーン ](#index1)
- [ 製造中心型マイルストーン ](#index2)
- [ マイルストーンの監視と管理 ](#index3)
前回のブログ[「マスクショップの経済性の概要」](/zh-hans/semiconductor-blog/manufacturing-execution/semiconductor-mask-shop-economics-overview/)にて、レチクル製造における多くの課題、特に「常に完璧なレチクルを期日通りに製造・出荷すること」に焦点を当てて解説しました。
マスクショップ内では、レチクル製造の効率性と顧客の納期期待に応える能力を把握するために、重要なマイルストーンを追跡することが不可欠です。
最終的な目的は、工場の高い生産効率、製品品質、そして顧客満足度を確保することです。
マスクショップにおけるマイルストーンは、大きく「注文中心型」と「製造中心型」の2つに分類されます。
### 注文中心型マイルストーン
注文中心型マイルストーンは、顧客の視点に基づいて設計されています。
レチクルの製造プロセスは、顧客からの注文がマスクショップに届き、製造実行システム（MES）に「注文受領日（Order Received Date）」として記録されるところから始まります。
注文には、契約上の出荷期限（Contract Shipping Deadline）や顧客指定の出荷希望日（Requested Shipping Deadline）などの重要な日程が含まれており、これらは契約義務と、ウェーハファブでレチクルが必要となる具体的な日付（ウェーハ製造ニーズ日）に基づいた特別な顧客要求の両方に対応します。
また、製造仕様書も注文に添付されており、最終製品の品質を保証するための処理許容値や制限が記載されています。
注文とともに届く最も重要な情報は、レチクルパターンを定義する設計データです。
このレチクルデータファイルは数ギガバイトに及ぶことがあり、先端マスクでは1テラバイトを超える場合もあります。
商用の高速ネットワークを使用しても、マスクデータの転送には数時間かかることがあり、特に複数のデータ転送が同時に行われている場合はさらに時間がかかります。
データ転送が完了すると「注文開始日（Order Start Date）」が記録され、ここからサイクルタイムの計測が開始されます。顧客の視点では、この時点以降はすべてマスクショップの管理下にあると見なされます。
サイクルタイムは、完成したレチクルがマスクショップから出荷された「注文出荷日（Order Ship Date）」で終了します。
マスクショップと顧客の間では、サイクルタイムの定義について意見が分かれることがあります。顧客は、マスク注文を送信し、レチクルデータの転送を開始する「Go」ボタンを押した時点から、完成したレチクルが自社工場に届くまでをサイクルタイムと考えます。
しかし、マスクショップ側では、データ転送時間は顧客のレチクルデータサイズや通信帯域に依存するため、管理外とされます。また、UPSやFedExなどの配送業者による物理的な配送時間もマスクショップの管理外であり、サイクルタイムの範囲外と見なされます。
### 製造中心
製造中心型マイルストーンは、マスクショップの製造工程、つまりマスクショップが管理可能な範囲に焦点を当てています。
顧客からのデータ転送が完了すると、設計データは「フラクチャー（fracture）」と呼ばれる処理を受け、マスクショップのパターニング装置に適した形式に変換されます。このフラクチャー処理にも数時間かかることがあり、「フラクチャー開始日（Fracture Start Date）」と「フラクチャー終了日（Fracture End Date）」が記録されます。
フラクチャー処理が完了すると、変換されたデータは製造工程の最初の装置（レチクルパターンをマスクブランクに書き込む装置）に転送され、物理的な製造が開始されます。
ただし、すぐに処理が始まるわけではなく、先に受け付けた注文の処理が完了するまで待機する必要があります。この待機時間は「ライトキュー時間（Write Queue Time）」と呼ばれ、先端マスクの製造では数時間から数日かかることもあります。
最初の製造ステップが開始されると「製造開始日（Manufacturing Start Date）」が記録され、製造サイクルタイムの計測が開始されます。マスクショップの視点では、この時点以前の工程（データ転送、フラクチャー、ライトキュー）は管理外であり、製造効率の評価には含まれません。
各レチクルの製造ライフサイクルでは、「Track-In日」と「Track-Out日」が各工程の開始と終了を示し、「処理開始日（Processing Start Date）」と「処理完了日（Processing Complete Date）」が物理的な処理の開始と終了を記録します。
レチクルは前工程の完了を待つ必要があり、「Track-In日」と「処理開始日」の間がキュー時間です。各工程における平均キュー時間の変化は、特定の工程が「ボトルネック」になっている可能性を示すものであり、製造部門と技術部門による装置の稼働状況の監視と対応が求められます。
「製造開始日」から「製造完了日（Manufacturing Complete Date）」までが製造サイクルタイムであり、この平均時間はマスクショップの運用効率を示す重要な指標です。短いほど効率が高いとされます。
最後に、出荷期限（Shipping Deadline）は、契約上の出荷期限と顧客指定の出荷希望日のうち早い方が適用され、マスクショップの生産計画に基づいて、顧客の工場に到着するように出荷されます。「出荷日（Ship Date）」は、マスクが配送業者に引き渡された日として記録されます。
### マイルストーンの監視と管理
各レチクルのマイルストーンを監視・管理することで、安定した納期遵守が可能になります。また、これらのマイルストーンを長期的に監視することで、マスクショップ全体の健全性や製造効率の指標となり、改善のための重要な洞察が得られます。
製造実行システム（MES）は、製造プロセスに関するリアルタイムデータを提供し、各マイルストーンやその他の製造指標を正確に記録・可視化することで、プロセスフローの最適化、サイクルタイムの短縮、全体効率の向上を支援します。
さらに、MESはマスクショップ内の関係者間のコミュニケーションを促進し、全員が生産目標と納期に対して共通認識を持つことで、顧客期待に応える体制を構築します。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [マスクショップにおけるMES：ラウンドvs スクエア、ウェーハ vs レチクル（第1回 / 全4回）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/round-vs-square-differences-between-wafer-and-reticle-manufacturing/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** 2つの製造パラダイムにおける生産効率と品質の比較
**Content:**
[ 第二回：マスクショップの経済性 ](/ja/semiconductor-blog/manufacturing-execution-ja/semiconductor-mask-shop-economics-overview/)
## 本ブログの内容
- [ ラウンドワールド vs. スクエアワールド ](#index1)
- [ 歩留まり vs. 生産効率 ](#index2)
- [ プロセス効率 ](#index3)
- [ プロセス制御 ](#index4)
- [ MESの役割 ](#index5)
ウェーハ製造におけるレチクルの重要性を考えると、マスクショップは半導体業界にとって不可欠です。しかし、ウェーハファブとレチクル製造の間には、根本的な違い、さらには製造パラダイムそのものの違いがあります。両者は「ディスクリート製造」に分類されますが、共通点はそこまでです。
### ラウンドワールド vs. スクエアワールド
ウェーハ製造とレチクル製造のパラダイムの違いが最も顕著に現れるのは、製造対象の形状です。ウェーハは円形、レチクルは正方形。この特徴から、ウェーハ製造は「ラウンドワールド」、レチクル製造は「スクエアワールド」と呼ばれています。
ラウンドワールドから見たスクエアワールドは軽視されがちです。なぜなら、レチクル製造は数十工程で完了するのに対し、半導体デバイス製造は数百工程を要するからです。「レチクル製造なんて簡単だろう」という認識が生まれやすいのです。
さらに、製造量の違いもこの認識を助長します。ウェーハファブは大量生産で、最終的に市場に出回る膨大な数のチップを製造します。一方、マスクショップは「少量多品種生産」で、注文ごとに一意のレチクルを製造します。しかし、各レチクルは完璧でなければならず、そうでなければウェーハファブの歩留まりに直結します。ここにスクエアワールドの難しさがあります。
### 歩留まり vs. 生産効率
スクエアワールドの歩留まりは二値的です。レチクルは「良品」か「不良品」かのどちらかであり、不良なら廃棄し、完璧なレチクルができるまで再製造します。
一方、ラウンドワールドの歩留まりは連続的です。1枚のウェーハに数百のダイ、1ロットに25枚のウェーハがあり、数千のダイ候補があります。各ウェーハにいくつかの不良ダイがあっても、ロット全体の歩留まりは許容される場合があります。場合によっては、数枚のウェーハを廃棄してもロット全体で良好な歩留まりを確保できます。
ただし、ラウンドワールドでは歩留まりも重要ですが、それ以上に生産効率が重視されます。なぜなら、ウェーハファブの工程は数百から数千ステップに及び、サイクルタイムは数か月単位だからです。
一方、スクエアワールドでは状況が大きく異なります。工程は数十ステップ、サイクルタイムは数時間から数日です。ここでの焦点は「完璧なレチクルを納期通りに出荷すること」です。これが効率の指標であり、納期が最重要です。マスクショップは顧客の納期を守るために全力を尽くします。場合によっては、歩留まりが低いと予想されるレチクルを複数同時に製造するなど、あらゆる手段を講じます。
マスクショップの顧客であるウェーハファブにとって、レチクルの納期遅延は、生産能力の拡大や新製品の投入が遅れ、重大な金銭的損失につながる可能性があります。
### プロセス効率
大量生産により、ラウンドワールドではいくつかのプロセス効率化が可能です。すべてのウェーハやロットを計測・検査する必要はなく、これにより工場全体のスループットを大幅に向上できます。統計的サンプリング計画により、品質を統計的に高い確率で保証するために、どの程度のロットを計測・検査すべきかを定義できます。
しかし、スクエアワールドでは事情がまったく異なります。各レチクルは一意であり、製造量もウェーハファブに比べて少ないため、出荷前にすべてのレチクルに対して計測と検査を実施し、完璧であることを保証する必要があります。
この「100％計測・100％検査」の要件は、サイクルタイムの増加を意味するだけでなく、追加の計測・検査装置が必要となるため、マスクショップの基本的な経済性にも影響します。
### プロセス制御
プロセス制御も、ラウンドワールドとスクエアワールドで大きな違いがある領域です。大量生産において一貫したプロセス制御を維持するため、ラウンドワールドでは統計的工程管理（SPC）が広く活用されます。SPCは、計測や検査を通過した一部のウェーハの結果を監視し、工程が管理状態にあるか、逸脱しつつあるかを判断します。確立されたSPCルールにより、工程が制御内か、制御外に向かっているかを判定できます。これにより、ウェーハファブは歩留まり問題になる前に潜在的な工程異常を特定し、是正するための有効な早期警告の仕組みを得られます。
一方、スクエアワールドではSPCの有効性は限定的です。その理由は2つあります。第一に、マスクショップの製造量は比較的少なく、統計的に有効なサンプルサイズを確保できないこと。第二に、仮に製造量が統計的サンプルサイズの閾値を超えたとしても、各レチクルが一意であるため、同一条件での繰り返し製造を前提とする従来のSPCは適用できないことです。
### MESの役割
ウェーハ製造とレチクル製造。ラウンドワールドとスクエアワールド。それぞれ異なる製造パラダイムを持っています。しかし、どちらにおいても、高度な製造実行システム（MES）は、リアルタイムのデータとインサイトを提供し、生産効率と品質を向上させるうえで重要な役割を果たします。
マスクショップにおいて、MESは工場全体でのシームレスな情報共有の促進、リソース配分の最適化、遅延の最小化をすることで、納期の遵守を確実にします。また、詳細なプロセスフローの作成や、その最適化を構造的かつ管理された方法で支援することで、完璧なレチクルの効率的な製造にも貢献します。
MESは、マスクショップにおけるスループットの向上、品質改善、そして「完璧なレチクルを毎回納期通りに出荷する」というウェーハファブ顧客の期待に応えるための鍵となります。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [实时排程决策优化：数据与 AI 技术的融合应用（第4篇，共4篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-4/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 深入探索数字孪生：厘清认知误区，揭示数字孪生框架。
**Content:**
[ 第3篇：人工智能带来的挑战与机遇 ](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology-part-3/)
## 内容概览
- [ 定义解析 ](#index1)
- [ 数字孪生技术示例 ](#index2)
- [ 框架剖析 ](#index3)
- [ AI 融合潜能展望 ](#index4)
- [ 结论 ](#index5)
知名行业专家 James Moyne 与 Samantha Duchscherer 展开了一场精彩对话，深入探讨将人工智能 (AI) 等先进技术及额外信息整合到半导体行业排程与派工流程中的重要性。本系列文章共分四部分，重点涵盖数据价值与优势、AI 技术应用、人机协作等核心议题，同时深入分析当前面临的挑战，并针对数字孪生技术的角色提供独到见解。
在本系列的第四篇（也是最终篇）文章中，两位专家将探讨数字孪生的两个关键方面：数字孪生的核心定义与常见误解，以及数字孪生框架的概念。
#### 定义解析
在讨论伊始，我们笑称：人们对数字孪生的认知往往停留在在好莱坞电影中塑造的形象——比如《我，机器人》中出现的人类复制体。然而在半导体制造领域，数字孪生实则是一种强大的工具。James 为我们清晰地界定了本次讨论所聚焦的数字孪生类型：
James Moyne 解释了数字孪生在半导体制造中的含义。
#### 数字孪生技术示例
Sam: 如果数字孪生并不像好莱坞电影里描绘的那样，能否举一个更贴近现实的例子？
James: 当然可以。我们以灯泡灯丝的老化过程为例。你可能记得，这种灯泡在烧毁前会突然变亮。如果我们监测灯泡的温度或灯丝的亮度，并预测它何时会损坏，那么这个模型就可以作为数字孪生的一部分，用于预测故障。在这个例子中，我们不仅仅是模拟灯泡的理论故障，而是让模型与实际灯泡的数据保持同步。
Sam：这么说，数字孪生的一个关键特性就是它和现实实体的同步关系？
James: 没错，数字孪生会以时间敏感的方式与现实实体保持同步。这里需要特别注意：这种同步不一定是实时的，但必须是时间敏感的。以灯泡为例，我可能需要每秒同步一次模型数据，因为要在灯泡熄灭前60秒内做出预测。
但在半导体制造环境中，比如派工和排程场景中，我只需要在新晶圆到达时进行同步即可。
Sam：那么预测的可信度呢？我们上篇博客讨论过这个问题的重要性，在数字孪生中如何体现？
James: 数字孪生的关键输出是预测或检测（比如某物已损坏或即将损坏）。但正如我们上期讨论的，它还必须提供准确度信息。如果数字孪生告诉你灯泡灯丝即将损坏，它必须指明何时损坏。如果它给出的时间是60秒，误差为 ± 5秒，且概率为95%，你就可以据此订购替换灯泡。
#### 框架剖析
Sam：根据您对数字孪生的定义——这项技术在半导体制造领域似乎已存在很长时间？
James: 没错！比如很多人没意识到，早在上世纪90年代初，我们就已在半导体制造的批次间控制 (Run-to-Run Control) 中应用数字孪生。如今它已无处不在。该技术通过建立设备模型来预测最佳工艺配方，从而提升设备的质量或产能。批次间控制本质上就是一种基于模型的过程控制形式，同样使用了过程的数字孪生。
预测性维护也是一种数字孪生技术，已经存在了十余年，可预测某些故障机制——就像我们之前讨论的灯泡案例，它同样运用了数字孪生技术。虚拟量测 (Virtual Metrology) 是另一种数字孪生应用：虚拟量测孪生通过采集设备测量数据来预测计量值，并与实际计量工具同步以更新模型。
因此正如您所指出的，必须强调数字孪生技术已有很长的应用历史。如果我们腰围行业建立数字孪生框架，就必须设计能兼容所有这些现有应用的架构体系。
Sam: 如何构建这种集成化框架？
James: 本质上，我们需要同时实现数字孪生的复用和组合功能。
首先讨论复用。假设我们已建立应用材料公司刻蚀设备的数字孪生用于预测设备产能。虽然可以开发适用于所有刻蚀设备的通用模型，但其精度有限。若针对特定品牌或具体机台优化模型——比如确定需增加的传感器类型，或调整特定刻蚀设备的算法方程——就能获得更高精度的孪生模型。这正是我们所说的“泛化层级“ (generalization hierarchy) 。
另一关键则是数字孪生的组合，这对排程和派工尤为重要。假设我们已有以下数字孪生：基于规则的排程与派工模型，决定不同晶圆在不同设备的排程；基于批次间控制的孪生模型，评估目标设备加工质量；预测性维护孪生，预判设备故障及概率。若创建能聚合这些信息的排程派工孪生——综合设备生成质量、故障时间及概率数据——就能构建更优的排程派工方案。这就是数字孪生聚合 (aggregation of digital twins) 的价值。
Sam: 机器学习或人工智能一定能从数字孪生中获益，对吧？
James: 没错！通过开发通用接口和标准化的模型交互方式，我们就能打造一个支持多样化应用的平台。
数字孪生可以整合来自不同组件的机器学习能力，从而构建更高效的系统。
### 结论
数字孪生是与现实系统（如工艺流程、设备或产品）保持同步的目标导向的系统映射。这项技术已在诸多领域得到长期应用。在构建数字孪生框架时，必须充分考虑现有应用场景，同时明确定义数字孪生及其框架的技术规范。我们可以充分利用数字孪生的潜力来推动创新，优化各类应用——甚至包括人工智能。
返回[第一篇](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology/)，[第二篇](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology-part-2/)和[第三篇](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology-part-3/)。
## Moyne 博士简介
James Moyne 博士是密歇根大学副研究科学家，专注于通过增强排程与派工领域的数据整合来优化决策。他在预测性维护、基于模型的过程控制、虚拟计量及良率预测等前瞻性技术方面拥有丰富经验，同时致力于数字孪生与分析等智能制造概念的研发，推动微电子行业的智能制造落地。
Moyne 博士积极参与先进过程控制 (APC) 的推广工作，担任多个行业协会的联合主席及领导职务，包括 IMA-APC 委员会、国际设备与系统路线图 (IRDS) 工厂集成专题组、SEMI 信息与控制标准委员会，以及美国年度 APC-SM 会议。
凭借其深厚的专业知识与丰富的行业经验，Moyne 博士被公认为标准和技术领域的权威顾问，在智能制造、预测和大数据领域做出了重大贡献。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [应用材料公司更快实现自动化的途径 - 在 90 天内完成 MES 部署（第 1 部分，共 2 部分）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation/)
**Published:** August 12, 2022
**Author:** Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®
**Excerpt:** 在 90 天内部署 SmartFactory 300works™：依靠经验丰富的团队和经广泛验证的流程。
**Content:**
对于新建的半导体晶圆厂而言，即使在最佳情况下，探索工厂自动化的道路也颇为复杂。 例如，配置 MES、为复杂流程建模可能就让人不知所措。 如果制造商依赖于在半导体行业经验不足或几乎没有经验的 IT 公司来实施，那么会进一步加剧这种复杂性。 此外，晶圆厂常常会迟滞于他们的启动时间表，因为他们没有在流程中尽早提供安装和配置自动化软件系统所需的经验丰富的资源。
如果您负责为新建晶圆厂部署 MES，您是否遇到过类似的挑战？ 您是否达到了首批晶圆生产的里程碑？ 为了帮助新的 300mm 晶圆厂开启提高工厂自动化水平之旅，本篇博客重点介绍了成功部署 MES 的途径。 内容侧重于整个流程中的第一步：设置和基本准备工作，从而支持晶圆厂在 90 天内完成首批晶圆生产。
### 达到里程碑以保持竞争力
对于新的半导体制造商来说，关键是要选择满足以下条件的经验证的软件解决方案：(1) 满足全新晶圆厂上线的苛刻技术要求，以及 (2) 达成关键的生产里程碑，例如首次投片和爬坡量产。 不允许失去成功爬坡量产的里程碑。 由于这个限制条件，审慎地管理每个自动化软件系统的部署，使其满足爬坡量产的要求至关重要。 如图 1 所示，新建晶圆厂与自动化竞争的道路上，最为重要的里程碑包括： 1. **上线运行。** 设置和验证不需要自动化的最低工厂自动化能力，即可达成该里程碑。
2. **基本准备。** 为支持首批晶圆生产，晶圆厂必须实施基本的自动化，借助统计流程控制（SPC）、手动派工和跟踪以及设备自动化来运行自动化数据收集。
3. **提高良率、质量和产量。** 为了实现这些关键绩效指标，晶圆厂必须通过进一步集成先进过程控制（APC）、故障检测和分类（FDC）、派工和物料控制系统来提高其工厂的自动化能力。
4. **实现价值最大化。** 为了实现价值最大化，晶圆厂必须持续改进这些自动化功能（例如，根据排程输入信息和自动化 MES 场景来调整派工场景）。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/automation-competitiveness-milestone.png) 图1： 如何达成自动化竞争力里程碑
### 上线运行
让自动化软件上线运行，进行首批晶圆生产的关键任务包括： - 安装并配置 MES
- 实现设备自动化
- 与 SPC 集成
- 配置设备维护事宜
图 2 重点介绍了为成功实现爬坡量产，而必须配置和集成的关键软件系统。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/key-automation-software-systems.png) 图 2： 需要配置和集成以实现成功爬坡量产的关键自动化软件系统
### SmartFactory MES 300works™ 如何发挥作用？
借助 [SmartFactory 300works](/zh-hans/semiconductor/manufacturing-execution-solutions/300works-full-auto/)，能够实现基本自动化上线运行，这使操作员能够控制晶圆加工何时开始，无需手动入机台和出机台。 仅在 90 天内便能够支持开展首批晶圆生产。如何实现？ 通过我们经验证的部署方案，以及按步骤进行的系统性部署方法来完成。 凭借在半导体工厂 30 多年的“老练”经验，我们的部署团队擅长帮助晶圆厂按时上线运行，同时使用下列方法将部署风险降至最低（见图 3）： - 经验证的**部署方法**和**资源**。 借助 SmartFactory 300works，晶圆厂可以利用部署团队的丰富知识，了解有效方法和无效方法，例如，某些设备可能不适用于自动化，且需要特殊或独特的场景。 在这种情况下，团队可以与客户协商，使得设备适用于自动化。
- 预定义的流程**建模模板**。 此类模板能够作为批次和载具命名规则、设备流程等的知识库。
- 基于标准**制造场景**、经验证的部署模板。 例如，这能够帮助晶圆厂获取关于不同设备类型和运行场景的资源。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/formula-for-successful-mes-deployment.png) 图 3： 快速部署 MES 的关键
### 典型案例
下面将通过介绍一家新半导体前道制造商曾遇到前面所讨论的诸多挑战，说明经验证的部署方法的价值。 在开始进行自动化项目时，该公司刚开始仅有少数经验丰富的资源。 因此，难以得知需要完成什么样的自动化功能，何时需要，以及在晶圆厂生命周期的哪个阶段需要（请查看[拉近和实际生产的距离](/zh-hans/blog/bringing-production-reality-closer-to-target/?hilite=bringing+production+reality)）。 随着自动化水平的提高，从基本自动化进阶为先进自动化，担忧也随之而来。 具体来说，持续安装设备的过程需要自动化，需要测试制造场景，还需要涵盖不同的自动化集成。 这个挑战给制造商带来巨大压力。
为了帮助解决这些问题，应用材料公司服务团队提供了一套解决方案，即借助预先定义的建模模板和经过验证的部署方法。 该解决方案包括部署 [MES](/zh-hans/semiconductor/manufacturing-execution-solutions/300works-full-auto/)、[维护管理](/zh-hans/semiconductor/manufacturing-execution-solutions/maintenance-management/)、[派工](/zh-hans/semiconductor/productivity-solutions/dispatching-and-reporting/)、[FullAuto](/zh-hans/semiconductor/productivity-solutions/fullauto/)（含 [Activity Manager](/zh-hans/semiconductor/productivity-solutions/activity-manager/)™）、[材料控制](/zh-hans/semiconductor/manufacturing-execution-solutions/material-control/)、[run-to-run control](/zh-hans/semiconductor/process-quality-solutions/run-to-run-control/)、[故障检测](/zh-hans/semiconductor/process-quality-solutions/fault-detection/)以及[配方管理](/zh-hans/semiconductor/process-quality-solutions/recipe-management/)。 应用材料公司团队在 3 个月内完成了基本的准备工作，在 1 年内便完成了先进自动化，然后进行了几个月的后期调试以进一步优化。 由于这项部署的成功实施，客户得以朝着实现大批量生产的目标前进。
### 后续步骤
成功部署自动化软件系统，以支持手动操作和首批晶圆生产，这仅仅是迈向完全自动化晶圆厂之旅的第一步。 但是，在我们经验丰富的团队帮助下，客户获得了经验证的部署方式和建模模板以及适当的方法，所有这些为自动化之旅付出的努力是值得的。 在我们的下一篇博客中，我们将讨论这场旅途接下来的步骤，识别优先事项，从而为实现先进自动化做好准备工作。
[ 第2部分：全自动准备工作 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/faster-automation-part-2/)
想要了解更多关于 MES 系统部署方式的信息？
[ 联系我们 ](/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Popular
---
### [应用材料公司更快实现自动化的途径——全自动准备工作（第 2 部分，共 2 部分）](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/faster-automation-part-2/)
**Published:** January 16, 2023
**Author:** Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®
**Excerpt:** 推动 MES 300works™ 的部署，实现完全自动化的 CIM 系统。
**Content:**
对于半导体前道制造商来说，怀抱一个实现完全自动化的目标，对于带领一家具备自动化功能的晶圆厂走向成功来说，是一大关键因素。
然而，实现这一目标的途径却不尽相同，而且取决于多种因素。 在这一过程中，风险是普遍存在的，这取决于客户管理，以及双方在共谋自动化的路途中是否建立了正确的合作伙伴关系。
当客户在具备基本自动化功能的工厂成功实现首次 MES 系统部署，并且能够运行晶圆制程时，就应该建立一个专注于提高工厂自动化能力的愿景，目标是及时实现完全自动化。
### 什么是完全自动化？
*完全自动化*，也称全自动或关灯制造，使工厂能够自动处理产品，最大限度的减少人的参与1。 完全自动化使晶圆厂能够以最佳方式利用数据和计算机系统来提高生产效率。
下图说明了完全自动化的概念，展示了决策、物料运输、学习和对例外情况做出反应之间的流程和关系。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/07/figure-1-full-automation.png) 图1： 完全自动化的概念
我们认为，建立实现完全自动化的愿景对制造商很关键，而且要在生产过程中尽早建立这一愿景。 为什么呢？ 因为这样制造商就可以同时进行以下工作：(1) 部署各种工厂应用，以提高产品质量； (2) 通过更好地集成这些应用，使产量达到最大化。 要在合适的时间实现完全自动化，制造商必须推进以下活动（总结在图 2 中）： 1. **设计自动化场景。** 工厂有不同的需求和情况，必须得到有效管理，例如工厂空间限制和在线功能有限的设备。 这种情况需要工厂仔细考虑和设计自动化场景，因此他们要根据工厂自动化范围采用多种应用，如派工、先进制程控制、故障检测和分类、警报管理、配方管理等。
2. **优化运营能力。** 实施完全自动化的时间表涉及到根据工厂不断添加的工艺和设备来优化 MES 系统执行场景。 工厂会不断做出变动以提高产量，因此改变制造场景是不可避免的，包括设备类型因素，以及与自动化物料搬运系统集成等。 晶圆厂会持续发生变化，特别是在部署后，因为客户会不断地寻求提高运营效率。
3. **部署自动化功能。** 在设计和优化之后，工厂可以部署具有完全自动化场景的自动化功能，以实现无人干预或最大限度地减少人工干预。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/07/figure-2-automation-path.png) 图 2： 实现完全自动化的活动
### 案例：先进自动化的常见挑战
本篇博文的第 1 部分重点介绍了一家前道制造商在 90 天内完成基本自动化的案例。 该制造商想尽早实现先进自动化，但是，即使在这期间改善了他们的自动化功能，他们仍然担心如果忽略了某个领域的一个集成点，该如何避免因此引起的一连串的无数错误。 该制造商面临的其他挑战包括： - 在全公司范围内形成*完全自动化*的认识
- 缺乏或没有足够的自动化知识，特别是集成方面的知识
- 缺乏关于如何改进的专业知识
- 对如何确定自动化任务优先级的认知有限
### 为先进自动化建立伙伴关系
应用材料公司是可以为自动化问题提供咨询的优质合作伙伴，特别在执行相关的问题上提供见解：首先实施哪些集成、需要优先考虑哪些流程以避免周折等。 与应用材料公司合作，客户可以期待获得什么价值？ - 在 6 至 9 个月内完成全自动准备工作
- 实现从基本自动化到半自动化的爬坡量产，以提高良率和产出
- 按时为完全自动化做好准备
图 3 展示了应用材料公司 SmartFactory 解决方案的自动化功能如何与各种不同自动化水平相结合，以实现完全自动化功能。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/07/figure-3-automation-journey.png) 图 3：为从手动到 L2 级自动化之旅保驾护航的能力
应用材料公司经过验证的解决方案提供系统化和经验丰富的方法，部署 MES 系统以及自动化应用程序。 该解决方案基于多年来通过多次部署获得的专业知识。 应用材料公司 [SmartFactory MES 300works™](/zh-hans/semiconductor/manufacturing-execution-solutions/300works-full-auto/) 已经过市场验证，可在 90 天内实现快速部署 MES 系统。 该解决方案可使客户能够在一年内在其工厂中执行完全自动化的功能。
**参考文献**
\[1\] Krishnaswamy, S., Hanny, D., & Napiah, J. (n.d.). Challenges and strategies to achieve full automation in semiconductor assembly and test. Semi.org 2022 年 6 月 29 日检索，网址：
[ 第1部分：MES 系统部署 ](/zh-hans/semiconductor-blog/manufacturing-execution-zh-hans/faster-automation-part-1/)
想要了解更多关于 MES 系统部署方式的信息？
[ 联系我们 ](/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Factory automation is key to overcoming productivity challenges](https://appliedsmartfactory.com/semiconductor-blog/productivity/factory-automation-is-key-to-overcoming-productivity-challenges/)
**Published:** October 18, 2021
**Author:** Shekar Krishnaswamy
**Excerpt:** Shekar Krishnaswamy shares insights on how planning, scheduling, equipment control and overall operations improve cycle time, factory output, costs and customer delivery.
**Content:**
Shekar Krishnaswamy shares insights on how planning, scheduling, equipment control and overall operations improve cycle time, factory output, costs and customer delivery.
#### Transcript
The consumer electronics world as we know it, be it smartphones, tablets, digital cameras, memory sticks, it has shaken up many worlds, namely home electronics or people communication or social media, book publishing. It’s also shaken up the manufacturing world and in particular the semiconductor manufacturing world. One subset of the semiconductor manufacturing world is post-fab manufacturing, which traditionally is called Assembly and Test. Assembly and Test is undergoing rapid changes in many areas. First, the consumer electronics world is driving rapid changes in how semiconductor devices are packaged. Smartphones and tablet companies are always looking to how to make their gadgets smaller while adding more functionality.
This is changing the manufacturing floor and these changes apply to what kind of processes are being followed, what types of equipment is being used, how the factory is going to be laid out, what the operators can do, how they identify and fix problems. These are a few changes, but there are many more. Some of the newer processes are very, very sensitive to factors that affect product quality and need.
Secondly, these processes are being more and more outsourced to companies collectively called Outsourced Semiconductor Assembly and Test or OSATs. By 2020, according to some estimates, it’s expected that 65 to 75% of all semiconductor devices will be assembled and tested by OSATs. This means that the device manufacturers and the OSATs have to be in constant communication and coordinated with a lot of important factors such as production orders, capacities, order priorities, product quality, status of manufacturing, etc.
And any changes that happen have to be communicated in a very timely fashion. Thirdly, the combination of in-house manufacturing and outsourced manufacturing makes the supply chain very complex. One company has reported that just for a single product in one year, the product went through 15 successive supply chains.
This is really complex. Furthermore, the Semiconductor Assembly and Test is the last link in the supply chain before shipment to the customer. So any hiccups in the supply chain or any breakage in the supply chain has a big impact on customer delivery, satisfaction, and inventory.
In the past, many manufacturing and supply chain aspects were managed manually. But with the constant increase in complexity and the changes in the dynamics, these manual methods will no longer work. Manufacturing has to be agile and they have to anticipate this dynamic or otherwise customer satisfaction will be negatively impacted, waste will be generated, product inventories are going to be growing, and what this means is it’s going to negatively affect operating costs and profit.
Factory Automation at all levels such as planning, scheduling, factory equipment and control, they can help significantly in reducing the waste and consequently they can improve the cycle time, the factory output, cost, and customer delivery. With a proven track record for over 40 years in factory automation and fab manufacturing, Applied Materials is transforming the post-fab operations at many companies. Please visit our website at AppliedMaterials.com, click on the link for automation software for more information on how we can transform your company.
Thank you.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [Boosting productivity with advanced planning & scheduling solutions](https://appliedsmartfactory.com/semiconductor-blog/planning/boosting-productivity-with-advanced-planning-scheduling-solutions/)
**Published:** October 18, 2021
**Author:** Madhu Mamillapalli, Global Product Manager, Planning Solutions
**Excerpt:** New ways to streamline device production processes and wring higher productivity
**Content:**
New ways to streamline device production processes and wring higher productivity.
[pdf-embedder url=”/wp-content/uploads/2021/07/Advanced-Planning-Scheduling-Solutions.pdf”]
[ Download this PDF ](/wp-content/uploads/2021/07/Advanced-Planning-Scheduling-Solutions.pdf)
**Semiconductor Category:** Semiconductor Planning
**Semiconductor Tag:** Semi
---
### [实时排程决策优化：数据与 AI 技术的融合应用（第3篇，共4篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-3/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 洞察 AI 技术为半导体制造带来的挑战与机遇。
**Content:**
[ 第2篇：理解与定义人工智能与机器学习 ](/zh-hans/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-2/)
[ 第4篇：数字孪生框架全解析 ](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology-part-4/)
## 内容概览
- [ 循序渐进推进 AI 应用 ](#index1)
- [ 系统集成化 ](#index2)
- [ 可信度的量化评估 ](#index3)
- [ 深度探讨——我们准备好了吗？ ](#index4)
- [ 结论 ](#index5)
知名行业专家 James Moyne 与 Samantha Duchscherer 展开了一场精彩对话，深入探讨将人工智能 (AI) 等先进技术及额外信息整合到半导体行业排程与派工流程中的重要性。本系列文章共分四部分，重点涵盖数据价值与优势、AI 技术应用、人机协作等核心议题，同时深入分析当前面临的挑战，并针对数字孪生技术的角色提供独到见解。 在本系列的第三篇文章中，两位专家将探讨实施人工智能 (AI) 解决方案时面临的挑战，以及当这些智能系统学会主动寻求协助时所带来的机遇。
#### 循序渐进推进 AI 应用
人工智能 (AI) 与机器学习 (ML) 为半导体制造商提升[质量](/zh-hans/semiconductor/process-quality-solutions/)和[良率](/zh-hans/semiconductor-blog/al-ml-zh-hans/smartfactory-ai-transforming-manufacturing-productivity/)等关键绩效指标 (KPI) 带来了诸多机遇。然而必须认识到，要将 AI 技术整合到半导体制造运营中，初期仍需人工构建一个足够智能的系统，使其能够从正确的数据源提出恰当的问题。 正如 James 所指出的，AI 技术由于缺乏上下文理解能力且高度依赖数据质量，容易出现决策失误。 在数据质量方面，他有一句名言：“一条坏数据足以抵消十条好数据的价值。”关于上下文理解的重要性，他强调我们不能盲目地将数据输入系统—— AI 需要理解其推理逻辑的上下文背景。举例来说，系统或许能判断一个灯泡即将烧毁，但若能掌握该灯泡是安装在住宅楼还是写字楼、户外还是室内等附加背景信息，将极大提升其预测灯泡具体失效时间的能力。 他指出：“观察数据时，我们常常会发现它们会围绕不同的上下文参数形成明显的聚类特征，比如白天与夜间数据、户外与室内数据等。这些系统的表现很大程度上取决于你是否为其提供了足够的背景信息。“
#### 系统集成化
Sam：能否谈谈为什么在拥有高质量数据的同时，还需要完善的系统集成？
James: 要确保这些系统能做出准确预测，数据本身必须具备高质量——包括准确性、精确性、可用性和时效性。不仅如此，数据还需要完善的系统集成。如果各系统之间无法实现数据交互与协作，就会产生诸如数据时间同步等问题，导致预测变得极其困难。
以排程为例，我们可能关注的是晶圆到达某台设备这样的离散事件——这正是我们制定决策依据。每次该事件触发时，系统就会生成一个决策。但在缺陷检测层面，监测对象可能并非离散事件，而是秒级甚至毫秒级的时间间隔数据。这种情况下，我们该如何实现跨层级的时间数据同步？
Sam：当开始考虑数据集成时，数据共享是否会成为新的障碍？
James: 确实如此，这又是一大挑战，尤其是在需要与外部供应商协作时。比如预判设备故障需要提前订购零件的情况——虽然供应商不会与我们共享他们的核心数据，我们也不会泄露自身数据，但双方仍需交换必要信息来达成协作。更重要的是，我们还需要利用这些信息来优化预测模型。这就引出了关键问题：如何在保护知识产权 (IP) 的前提下实现数据流通，以确保分析、预测和检测等关键功能正常运行？
Sam：要实现稳健的 AI 解决方案，还需要哪些系统集成？既然 AI 可能出错，我们该如何降低其错误率呢？
James: 我们的研究发现，大预言模型 (LLM) 在挖掘人工维护记录、解析技术人员表述等方面表现优异。但这些输出必须经由（人类）领域专家进行事实核验，过滤错误信息后，才能将数据传递给排程和派工系统用于关键决策。 因此，一个稳健的解决方案需要设计一个能够主动寻求协助的交互界面——始终懂得何时需要向领域专家获取输入。在我看来，最智能的系统不是那些仅会输出答案的系统，而是清楚知晓何时需要求助的系统。这正是当前 AI 系统的局限所在：它们尚不具备人类 “这个领域我不懂，请指导我 “的认知能力。未来的 AI 应该更像学生——在接受训练时主动提问，在持续学习中完善认知。
#### 信任的量化评估
Sam：除了追求 AI/ML 预测的准确性外，我们该如何真正理解这些系统并信任其输出结果？
James: 这个问题至关重要。如果无法信任系统的建议，人们就难以有效运用分析、预测甚至检测功能。这种信任不仅关于建议本身的准确性，更在于能否理解其准确程度——我们称之为 “信任量化 “。举个或许有些沉重的例子：如果医生告诉我” 你会死 “， 我会认真对待，但若医生不给出时间范围，这个100%正确的诊断实际上毫无价值。即便医生说” 我100%确定你会死 “，这依然没有帮助。但如果他说” 我有62%的把握认为你会在未来两年内去世 “，这个量化评估就具备了可操作性。 对于预测系统而言，其预测能力的优劣并非关键因素，更重要的是我们必须全面掌握其预测质量的各项参数——包括预测的起始与终止时间范围，以及对应的置信水平。只要掌握这些元数据，就能将其与分析系统深度整合，从而显著优化排程与派工系统的运作效能。
#### 深度探讨——我们准备好了吗？
在与 James 的对话中，我们深入探讨了 AI 优化制造流程与产品的多种可能。但在展望这些优势之前，我们首先审视了制造业与成熟 AI 应用之间尚存的距离。
Sam 与 James 共同剖析了 AI 技术发展的多维路径
### 结论
AI/ML 为半导体制造商在质量管控、生产效率及[供应链](/zh-hans/semiconductor/supply-chain-solutions/)优化等领域开辟了广阔机遇，具体涵盖缺陷检测、预测性维护、虚拟量测、排程、派工以及产能规划等诸多环节。要充分释放这些技术的潜力，关键在于探索如何更有效地将人类领域专家的知识与 AI 系统相融合。
本系列最终篇中，James 将聚焦数字孪生技术，阐述其如何进一步推动 AI 在半导体制造中的应用演进。
返回[第一篇](/zh-hans/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/)和[第二篇](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology-part-2/)
## Moyne 博士简介
James Moyne 博士是密歇根大学副研究科学家，专注于通过增强排程与派工领域的数据整合来优化决策。他在预测性维护、基于模型的过程控制、虚拟计量及良率预测等前瞻性技术方面拥有丰富经验，同时致力于数字孪生与分析等智能制造概念的研发，推动微电子行业的智能制造落地。
Moyne 博士积极参与先进过程控制 (APC) 的推广工作，担任多个行业协会的联合主席及领导职务，包括 IMA-APC 委员会、国际设备与系统路线图 (IRDS) 工厂集成专题组、SEMI 信息与控制标准委员会，以及美国年度 APC-SM 会议。
凭借其深厚的专业知识与丰富的行业经验，Moyne 博士被公认为标准和技术领域的权威顾问，在智能制造、预测和大数据领域做出了重大贡献。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [优化半导体先进封装的 MES 智能系统](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/semiconductor-advanced-packaging/)
**Published:** October 16, 2024
**Author:** Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®
**Excerpt:** SmartFactory MES for ATP（面向先进封装的SmartFactory MES 系统）为扇出型 (Fan-Out) 工艺提供芯片追踪与溯源功能，并记录材料消耗历史。
**Content:**
## 内容概览
- [ 案例1：芯片追踪 ](#index1)
- [ 案例2：芯片溯源 ](#index2)
- [ 核心优势 ](#index3)
- [ 总结 ](#index4)
- [ 后续计划 ](#index5)
半导体先进封装已成为下一代设备开发的关键环节。随着技术不断进步，传统封装方式在尺寸、性能和功耗方面面临诸多限制。先进封装技术通过提供更强的功能性、更小的封装尺寸以提升性能、更低的功耗以及更高的可靠性，有效应对了这些挑战。
先进封装技术领域的最新创新尤为显著——特别是扇出型封装技术，因其多功能性和可扩展性优势而迅速获得业界青睐。扇出型封装能够在单个高性能封装中实现多种半导体器件的异质集成，例如处理器、传感器和高带宽内存 (HBM) 。该技术在涉及灵活性和外形尺寸方面具有显著优势，能够以更低成本实现功能更强、体积更小的模块。
在本篇博客中，我们将探讨两个关键案例，展示 MES 系统如何优化扇出型封装工艺流程。
### 案例1：芯片追踪
**问题描述**
在扇出型封装工艺中，当多个芯片被贴装到基板上，必须准确记录每个芯片的贴装位置和顺序（如下图 1 所示）。由于单个基板位置可能需要贴装多种不同类型的芯片，因此精确配置芯片贴装顺序至关重要。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure1-substrate-1.jpg) 图 1：基板上的多个芯片
SmartFactory MES for ATP 解决方案提供了一种灵活的建模方法，如图 2 所示，可在每个工艺步骤预先定义正确的芯片类型及其贴装顺序。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure2-setup-die-attach-spec.png) 图 2：芯片贴装规格定义设置界面
**核心优势**
SmartFactory MES for ATP 解决方案使客户能够建模和追踪芯片在基板上的贴装过程，通过防错机制提升运行效率。此外，预定义的自动化场景可显著减少设备自动化集成的工作量。
### 案例2：芯片溯源
**问题描述**
扇出工艺显著增加了确定每个基板位置芯片贴装数量和顺序的复杂度。必须建立溯源机制来追踪每个基板上消耗的芯片。同时需要配备灵活的报表工具，让用户能便捷查看和评估芯片消耗历史记录。
SmartFactory MES for ATP 解决方案可精准报告每个组装批次所消耗的芯片类型。如图 3 所示，用户可清晰查看组装批次消耗的芯片产品 ID。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure3-die-consume-info-1.png) 图 3：组装批次芯片消耗报表
用户还可按工单查看芯片消耗情况（见图 4 ），并能根据基板 ID 确定已消耗的芯片数量。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figur-4-die-lot-consume-report.png) 图 4：按工单显示的芯片消耗报表
### 核心优势
SmartFactory MES for ATP 解决方案提供全面的芯片溯源报告功能，涵盖消耗芯片数量及芯片 / 基板位置追踪。无论是 AI 处理器还是高带宽内存 (HBM) 模块，该解决方案都能提供详尽且精准的信息，显著缩短根本原因分析时间，并最大限度地降低生产问题的影响。
### 总结
SmartFactory MES for ATP 解决方案提供以下核心功能：
- 支持基板上芯片贴装位置与顺序的精准建模，从而实现扇出工艺全流程中对芯片、基板和批次的全面精准追溯。
- 提供材料消耗、工具耗材使用、制程谱系以及设备利用率和维护的完整追溯，确保制造过程中的可视性和可审计性。
- 追踪批次移动、监控生产进度，并确保在整个扇出工艺过程中 MES 系统与设备自动化之间的数据同步准确无误。
### 后续计划
半导体先进封装技术正经历革命性的快速发展。我们诚邀您共同探索这一技术领域，了解 SmartFactory MES for ATP 解决方案如何通过创新技术应对各种先进封装应用场景。在下一篇博客中，我们将深入解析该解决方案如何助力先进封装工厂实现全自动化生产。
想要了解更多关于应用材料公司 SmartFactory MES for ATP 的信息？点击[此处](/zh-hans/connect)与我们联系。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [数据与模型管理对部署人工智能的重要意义](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/model-management-for-deploying-ai/)
**Published:** November 28, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 构建可扩展的人工智能解决方案。
**Content:**
## 内容概览
- [ 数据采集与准备 ](#index1)
- [ 生产工作流程 ](#index2)
- [ 监控与维护 ](#index3)
- [ 结论 ](#index4)
随着人工智能 (AI) 需求的持续增长，各组织正在寻求有效扩展其 AI 项目的方法。其中，数据与模型管理的部署对 AI 解决方案的可扩展性具有决定性影响。本文重点阐述了构建一套高效的框架来管理与部署 AI 模型的重要意义，同时指出了实现该目标所需的核心要素。
了解强大框架如何协同管理端到端 AI 生命周期中最具挑战性的环节，包括代码标准化、追踪和维护 AI 模型。
### 数据采集与准备
构建 AI 模型最具挑战性的环节之一，将所需数据转换为可用的格式。要使 AI 模型成功做出有助于优化决策（或自主决策）的预测，训练模型的数据必须包含能体现半导体制造工厂复杂性的动态场景。这些场景包括由设备停机事件引起的在制品 (WIP) 波动、认证变更、生产瓶颈等。
在某些情况下可能会出现数据缺失，例如引入新型号部件或设备处于闲置状态时，都会导致数据断层。此时数据科学家可能需要采用其偏好的模拟方法来生成缺失数据，并进行临时性的特征计算。虽然这些定制化的 AI 部署任务能实现特定目标，但缺乏在整个工厂或组织范围内的可扩展性。
为实现更高效的扩展性，需要采用标准化的预配置特征管理系统来加速数据准备工作。这一核心概念将使晶圆厂或组织内任何尝试开发其他 AI 模型的用户都能访问特征库。先进的数据管理方法不仅应实现特征管理流程的自动化，允许用户整合自有知识产权 (IP)，更应提供多种预置数据验证检查、可直接使用的特征以及[模拟功能](/zh-hans/semiconductor-blog/al-ml-zh-hans/semiconductor-manufacturing/)——这些能力可在数据缺失时辅助特征生成。此外，在部署模型时还应提供非编码选项，用于标准化、执行和自动化这些任务。通过基于 Web 界面等非编码替代方案，更多不同背景的用户能够积极参与并贡献他们的专业知识到集中式的特征管理库，最终推动构建更高效的 AI 模型。
### 生产工作流程
没有人愿意在无保障的环境下工作。必须避免这样的情况：个人在自己的计算机上编写自定义代码，并将其独特模型直接部署到生产服务器，这种做法缺乏透明度和问责机制，可能导致预测结果不准确甚至完全失效，或对生产模型进行未授权修改——这些潜在后果凸显了在整个 AI 部署过程中实施强有力保障措施和维护问责制的重要性。将 AI 集成到生产环境绝非儿戏。因此，建立支持离线或初步场景测试、模型训练和模型分析的模型管理流程至关重要。通过这种方式，可以在不影响生产环境的前提下完成必要的模型验证方法审核。
在 AI 开发的初步阶段，选择本地部署 (on-prem) 或云端的灵活性至关重要。尤其是在处理大型数据集进行模型训练时，往往需要额外的计算能力支持。若采用本地部署方案，任务必须具备并行执行的能力，以充分利用并行计算的优势。此外，公共云、私有云或混合云选项的多样性也带来显著优势。在协调 AI 组件时提供这种模式选择，可确保终端用户能够有效满足其特定性能需求与数据要求。
当模型部署到生产环境时，系统不仅需要自动将历史版本存档，还应提供生产模型的完整信息档案。这些信息应当便于获取，并包含训练数据、模型参数、预测准确性等详细记录，以及明确的模型部署历史轨迹——包括负责推送到生产环境的个人或团队。实施用户权限限制同样至关重要。通过限制特定操作（如仅允许用户查看模型而无权部署至生产环境），可有效维持控制力与问责机制。这种认证、授权与模型生产工作流程的能力（涵盖初步测试、生产部署到归档的全周期）建立了信任，更重要的是，通过确保每个模型的完全透明度，提升了 AI 部署效率。
### 监控与维护
尽管人工智能引起了很多关注且拥有众多成功案例，[人们对其仍存有疑虑](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology-part-3/)。这很大程度上是因为人工智能有时看起来像一个“黑盒”。围绕人工智能的变革管理需要用户信任其输出，而获得这种信任的关键在于可解释性。一个稳健的模型管理实施方案应允许用户（领域专家）查看分析报告，这些报告需能深入解读模型性能及其背后的决策逻辑。例如，当机器学习模型持续显示批次周期时间预测值偏高时，用户应获得必要的工具和分析能力来调查根本原因。借助这些工具，他们可能会发现预测值偏高是由于特定工艺步骤存在在制品 (WIP) 积压，而调整特定的排程规则将有助于解决这一问题。
部署 AI 的另一项挑战在于维持其 7×24 小时持续运行环境。随着时间的推移，数据分布难免发生变化——可能由于新型号部件的引入，或设备随使用年限偏离原有性能特征。通过实施自动再训练方法，可确保模型在任何数据变化下都能保持最佳性能水平。理想的模型管理界面应允许用户无需编码即可设置自动训练触发器。这些触发器可基于时间间隔，例如每周更新，也可基于条件触发，例如当特征发生漂移或模型准确率下降时，启动再训练。
另一层面的维护涉及模型部署后的功能增强。例如当工业工程师认为某个质量特征可提升模型准确性时，采用用户友好的基于 Web 界面的生产模型管理工作流，将赋能非数据科学家背景的人员有效参与 AI 模型优化。这种界面通过让数据科学家能够专注于解决下一个具有商业价值的 AI 应用场景，而不被模型维护或优化工作所困扰，从而提升了可扩展性。
最后一个维护痛点在于必须管理与操作多个不同的系统。通过将 AI 数据和模型管理工作流集成至工厂已验证且熟悉的现有产品体系，可显著提升 AI 扩展效率。这种做法无需额外采用、集成和学习新软件，通过与现有基础设施的无缝集成，不仅能简化流程，更能加速 AI 实施效率。
### 结论
实施完善的数据与模型管理方法对有效扩展 AI 计划至关重要。强大的解决方案能够协调 AI 模型的高效管理与部署，赋能工程师流畅地与 AI 系统交互，并克服特定的数据与建模挑战。这种端到端 AI 运营流程的简化与自动化，将使组织获得显著的竞争优势。
探索我们如何通过协调数据与模型管理，为可扩展的[ AI 生产效率解决方案](/zh-hans/semiconductor-blog/al-ml-zh-hans/smartfactory-ai-transforming-manufacturing-productivity/)带来制造革命！
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [实时排程决策优化：数据与 AI 技术的融合应用（第2篇，共4篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-2/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 理解与定义人工智能 (AI) 与机器学习 (ML) 。
**Content:**
[ 第1篇：数据在生产效率与质量中的作用 ](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology/)
[ 第3篇：人工智能带来的挑战与机遇 ](/zh-hans/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-3/)
## 内容概览
- [ 人工智能与机器学习 ](#index1)
- [ 人工智能的不同层级 ](#index2)
- [ 探讨与分析 ](#index3)
- [ 案例研究：聊天机器人与半导体行业应用 ](#index4)
- [ 结论 ](#index5)
知名行业专家 James Moyne 与 Samantha Duchscherer 展开了一场精彩对话，深入探讨将人工智能 (AI) 等先进技术及额外信息整合到半导体行业排程与派工流程中的重要性。本系列文章共分四部分，重点涵盖数据价值与优势、AI 技术应用、人机协作等核心议题，同时深入分析当前面临的挑战，并针对数字孪生技术的角色提供独到见解。 在本系列的第二篇文章中，两位专家将重点探讨机器学习 (ML) 与人工智能 (AI) 的定义。文章将通过具体示例阐明二者的区别与联系。
#### 人工智能与机器学习
人工智能 (AI) 与机器学习 (ML) 的界限有时较为模糊，因为目前尚无一个被普遍认可的明确定义能将二者完全区分。不过，一般来说，人工智能是一个更广泛的领域，指通过创建智能系统来执行需要类人智能的任务，其涵盖包括机器学习在内的多种技术方法。而机器学习是人工智能的一个特定分支，专注于使机器能够从数据中学习，并基于学习结果做出预测或决策。机器学习算法通过识别数据中的模式和关联联系来持续提升性能，而无需依赖明确的程序指令。尽管人工智能与机器学习密切相关，但人工智能的范畴远不止于机器学习，还包含自然语言处理、计算机视觉和专家系统等其他技术。二者之间的界限具有流动性，机器学习通常被视为人工智能的核心组成部分。
#### 人工智能的不同层级
人工智能可分为多个层级，每个层级都具有其特定的应用范围和能力：
- 细粒度人工智能 (Granular AI)：在既定边界或参数范围内运作，通过机器学习算法在已知领域内做出精确预测或决策。它能填补数据点之间的空白，从而提供对系统行为更细致的理解。
- 探索型人工智能 (Exploratory AI)：突破已知边界，探索现有模型可能不适用的未知领域。它整合来自多源的外部知识和数据，以获得对复杂问题更全面的认知。
- 通用人工智能 (General AI 或 AGI)：代表人工智能发展的最高层级，它能模拟类人智能（包括推理、问题解决和适应能力），对环境具有全面认知，并可适应广泛的任务需求。
#### 探讨与分析
在下面的视频中，我和 James 首先就机器学习与人工智能的区别展开了讨论。
在这段短视频中，Sam 和 James 深入探讨了人工智能与机器学习的复杂技术细节
#### 案例研究：聊天机器人与半导体行业应用
在深入理解人工智能和机器学习之后，我们将注意力转向实际应用案例的探究：
Sam: 我们以大家都熟悉的聊天机器人为例来讨论吧。聊天机器人在 AI 和 ML 的范畴中属于哪一类呢？
James: 可以说聊天机器人并不算真正的 AI。比如它在帮我生成简历时，并没有创造出新内容，只是挖掘数据并告诉你： “基于所有这些信息，我通过概率计算给出我认为正确的结果。” 但从另一个角度看，它确实是在海量信息中建立关联，这又符合 AI 的特征。说到底，目前并没有一个明确的界定标准。不过在我看来，聊天机器人本质上更像是一个贝叶斯推理引擎。
Sam: 再举个半导体的例子——如果基于两年的历史数据开发算法来[预测批次生产周期](/zh-hans/semiconductor-blog/al-ml-zh-hans/prediction-accuracy/)，这应该属于机器学习范畴，对吧？
James: 没错！这个例子的关键在于：你始终在已有经验的领域内，只是通过补充更多数据让机器学习能够建立预测模型。
Sam: 那么开发一个[强化学习](/zh-hans/semiconductor-blog/productivity-zh-hans/advantages-of-reinforcement-learning/)模型，用来为晶圆厂可能发生的未知事件寻找最佳派工参数呢？这个例子应该归为哪一类？
James: 我认为这仍然属于机器学习范畴——虽然肯定有人会说 “不，这已经是人工智能了。” 不过，当面对从未发生过的事件时，我可能会咨询专家、查阅资料，来识别这类故障的特征及其风险与收益。当我们基于这些新引入的数据（无论是真实还是模拟数据）构建算法时，这才开始触及真正的智能层面。
Sam: 那么在这个语境下，您如何定义 “智能” ？
James: 这是一个从纯人工智能到纯人类智能的连续光谱。长远来看，我们需要的是人类与 AI 的完全融合——即便是 AI 系统也需要某种形式的人类制衡。人类与人工智能的交互必须变得更加异步化。比如说，人类应该能够在获得并验证信息后立即为 AI 系统提供智能（例如无需系统提示）。反过来，AI 系统也应该知道何时以及如何向人类寻求帮助。 对此我有一个说法：“不让任何知识掉队。”
### 结论
机器学习与人工智能同属实现相似功能的技术谱系，这往往令人难以区分实际应用的究竟是哪一种技术。归根结底，人工智能与机器学习的界定会因应用场景和观察视角而有所不同。这两个领域都在持续演进，随着新技术和新方法的出现，这两者之间的界限可能会变得更加微妙。
在接下来的篇章中，我们将深入讨论在排程与派工框架中应用 AI 和 ML 技术所面临的挑战与潜在收益。
[返回第一篇](/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology/)
## Moyne 博士简介
James Moyne 博士是密歇根大学副研究科学家，专注于通过增强排程与派工领域的数据整合来优化决策。他在预测性维护、基于模型的过程控制、虚拟计量及良率预测等前瞻性技术方面拥有丰富经验，同时致力于数字孪生与分析等智能制造概念的研发，推动微电子行业的智能制造落地。
Moyne 博士积极参与先进过程控制 (APC) 的推广工作，担任多个行业协会的联合主席及领导职务，包括 IMA-APC 委员会、国际设备与系统路线图 (IRDS) 工厂集成专题组、SEMI 信息与控制标准委员会，以及美国年度 APC-SM 会议。
凭借其深厚的专业知识与丰富的行业经验，Moyne 博士被公认为标准和技术领域的权威顾问，在智能制造、预测和大数据领域做出了重大贡献。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [SmartFactoryによるユニークなMES統合機能](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** これからDan Meier氏は、SmartFactory MES の突出した統合機能について説明します。貴社の生産オペレーションを再構築できるユニークなソリューションについてぜひ読んでみてください。
**Content:**
#### 字幕（全文）
Dan Meierです。アプライドマテリアルズにて MES システム戦略ディレクターを務めています。MES システムとは 「製造実行システム」の略称です。
MES システムは製造ソフトウェアの中核的なハブとして、製造プロセス全体に一貫して関わっています。アプライドマテリアルズの SmartFactory ソリューションは、この分野で独自の強みを持っています。多くの企業も製造向けのソフトウェアや、統計的プロセス制御（SPC）、歩留まり率管理システムといった個別の機能モジュールを備えていますが、SmartFactory ソフトウェアスイートの真の優位性は、全ソフトウェアを深く、高度に統合できる点にあります。
私たちは製造ソフトウェアの各カテゴリにおいて業界をリードしているだけでなく、ソフトウェア全体の統合という面でも業界をリードしています。実際、これ以上の統合化されたソリューションはないと言ってよいでしょう。通常、製造業のお客様は複数のソフトウェアを個別に購入し、自社のソフトウェアエンジニアが中間層コードを開発して統合を図ります。しかしその開発はコストは高く、時間もかかります。さらに、ソフトウェアベンダーがバージョンアップすると、その自社開発の中間層は機能しなくなる恐れがあります。SmartFactoryソフトウェアスイートの強みは、こうした統合用の中間層をあらかじめすべて提供している点です。その結果各ソフトウェアはシームレスに接続され、問題が発生することなく真の一体運用を実現できます。私はこれが非常に大きな価値を持つと考えています。
MESは、あることを非常にうまく処理できます。それは、製造プロセス各所で発生する全てを統合整理できるということです。少し大げさに聞こえるかもしれませんが、単純一つの役割を果たすだけのソフトウェアではありません。MES は単にプロセスの流れを定義するだけでなく、使用する装置や、その装置で特定の工程を行うために必要なレシピなど、各プロセスの実行に必要なリソースを定義します。さらにはプロセスに必要な部品、材料、化学薬品の構成までも定義します。MES システムはこれらの要素を体系的に管理することで、繰り返される製品製造において一貫性と正確性を保証します。
これこそが半導体製造メーカーが求めているものです。MESは、私たちが「CIM（コンピュータ統合製造システム）」と呼ぶものの中心に位置し、他の多くの機能を統合する役割を担います。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [イノベーション統合：新たな機会の獲得](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Bing Wang氏は、SmartFactoryソリューションによる機能統合がいかにしてお客様に革新の力を与え、新たな発展の機会を提供するかについて説明してくれます。SmartFactoryソリューションを活用して、イノベーションへの道を切り開く方法を探っていきましょう。
**Content:**
#### 字幕（全文）
みなさん、こんにちは。Bing Wangです。アプライドマテリアルズで CIM ソリューションのプロダクトマネージャーを務めています。スマートファクトリーという言葉が使われるとき、通常、高度にデジタル化され、相互接続された製造環境を指します。この環境では、すべてのシステムと技術がリアルタイムで通信し、協調して動作します。特に半導体製造では、スマートファクトリーの主な目的は、IoT、人工知能（AI）、機械学習（ML）、データ分析の4つの先端技術を活用し、製造プロセスを簡素化・最適化することにあります。
半導体業界のスマートファクトリーには7つの主要なポイントがあります。それはつまり、自動化、接続性、データ分析とリアルタイム監視、柔軟性、カスタマイズ、省エネルギー、そしてサイバーセキュリティです。SmartFactoryという言葉まさに、当社の最先端の自動化ソフトウェアのブランド名であり、半導体製造を非常に高度に自動化された方法で実現することを意味します。
すべての製造オペレーションはこの自動化されたソフトウェアで実現されて、ファブのクリーンルームに人が入ることはありません。当社は市場で唯一、先ほど挙げた主要な4つの先端技術をカバーする完全統合型ソフトウェアを提供できるソフトウェアベンダー・ソリューションプロバイダーです。お客様は、この統合型ソフトウェアを通じてイノベーションを実現し、新しいビジネスチャンスをつかむことができます。
当社が提供する統合されたCIMソリューションの最大の価値は、お客様が新しいファブを迅速に立ち上げ、短期間で稼働を開始することができるということです。お客様にとって製品の市場投入までのスピードは、収益性や投資回収率に直接関わるため極めて重要なことです。特に新たなファブの建設においては、その意義は非常に大きいといえるでしょう。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [Innovation Integration: Seizing New Opportunities](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Bing Wang discusses how SmartFactory's solutions empower customers to innovate and capture new opportunities through seamless integration. Explore the pathways to innovation with SmartFactory.
**Content:**
#### Transcript
I’m Bing Wang and I am the CIM Solution Manager at Applied Materials. When the industry talks about a SmartFactory, they are usually referring to a highly digitized and interconnected production environment where all the systems and the technology they communicate and collaborate in real time. Basically the goal for a SmartFactory is to leverage the advanced technologies such as IoT, AI, ML, and data analytics to streamline and optimize manufacturing process, especially when we talk about the semi-manufacturing industry.
From the industry perspective, when we talk about the SmartFactories, we’re referring to seven major characteristics. So basically it’s about automation, interconnectivity, data analytics, and real-time monitoring, flexibility, customization, energy efficiency, and also cybersecurity. SmartFactory represents the brand of our top-notch automation software and that is running the manufacturing in a very highly automated manner.
There’s no human inside the clean room of the Fab and everything is run by the automation systems. We are the only vendor or supplier or solution provider in the market that has the fully integrated suite that encompasses four main domains that I mentioned earlier. We provide opportunities for customers to innovate and seize new opportunities through integration.
I think the key value is that since we are the fully integrated CIM solution suite, we can get our customers deployed fast and ramp up their Fab, which is significant for our customers because the time to market for our customer is the key that actually determines how much profit margin they can gain, the return on the investment, especially when they build up a new fab.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi
---
### [SmartFactory MES自動化ソリューションによる製造業の卓越性の強化](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 技術専門家のDavid Hanny氏、Selim Nahas氏、Madhav Kidambi氏、Dan Meier氏から、SmartFactory 製造実行システム（MES）のオートメーションソリューションが、完全に統合された機能によって、どのように工場のオートメーションを最前線で推進しているのかをご紹介します。
**Content:**
#### 字幕（本文）
私たちはよく、こんな質問を受けます。MESシステムはどのような価値をもたらすのか？というものです。要するに、私が正しく理解していれば、「これにどう取り組み始めればよいのか？」ということです。まず第一に、MESは工場資産の最適化を支援し、産業ラインのボトルネックを突破し、重要工程の効率を向上させることで、全体の生産量を大幅に高めます。第二に、SmartFactoryのインテグレーションによって、工場での突発的な事象にも迅速に対応できます。総じて言えば、MESは工場の生産性を向上させるのです。
さらにもう一つの重要な要素は「予測可能性」 です。サプライチェーンの観点から大きな利益を得られる部分です。サプライチェーンが複雑化するなかで、企業は顧客の需要や需要の変化に迅速に対応する能力、ツールをより効率的に活用する能力が必要です。この予測機能を活用しツールを最適化することで、エネルギー効率やコスト削減を実現することも可能です。私は、MESの価値は大きく三つに集約できると考えています。
それは、スツールの3本の脚のようなものです。
1つ目は、繰り返し製造することです。私は何かを作っていて、それを毎回同じ方法で作りたいのです。
MESの観点からいえば、プロセスを定義しその順序通りに実行、設備の適時投入、プログラムパラメータの正確な設定、レシピ条件の遵守などを通じて、一貫性を担保します。2つ目は、一貫性を前提に生産効率を向上させることです。これは生産効率に関する点です。
どのように生産効率を向上させるのでしょうか？具体的には、生産サイクルの短縮、プロセス時間の最適化、ボトルネックの特定と解消などです。三つ目に、繰り返し作業の一貫性と高速量産を両立させながら、製品品質を保証することです。迅速な大量生産における不良は、不良品を大量に生産する大きなリスクをもたらすため、品質の強化は不可欠です。
これら三つの支柱から多くのことが派生します。我々には各領域に対応する様々なシステムがあります。
肝心なのは、それらシステムをいかに統合し、協調させるかという点です。これこそが、基本となる三つの支柱なのです。さらにグローバルな視点で見れば、MESや工場の生産性を超えて、最終的にはビジネスを支援するために自動化に関する意思決定を行う必要があると思います。顧客は、仕様の要件に合致した製品が納期通りに届いたときに利益を得ます。
そのため、各社はそれを測定するためのさまざまな方法を模索しています。
とりわけ重要な二つの指標は、第一に、ゼロ欠陥にどれだけ近づいているか。第二に、資産・設備・人材・プロセスに多額の投資をしているが、それらから最大の効果を引き出せているか、という点です。
私たちは常に、スマート製造はビジネス目的のために行っているということを忘れてはなりません。
これには、これまでに話した統合とその必要性、そして複数のシステムが連携して動作することが含まれます。
それが一つ目です。二つ目は、従来以上のことを可能にする先端技術を導入することです。工場で良いことでも悪いことでも何かが起きたときに、より迅速に意思決定できるようになれば、より多くのことが実行可能になり、Madhav氏が述べたように、工場の予測可能性が高まります。
要点を整理すると、SmartFactoryがもたらす価値は二つあります。第一に、これまで実現できなかったものづくりを可能にすることです。これらの生産はそもそもコストが高く、持続可能ではありません。
第二の要素は、人の要素、すなわち学習の要素です。
現場で何が起きているかの理解がなければ前進できません。その理解を記録・蓄積できます。技術面では、これまで述べてきた統合、プラットフォームのスケーラビリティ、合理的なコストで拡張できる能力が重要です。検討の結果、これは解決できない問題だと言わざるを得ない局面もあります。
費用がかかりすぎて割に合わないこともあります。
私の見方では、SmartFactoryは、私がどのシステムを評価する際にも重視する三つの基本要素—人の要素、技術の要素、経済の要素—をうまく両立させます。
**Semiconductor Category:** Smartclips, Panel
**Semiconductor Tag:** Smartclips
---
### [スマート製造：進化の最前線](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Phil Walker氏が、スマート製造の発展における SmartFactoryソリューションの重要な役割を解説するとともに、業界の未来を形作る最先端技術の進展を紹介します。
**Content:**
#### 字幕（全文）
皆さん、こんにちは。Phil Walkerです。アプライドマテリアルズにて メンテナンス及び持続的収益製品ビジネスを担当しており、製造業界で長年の経験を積んできました。振り返ると、私が若手エンジニアとして業界に入った頃、当時の製造プロセスがストップウォッチと紙の記録表だけで管理されていたことが信じられません。
当時は製造プロセスの各ステップを観察し、ストップウォッチで時間を計測し、ノートに記録し、それを表計算ソフトで整理して分析していました。当時はこれでも「スマート」工場と呼べるレベルでした。しかし、技術は大きく進化しました。今では、様々なシステムが存在し、より迅速にデータを取得し、分析し、可視化することが可能になっています。つい最近までの状況と比べると、大きく変化しました。まさに変革と言えるでしょう。
現在では、分析サイクルも大幅に短縮され、プロセス最適化の効率も飛躍的に向上しています。次のスマート工場の波では、これまでの基礎プロセスの全面的な自動化を実現することが目標です。
将来のスマート工場では、機械学習やAIが、データ収集や分析の計画を立てるだけでなく、自らデータを取得するようになります。つまり、「AI自体」がその役割を担うのです。製造業で起きることは、これまで存在していた基盤、すなわち情報を収集し、それに基づいて行動するという基本的な仕組みの大部分が、情報をより良く収集・分析する方法をすでに考えているシステムによって自動的に実行されるということです。
それでもなお、エンジニアには、その情報が何であるかを理解し、システムが提供する情報と洞察を基盤として受け取り、そこに独創性と創意工夫を加えて、飛躍的な改善を実現する役割が求められます。
これがSmartFactoryソリューションの核心的価値です。そして、これこそ、私がアプライドマテリアルズでの仕事にワクワクしている理由です。私たちが全力で開発している革新的技術は、単にエンジニアに有益なデータを提供するだけでなく、世界最先端の製造現場に直接関わっています。私たちは恵まれた環境と優れた条件を活かし、製造業及びスマート工場をさらに高いレベルへ持続的に推進することができます。
このような理由から、私はアプライドマテリアルズでの研究開発活動に胸を躍らせています。そして、製造業の未来に無限の可能性を感じています。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi, Smartclips
---
### [SmartFactory : 製造業の未来を切り拓く](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 当社のテクニカルリーダーであるDavid Hanny、Selim Nahas、Madhav Kidambi、Dan Meierが、SmartFactoryオートメーションソリューションがいかにあらゆる規模の工場における生産性と品質を変革しているかを探求しますのでこれらから知見を得ましょう。
**Content:**
#### 字幕（全文）
私たちはよく、こんな質問を受けます。SmartFactory ソリューションとは何ですか？お客様にとって何を意味しますか？おそらく、皆さんそれぞれ異なる見方をお持ちでしょう。そうですね。私の考えでは、SmartFactory ソリューションとは、完全にインテグレーションされ、相互に連携・協働できる製造システムを意味します。これにより、物理設備からのデータをリアルタイムに取得でき、迅速に対応し、より良い戦略を立てて製品品質を高め、生産量を向上させ、さらにファクトリオペレーションの予測可能性を実現することが可能となります。
現代の生産施設では、スケジューリングソフト、歩留まり管理ソフト、バッチトラッキングソフトなど、様々なソフトウェアが導入されています。重要なのは、これらのソフトウェアがいかに深くインテグレーションされ、共生的なシステム を形成できるかという点です。私にとって、まさにここに SmartFactory ソフトウェアスイートの独自の強みがあります。そのインテグレーションレベルは他の追随を許さず、そしてこのインテグレーションこそが、SmartFactory の中核的な価値だと考えています。
真のインテグレーションとは、複数のシステムが協調して課題解決にあたり、システム間でインテリジェントにトリガーが働くことを指します。これは単なるデータパイプラインではなく、データの共有を意味します。
場合によっては、共通の問題を一緒に解決するために、ロジックを共有して相互運用できるようにすることがあります。そして、その統合について考えるとき、それはスマートマニュファクチャリングにおいて本当に必要とされる3つの重要な要素の1つだと思います。私はこう考えます。「私たちは何を理解していて、何を理解していないのか？」ということです。つまり、もしその環境が、自分の業務について何かを学び、それを製造の行動に組み込む手段を提供するのであれば、それはSmartFactoryです。なぜなら、まず第一に、これまで知らなかったことを学ぶことができ、次に、それを工場内の行動に反映できるからです。それは、自分が知らないことを学び、知っていることを習得し、自分の専門分野を磨き、最終的には自動化領域における何らかの行動に変換し、それがリアルタイムで工場に直接影響を与えるという、自動化システムの行動です。
現状、私たちのデータ利用率は十分ではありません。これは最優先で改善すべき点です。もし重要なデータ特性を特定できれば、今日なお目的もなく保持されている膨大なデータの多くを廃棄できるでしょう。核心的な問いは、製造における認知の進化を支える環境を構築し、これまで不可能だったイノベーションを実現できるかどうかです。これこそが、私にとっての SmartFactory ソリューションの解釈です。
SmartFactory の本質は、ソフトウェア機能を工場の中核指標にマッピングし、運営効率を高め、プロセス品質を最適化し、生産性を向上させることにあります。これらはすべて極めて重要な要素です。
**Semiconductor Category:** Smartclips, Panel
**Semiconductor Tag:** Smartclips
---
### [AI：工場の自動化を革新し、体験を変革する](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** AIが次世代の工場自動化を加速し、私たちの日常生活を変えていく様子を、当社の技術リーダー、David Hanny、Selim Nahas、Madhav Kidambi、Dan Meierとともに探りましょう。
**Content:**
#### 字幕（全文）
ここで、少しAIに注目してみましょう。先ほど、環境がますます複雑になっているというお話がありました。最近、ある顧客とお会いして、AIについて少しお話ししたところ、「AIなんて必要ない」と冗談めかして言われました。
必要なのは「なぜ」です。何が起こっているのか、その「理由」を示してくれるものなのです。製造業のビジネス課題を解決する溜ために有益なものが必要です。
ChatGPTが市場に登場した速さに驚いた人はいますか？そうですよね。何かが出てくることはみんな分かっていましたが、ここまで進んでいると予想していましたか？発売も普及も、これまでのどんなテクノロジー製品よりも迅速でした。本当に。
少し予測してみましょう。もし製造業の世界で同じようなことが起これば、現状とはまったく異なるものへの、大きな変革となるでしょう。現時点では、そのようなものはありません。
問題は、誰かそれを実現するのかです。実際にそれをできる立場の人は、現場にいるのでしょうか？個人的な意見で、偏っているかもしれませんが、私は私たちであると思っています。というのも、その気になればできると考える企業は、過去にもありましたよね？まるで「自分たちになら何でもできる」と考えているかのようでした。データを分析し、活用し、AIの原理を使ってさらに掘り下げることができるのです。
問題は、彼らがデータに何が含まれているのかという基本を飛ばしてしまったことです。データの明確さはどの程度か？データの解像度はどの程度か？データの意味するところは何か？しかし、現在の工場の性能を大きく伸ばしたいのであれば、基盤がしっかりしている必要があります。そしてこれを実現するには、総合的なCIMを提供できることが求められます。
つまり、それらの機能は既にあるのです。現在SmartFactoryは、接続も実現しています。これは例えば、ロボットが自分で動いたり、さまざまな作業をこなしたりできるようにするうえで有用です。SmartFactoryのユニークな点は、AIデバイスやAI搭載機器が工場内で自律的に動作できることです。
それを私たちは今日、実際に目にしていますよね？そして、2つ目の機械学習ベースの機能セットには、パターンの検出や予測に関する様々なアプリケーションが含まれます。やはり、多くの進歩があったわけです。SmartFactoryが独自の価値を発揮するのは、先ほどお話ししたように、工場の生産性システムや MES、E3プラットフォームからデータを取得し、それを活用してより優れたマシンラーニングモデルを作る統合機能です。
ここでは特定のモデルにおいて、さまざまな観点からAIについて話していますよね？例えば、ウェハーの歩留まりを管理するAIや、生産性やサイクルタイム、スループット、ツールの負荷を管理するAIなどでしょうか？私たちは現在、SmartFactoryのソフトウェアスイート内で、様々な面で将来のAIの基盤を築いているのだと思います。ええ、各種コンポーネントにAIを組み込む必要があります。しかしいずれ次のステップで、ある汎用人工知能に到達すれば、工場全体を包括的に制御するAIを作ることも可能になります。
これは本当にワクワクすることで、今後5年から10年の間にどのような方向に進んでいくのか、とても楽しみです。生産性を最大限に高めることができますね。私たちはその段階にあります。現在は、様々なシステムを使って工場内の個別のポイントレベルでこれを行っていますが、それらすべてを工場全体のAIと統合し、各コンポーネントを配分・制御できるようにすれば、非常に少ない労力で大量の作業を実行できるようになります。
考えるだけでもワクワクしますね。
**Semiconductor Category:** Smartclips, Panel
**Semiconductor Tag:** Smartclips
---
### [Reduce cycle time with a powerful MES strategy](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
**Published:** May 16, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Increase KPIs by automating repetitive tasks and improving communication
**Content:**
Among the ways manufacturers can increase efficiency, productivity, and profitability is by improving cycle time—the average time it takes to manufacture a single lot from start to finish. There are several steps you can take to improve cycle time, including investing in technology that can automate repetitive tasks and improving communication and collaboration across your factory.
You’ll first need to map out your process and identify the bottleneck processes that limit the output of the entire factory – perhaps because they simply take the longest to complete or because there are too few of the required process tools to keep up with the needed processing. Focusing on these bottlenecks and inefficiencies can help reduce cycle time.
Several other factors impact cycle time. The time lots spend waiting to process can add significantly to cycle time, so look for ways to reduce wait times, such as through the use of automation or streamlining handoffs between different teams or departments. Similarly, complex processes with many steps take longer to complete so it is helpful to eliminate unnecessary process steps and streamline workflows. Another significant factor in cycle time is the number of lots in the factory—the work in progress (WIP). If WIP exceeds the factory’s capacity, there is an exponentially higher wait time between each lot. Variability is also a common impact on cycle time since fabs operate in the real world. Variability in processing time and the rate at which new lots are started in manufacturing are also frequent causes for delays. A manufacturing execution system (MES) can be a valuable tool in reducing cycle time.
The MES is the operational backbone of many factories and can help monitor, control, and optimize production processes in real-time. The SmartFactory MES can help improve cycle time by providing real-time visibility, automating data collection, using predictive analytics, improving communication and collaboration, and optimizing production processes.
- Real-time visibility into the production process enables you to monitor key performance indicators (KPIs) such as production output, downtime, and quality to identify and address issues quickly and minimize disruptions.
- Automated data collection eliminates the need for manual data entry and reduces the risk of data entry errors. The data can then be used to optimize the production process, identify bottlenecks, and improve cycle time.
- Predictive analytics can be used to forecast demand, identify potential production issues, and optimize production schedules.
- Improved communication and collaboration between different departments and teams involved in the production process also can help identify and address issues quickly.
- Dynamic process optimization through automated lot scheduling, dispatching, and routing based on real-time conditions within the factory can help improve productivity and reduce cycle time.
Whatever steps you take to reduce cycle time, it’s important to measure and track your progress, both to ensure the improvement steps you’ve taken are achieving the results you expect, and to identify areas that still need improvement. Be sure to celebrate your successes along the way!
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released, Semi
---
### [SmartFactoryが描く、人間中心のものづくり](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Selim Nahas 氏は、SmartFactory ソリューションが「人」をその中核的な要素として位置づけているというコミットメントを強調し、スマート製造ソリューションに人間中心の理念を取り入れることの重要性を述べました。
**Content:**
#### 字幕（全文）
Selim Nahasです。アプライドマテリアルズにおいて、プロセス品質ソリューションのディレクターを務めています。1995年からこの業界に携わっています。
SmartFactory は本質的に、私たちが投資し開発してきたエコシステムです。これは、工場の生産プロセスにおけるタスクを管理するために、行動を捉え、学習し、自動化に組み込んでいく仕組みです。そのため、私が強調したいことは、人と、そのエコシステムへの理解こそがすべての基盤である、ということです。今大事なのはどうやってそれを実現するか、ということです。人々がプロセスや手順の複雑さを理解し、それを工場の自動化にどのように組み込むかを決定できるようなエコシステムを、どう構築すればいいでしょうか？実際、私たちが一つひとつプロセスや手順を特定し、自動化しようと試みるたびに、ああ、これは本当に自動化できるのだ、と気づくのです。
これこそが、私たちと他のシステムとの最大の違いだと考えています。他のどのシステムもここまでは到達できません。その理由は、プラットフォームの設計の仕方、つなげ方、そして可視化の方法に深く関わっています。
私の見方では、これこそがイノベーションです。そしてそれは単一のものではなく、非常に幅広いものです。
多くの領域に適用されます。産業は世界中で一様ではありません。したがって、世界は人によって違って見えるのです。
SmartFactory ソリューションの真の価値を顧客が理解するのは、それが単一の解決策ではなく、包括的なソリューションのロードマップであると気づいたときです。そしてそれらを組み合わせることで、その価値は 25％や 50％をはるかに超えるものとなります。その瞬間、顧客は初めてその価値を実感します。なぜなら、これまで工場の生産プロセスは極めて断片的であったからです。今では、追求すべき統一的なソリューションのロードマップがあるのです。それにより、統合的な取り組みが可能になっています。つまり、それは一つの投資であり、サプライヤーとの共同投資でもあります。顧客自身がロードマップに対して大きな影響力と発言権を持つことができるのです。そのため、期待される成果やリリース時期、コストについても明確に把握できるのです。
私たちのソリューションは予測可能性と安定性を備え、さらに必要に応じて進化・維持していく力を持っています。そのため、顧客が必要としない限り、すべての時間をそこに費やす必要はありません。これこそが、顧客が本当に得る価値なのです。
それは単なる技術的な価値にとどまりません。関係性としての価値でもあります。真に実現できるのは、大規模なユーザー基盤を持ち、長期的に投資と開発を続けている業界のリーダー企業だけなのです。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [实时排程决策优化：数据与 AI 技术的融合应用（第1篇，共4篇）](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 本系列博客将重点探讨数据如何助力半导体制造商在生产力与质量方面实现更大效益。
**Content:**
[ 第2篇：理解与定义人工智能和机器学习 ](https://appliedsmartfactory.com/zh-hans/semiconductor-blog/al-ml-zh-hans/leveraging-data-and-ai-technology-part-2/)
## 内容概览
- [ 排程与派工中的数据应用 ](#index1)
- [ 推动式与拉动式干预 ](#index2)
- [ 基于规则系统的事件处理 ](#index3)
- [ 向预测型系统演进 ](#index4)
- [ 数据的影响力 ](#index5)
- [ 结论 ](#index6)
知名行业专家 James Moyne 与 Samantha Duchscherer 展开了一场精彩对话，深入探讨将人工智能 (AI) 等先进技术及额外信息整合到半导体行业排程与派工流程中的重要性。本系列文章共分四部分，重点涵盖数据价值与优势、AI 技术应用、人机协作等核心议题，同时深入分析当前面临的挑战，并针对数字孪生技术的角色提供独到见解。
在本系列的第一篇文章中，两位专家将聚焦排程与派工的发展现状。
Sam: 工业4.0对半导体制造业为何如此重要？数据在[排程](/zh-hans/semiconductor-blog/smartfactory-dispatching-solutions/)与派工中又扮演着怎样的关键角色？
James: 半导体行业在排程与派工方面领先于其他所有行业，因为半导体制造是一个高度自动化、快速运转且灵活多变的系统，需要快速且自动化地做出决策。
目前，实时排程派工技术几乎仍是半导体制造业所独有的。过去五年间，虽然制药和航空航天等行业已开始引入相关技术，但仍难以望其项背。事实上，这些行业正以半导体制造为标杆，试图复制其成功经验。
Sam: 当前半导体行业常用的排程与派工干预手段有哪些？其运作机制是怎样的？
James: 目前的排程与派工都是[基于规则的系统](/zh-hans/semiconductor-blog/scheduling-zh-hans/scheduling-solutions-for-semiconductor-factories/)。通过专家经验与数据来控制操作，比如“当某个事件发生，并且伴随A、B、C 的情况，需做出决策并将某个任务分配到至特定位置。”
这其中既有推动式也有拉动式机制。在推动模式中，重点是如何将晶圆从上层系统被分配到下游的资源上。这本质上是“我有晶圆，并且知道该把他们送到哪台设备”。
而在拉动模式下，则是决定加工顺序。例如，一台设备被分配了四片晶圆需要加工，这时需要决定处理它们的顺序。推动和拉动模式协同工作，通过 APF RTD™ 等基于规则的解决方案来实现。
Sam: 制造过程中常会出现各种意外事件，当前这些基于规则的系统是如何处理这类事件的？
James: 当前的系统兼具预测性和反应性功能。其反应性体现在：当遇到未预测到的事件时，系统没有预设或自动化的应对方案。面对意外情况，系统基本上会“束手无策”。这时就需要领域专家进行人工干预。专家会判断是否需要新增规则，以应对未来可能再次发生的类似情况；或者，如果认为这只是偶发事件，则会在当下制定解决方案。
系统的预测性则体现在：它会综合考虑预设规则、设备运行方式、预期产能和质量要求等因素，然后做出诸如“将一些成本更高的晶圆分配给产能更高的设备”这类决策。
Sam: 要让这些系统更具预测性并实现升级，需要具备哪些条件？
James: 我们已经开始在排程与派工系统中引入预测功能，这正是数据发挥作用的关键所在。首先需要收集大量数据——不仅包括排程与派工本身的数据，还要涵盖所有可能对其产生影响的因素。设备维护就是典型例子：通过收集大量数据，您可能会发现某台设备存在特定的维护规律。您将逐渐掌握设备故障的时间节点、频率，更重要的是这些数据的波动特征。这些洞见最终都能整合到排程与派工的决策中。
预测性维护的可信度取决于历史数据的积累程度。数据越丰富，越能识别历史规律。例如，当您拥有某台设备两年的维护日志时，就能准确判断该设备的维护特性，并据此优化后续决策。若缺乏此类历史数据，则需从零开始逐步建立预测模型的可信度。因此，预测能力本质上取决于：数据存储的时间跨度、数据可靠性、数据质量、行为模式的动态变化等关键维度。
Sam: 目前哪些数据对预测排程与派工事件的影响最为显著？
James: 我们的研究发现，预测功能可分为两个层面：首先时处理微小异常。例如当生产整体平稳运行时，某台设备的加工时间从1分钟波动到1分10秒，系统就基于这种预测和波动做出相应决策。
第二个层面是预测重大中断事件。比如预测计划外停机并提前通知排程派工系统，从而能做出更关键的决策，比如重新分配任务。可以看出，数据驱动在这一层面起到了关键作用，帮助应对那些需要我们对排程派工决策做出重大调整的灾难性或大规模变更。
需要强调的是，数据不仅直接影响排程派工，还会通过其他应用的输出间接产生影响。例如预测性维护和批次间控制，这些应用旨在提高生产效率和晶圆质量。如果您知道批次间控制系统在 A 设备上生产出的晶圆质量优于 B 设备，这对排程来说就是非常重要的信息。
我们目前正在尝试将这类信息整合到排程派工系统中。未来，数据驱动技术（如[集成人工智能](/zh-hans/ai)、机器学习和数字孪生）将为排程派工带来更多革新机遇。
### 结论
半导体制造业在实时排程与派工领域处于领先地位。随着其他行业将其视为实施标杆时，半导体行业已开始利用数据提供的机遇，开发更具预测性的排程派工系统，从而提升生产效率与质量。
在下一篇文章中，我们将详细阐述人工智能 (AI) 与机器学习 (ML) 的定义。
## Moyne 博士简介
James Moyne 博士是密歇根大学副研究科学家，专注于通过增强排程与派工领域的数据整合来优化决策。他在预测性维护、基于模型的过程控制、虚拟计量及良率预测等前瞻性技术方面拥有丰富经验，同时致力于数字孪生与分析等智能制造概念的研发，推动微电子行业的智能制造落地。
Moyne 博士积极参与先进过程控制 (APC) 的推广工作，担任多个行业协会的联合主席及领导职务，包括 IMA-APC 委员会、国际设备与系统路线图 (IRDS) 工厂集成专题组、SEMI 信息与控制标准委员会，以及美国年度 APC-SM 会议。
凭借其深厚的专业知识与丰富的行业经验，Moyne 博士被公认为标准和技术领域的权威顾问，在智能制造、预测和大数据领域做出了重大贡献。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [借助强大的 MES （制造执行系统）策略缩短生产周期](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-strategy/)
**Published:** October 16, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** 通过自动化重复任务和改善沟通来提高KPI
**Content:**
制造商提高效率、生产力和盈利能力的方法之一是缩短生产周期，即生产单个批次从开始到结束所需的平均时间。 您可以采取若干措施来缩短生产周期，包括投资可自动执行重复任务的技术，以及改善整个工厂的沟通和协作。
首先，您需要梳理业务流程，并识别出制约整个工厂产出的瓶颈环节。可能是因为这些工序需要花很长的时间完成，或者因为所需的工艺设备数量太少而跟不上所需的工艺处理效率。 专注解决这些瓶颈和低效环节有助于缩短生产周期。
影响生产周期的还有其他几个因素。 等待处理的时间会大大增加生产周期，因此要想方设法减少等待时间，如使用自动化或简化不同团队或部门之间的交接。 同样，具有许多步骤的复杂工艺需要更长的时间才能完成，因此消除不必要的工艺步骤并简化工作流程会有所帮助。 影响生产周期的另一个重要因素是工厂中的批次数，即在制品 (WIP)。 如果 WIP 超过工厂的产能，那么每个批次之间的等待时间就会呈指数级增长。 在晶圆厂的实际运作场景中，存在着各种变化因素，会对生产周期造成影响。 加工时间的变化和制造过程中新批次的开始效率，也是造成延误的常见原因。 因此，制造执行系统 (MES) 可以成为缩短生产周期的有效工具。
MES（制造执行系统）是许多工厂的运营支柱，可帮助实时监控、控制和优化生产流程。 SmartFactory MES 可以通过提供实时可见性、自动化数据收集、使用预测分析、改善沟通和协作以及优化生产流程来帮助缩短生产周期。
- 实时的生产流程可见性使您能够监控关键性能指标 (KPI)，如产量、停机时间和质量，从而快速识别并解决问题，最大限度地减少中断。
- 自动化数据收集使手动数据输入不再成为必需，并降低了数据输入错误的风险。 然后，这些数据可用于优化生产流程、 识别瓶颈和缩短生产周期。
- 预测分析可用来预测需求、识别潜在的生产问题，并优化生产计划。
- 改善生产流程中不同部门和团队之间的沟通与协作，也有助于快速识别和解决问题。
- 基于工厂内的实时情况，通过自动化的批次排程、派工和工艺路线进行动态工艺优化，有助于提高生产力并缩短生产周期。
无论您采取什么措施来缩短生产周期，都必须衡量和跟踪您的进度， 这至关重要。这样做的目的是确保您所采取的改进措施达到您期望的结果， 同时又能够识别仍然需要改进的领域。 一路走来披荆斩棘， 最后祝您达成目标！
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, Newly Released
---
### [SPC戦略で品質の卓越性を実現する](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Vishali Ragam氏が SmartFactory の統計的工程管理 (SPC) がどのように顧客の品質改善を推進するのかを明かします。卓越した品質管理を実現する秘訣をご紹介します。
**Content:**
#### 字幕（全文）
みなさん、こんにちは。Vishali Ragamです。アプライドマテリアルズのオートメーション製品部、プロセス品質ソリューションチームでSPC プロダクトマネージャーを務めています。Applied SmartFactory SPC が提供する最も革新的なソリューションの一つは、人工知能や機械学習アルゴリズムを容易に導入できる点です。
顧客は機械学習モデルを使用する際に、特別な専門知識を必要としません。このモデルは顧客が全体的な品質を向上させるのに大きく貢献し、さらに先進的な分析技術を工場に取り入れることを可能にします。多くの顧客は、価値を測る指標として主要業績評価指標を用いています。もし SPCがプロセスを簡素化し、製品品質を高め、生産コストを削減できるのであれば、顧客はそれを成功と見なすでしょう。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi, Smartclips
---
### [Improve throughput by 5-10% using SmartFactory dispatching solutions](https://appliedsmartfactory.com/semiconductor-blog/scheduling/smartfactory-dispatching-solutions/)
**Published:** May 3, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** Increase productivity by another 3-5% by integrating SmartFactory scheduling and dispatching solutions
**Content:**
Semiconductor factories often use the terms “scheduling” and “dispatching” loosely. In this blog, I define these terms, with greater emphasis on context, outline common misconceptions and challenges associated with these techniques, and highlight the value of deploying an integrated approach with scheduling and dispatching.
### Scheduling: Lot Assignment
*Scheduling* in this blog refers to assigning lots to a given set of equipment in a specific area. Assigning lots is based on current and predicted lot arrivals, as well as current and future equipment conditions. Manufacturers typically create schedules for a 12-hour shift and generate them on 10–15-minute intervals. Typically, scheduling solutions are implemented for bottleneck tools or areas with complex processing requirements. Some examples include litho, wets/diffusion, chamber-based tools, testers, and so forth. The scheduling solution can be based on optimization or heuristics methods. Both these options enable better throughput. The optimization-based methods are known to provide an additional **3–5%** improvement in throughput over heuristic methods. For details on this improvement, refer to [Michael Förster of Infineon Technologies](/blog/infineon-technologies-describes-how-they-optimize-productivity/) describe how they optimized their productivity, using SmartFactory integrated solutions.
### Dispatching: Lot Sequence
*Dispatching* in this blog refers to the sequence of lots to process at specific equipment in real-time. Dispatching rules are implemented factory wide and are typically implemented as global and local rules. The **global rule** includes line balance logic that enables managing customer commits, and **local rules** that contain additional logic to optimize the throughput for a given area—like Litho.
### Misconceptions
A common misconception is that dispatching rules don’t comprehend the upstream and downstream WIP/equipment conditions while creating a sequence of lots processed for specific equipment. Our SmartFactory dispatching solutions incorporate upstream and downstream WIP conditions, as well as current and future factory states to create dispatching lists in real-time. Based on the current capabilities, our dispatching solution can be considered as “real-time scheduling” and the scheduling solution as “near real-time scheduling.” Table 1 summarizes the differences between planning, scheduling and dispatching solutions.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-fig-min.jpg) Table 1: Planning, Scheduling and Dispatching Solution Scope
One more common misconception is that you only need a scheduling solution and not dispatching. Typically, schedules are generated every 5–15 minutes in a factory. During this time the factory floor encounters many changes. Equipment states might change, a lot might be put on hold or a process on qualified tools might become restricted. In their paper on near real-time scheduling and dispatching, Govind et al. present data on how often an area state changes1. Based on this data **50%** of the changes occur in <5 minutes and **80%** occur in <15 minutes. Due to this change a published schedule creates unclear and inconsistent decisions on the floor. Some of the challenges are:
- **Manual Adjustments.** An operator working from a 5 to 15-minute old schedule attempts to select a lot for the tool, but the lot is now on hold. The next lot on the screen is scheduled for a tool that just went down. In this case the operator must now adjust manually. This adjustment creates more idle equipment with WIP on hand, impacting throughput and cycle time.
- **Schedule Responsiveness.** Published schedules are unable to react in real-time for critical yield excursion recovery. In this case engineering needs to immediately restrict certain tools and funnel work to a golden tool “where possible.”
- **Automated Transportation.** In factories where transportation is automated using an overhead track (OHT) system or automated guided vehicles (AGVs) or other types or robots, they often fail to deliver lots to the correct equipment, resulting in numerous exception handling scenarios and creating white space on equipment.
To overcome these challenges an integrated dispatching solution is required. In areas where manufacturers implement scheduling, dispatching rules try to follow scheduling results and due to some of the challenges mentioned previously, it adjusts the scheduling results based on real-time factory status. Figure 1 shows how a SmartFactory integrated and dispatching solution is implemented.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/final-table1-min.jpg) Figure 1: Executing Integrated Dispatching and Scheduling Solution
Deploying an integrated scheduling and dispatching solution ensures that:
- Real-time adjustments to dynamic events in a factory occur with a consistent, heuristic-based approach.
- Rules incorporate both global and local parameters at a fast logic execution time (in seconds) for the lowest hanging fruit in productivity.
- Scheduling in highly constrained areas provide additional value when rules become too complex to provide an optimum path.
- Each domain is used to converge consistently and tightly with direct links toward factory objectives and key metrics.
Customers using our SmartFactory dispatching solutions improve throughput by 5-10% and increase productivity by another 3-5% by integrating these solutions.\[1\]
**REFERENCE**
\[1\] Operations Management in Automated Semiconductor Manufacturing with Integrated Targeting, Near Real-Time Scheduling, and Dispatching, Nirmal Govind, Eric W. Bullock, Linling He, Bala Iyer, Murali Krishna, and Charles S. Lockwood, IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, VOL. 21, NO. 3, AUGUST 2008
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [SmartFactory AI概要](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactory-ai-overview/)
**Published:** May 13, 2025
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** SmartFactory AIソリューションがどのようにイノベーションを推進し、パフォーマンスを最適化し、シームレスな製造
管理のためにリアルタイムのデータアクセスを強化するか
について説明します。
**Content:**
## 字幕（全文）
AIによる製造業の未来へようこそ。
私たちのSmartFactoryチームは、イノベーションを推進し、みなさまのビジネス運営の価値を向上させています。AI駆動のソリューションは理解を統一し、リアルタイムでデータをアクセス可能にし、これまでにないパフォーマンスの最適化を実現します。
AIが製造業をどのように変革していますか。AIが大規模なデータセットに基づいて即座に洞察を提供し、より迅速で正確な意思決定を可能にする様子を想像してください。これは単なる生産性の向上ではなく、製造業全体の風景を変革することなのです。
なぜならば、それは競争相手が休まないからです。この変革を理解するために、AIシステムの主要な機能を見てみましょう。環境の認識、入力の解釈、過去の結果からの学習、そして是正措置の提案です。
これらの能力は製造業者に大きな利益をもたらします。AIを適切に使用することで、収率を向上させ、出力を加速し、コストを削減することができます。AI駆動のシステムは設備の稼働時間を増やし、設備のメンテナンスを提案し、サプライチェーンを最適化することで、障害を減らし効率を向上させます。
センサー、機械、人々からのデータを組み合わせることで、AIはより多くのデータを使用して意思決定の精度を高め、意思決定の速度を加速します。製造業におけるAIの実際の応用例をいくつか見てみましょう。AIは設備の故障を予測し、ダウンタイムとコストを削減します。
AIはワークフローを最適化し、リアルタイムの欠陥検出による正確な品質管理を保証することで、生産ラインの利用率を向上させます。さらに、AIは計画の意思決定を最適化し、潜在的な環境リスクを特定することで安全性を向上させ、Cobotsのようなシステムを通じて人間と機械の協力を強化します。AIは多くの利益を提供しますが、課題もあります。
セキュリティとデータ品質の問題が最も重要であり、AIの導入を妨げる可能性があります。他の既知の課題には、ソリューションの説明可能性、データの不足、異なる技術などがあります。最後に、AIの使用ケースのビジネス価値を特定することが重要です。
このような課題に対応することで、製造業におけるAIの未来は有望です。私たちと一緒にこの未来を形作り、SmartFactory AIで一歩先を行きましょう。
最新情報は[AppliedSmartfactory.com/ja](/ja)に随時チェックしてください。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [AIが半導体の製造現場にもたらす変革](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-transforming-manufacturing-kpis/)
**Published:** April 16, 2025
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** 半導体メーカーは、工場の生産性を加速させるとともに、新たなビジネスチャンスを切り拓いています。
**Content:**
## 本ブログの内容
- [ AIのパラダイムシフト ](#index1)
- [ 実績ある技術で、新たな革新を ](#index2)
- [ 人的要因 ](#index3)
- [ 経済的要因 ](#index4)
- [ 次世代のアドバンテージ ](#index5)
### AIのパラダイムシフト
既存の統合ソフトウェアソリューションやAIベースのソリューションを使用する場合でも、製造業者の目的は基本的に同じです。すべての製造プロセスで効率と品質の向上を図ることです。しかし、既存のソリューションが達成できることに限界がある一方で、AIは前例のないレベルの学習とデータ処理を可能にします。この破壊的技術の導入により、品質、生産性、スループット、稼働時間などの従来のKPIに対する新たな視点が得られるパラダイムシフトが生まれました。
### 実績ある技術で、新たな革新を
AIは、1950年代に「AI」という用語が生まれたことを考えると、新しいものでも革命的なものでもありません。新しいのは、AIの主流の応用とアクセスのしやすさです。これにより、AIの利用方法に関する人間の理解が急速に進化し、特に破壊的な力が生まれています。これにより、パフォーマンスレベルが向上し、新たなビジネスチャンスが生まれています。
製造業者にとって、AI革命は技術をこれまでよりもはるかに速いペースで市場に投入する能力です。以前は、ビジネスが何かを設計し、それを生産ラインに投入するのに9か月かかっていたところ、AIはそれを画期的な3か月で実現できるようにします。この能力により、より高度な製品に焦点を当て、コスト効率を高め、品質とスループットの向上を図ることができ、ビジネスを大きく変えることができます。これには、以前は手の届かなかった高利益の契約を追求する機会も含まれます。
例えば、半導体業界では、革新的で改良された製品を市場に投入できる企業はごくわずかであり、その製品で一定期間驚異的な利益を享受しています。AIを活用することで、これまで競争できなかった企業も1世代または2世代先を飛び越えて、より高いレベルでパフォーマンスを発揮できるようになります。
AIシステムを教えるために必要なデータも変化しています。かつては膨大なデータにアクセスできる大手企業だけが可能とされていたものが、合成データ生成の新技術によりギャップを埋めることができるようになっています。工場内の異なる製品間の理解を橋渡しする能力に焦点が当てられるでしょう。製品の切り替えがよりシームレスになり、バリエーションをより効果的に管理できるようになります。これにより、ラインバリエーションの管理能力が大幅に向上します。AIに関する技術的進歩により、次の革命のステップは、それを反復可能でスケーラブルかつ意味のある方法で実装する方法を学ぶことです。
### 人的要因
AIが技術革新であると同時に、その潜在能力を実現し、新しいパラダイムを推進するのは人間の役割です。現在、AIを最適化するために必要なスキルセットは、AIと関連技術に精通したデータサイエンスの専門家と、半導体製造を深く理解しているプロセスの専門家の2つのグループに分かれています。彼らは協力して、AIの影響を最大化し、特定のアプリケーションに対してモデルをトレーニングする方法を最適化する必要があります。
製造業者はまた、AIを使用して人間の限界を克服します。例えば、AIは16の分析を同時に実行し、数秒以内に応答を導き出すことができます。一方で、人間は疲労やバイアスにより誤りを犯しやすく、これらの分析を処理するのに時間がかかり、結果に独自の解釈を加えることになります。
AIが人間の限界を改善するもう一つの方法は、記憶保持に関するものです。人間の記憶、訓練、経験の違いにより、各人が問題に対処したり情報を学習したりする方法が異なるのに対し、AIは効果的な代替手段です。AIと人間が情報を扱う方法の違いは、学習がどのように捕捉されるかにあり、全体的な理解が統一され、リアルタイムで必要なすべてのデータセットを関連付ける能力が得られます。
AIはまた、製造業における知識保持の課題にも対処できます。特に経験豊富な労働者が退職し、新しい労働者が労働力に加わる際に役立ちます。AIによって保持された知識は、工場全体で即座に利用可能となり、新しい人材の指導に役立ちます。私たちは本質的に学習システムを構築することができます。これは新しいことです！
### 経済的要因
製造業におけるAIの統合は、技術的および人的要因と同様に経済的要因にも影響されます。300mmの先進ノードを行っているファウンドリ、200mmの自動車メーカー、150mmのMEMS工場はそれぞれ異なるビジネス展望を持っています。彼らの構造は異なり、支出の意欲と必要性は全く異なる要因によって駆動されます。例えば、150mmの工場は大きな利益率を持っていますが、何かを変更したり投資したりするための説得力のある理由が必要です。彼らはビジネスを変える意味のある結果を得ることができなければ、AIに投資するインセンティブはありません。このような工場は効率向上に投資します。
代わりに、AIの統合は300mmの製造レベルで開発されます。それは厳密なルールではありませんが、レガシーな工場 での大規模な支出を想像するのは難しいでしょう（以前に驚かされたことがあります）。AIは多品種少量生産のシナリオで大きな役割を果たし、新製品を市場に投入するのに非常に強力です。
半導体メーカーが最も懸念していることの一つは、高齢化による退職とともに失われる経験です。彼らが不安に感じているのは、3年に一度あるかないかの深刻なトラブルを、どうやって管理すればいいのかということです。というのも、それを実際に経験したことのある人たちは、すでに現場を離れてしまっているからです。AIはそのギャップを埋め、知識を保持し、新しい労働者に利用可能にします。また、企業が人々にその職業をより効率的に教えるのにも役立ちます。これは、製造業者がAIに投資する最も意味のある理由の一つです。
最終的には、AIをめぐる経済的意思決定は、工場の経済性とそれに関係する市場原理に基づいて、時間の経過とともに動いていくだろう。
### 次世代のアドバンテージ
AIの開発と展開を最適化するためには、半導体メーカーが考慮すべき人的 技術的、経済的な要素が多くあります。これにより、ビジネスニーズと可能性について新しい考え方が生まれ、これまで理解されていなかったことや管理されていなかったことを学ぶ機会が生まれます。AI導入前と導入後の性能レベルの違いは、ジュニア選手とオリンピックレベルの選手が競うようなものです。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Featured, Semi
---
### [アラートノイズを削減し、運用効率を向上](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
**Published:** October 11, 2022
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** SmartFactoryチームがアラーム処理向けの新ソリューションを発表
**Content:**
## 内容一覧
## 本ブログの内容
- [ SmartFactory Alarm Managementソリューション ](#index1)
- [ 主な機能 ](#index2)
- [ まとめ ](#index3)
ご存じですか？大量生産の製造工場では、さまざまなシステムや装置から発生するアラームの数が、1秒間に最大1,000件に達すのアラームやアラートを管理することはオペレーターにとって大きな負担となり、重要なアラームを見逃してしまう原因になります。これにより、ウェーハの廃棄や逸脱（エクスカーション）が発生する可能性があります。オペレーターがこのような状況に直面すると、アラームに対する感度が鈍くなり、アラームスパムに圧倒されてしまいます。その結果、アラームへの対応が遅れ、装置が問題のある状態のまま長時間放置されたり、誤処理されたウェーハが検査されずに処理され続けたりします。（図1：アラーム管理の概要をご覧ください）
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/10/alarm-management-works.jpg) 図1：アラーム管理の仕組みの概要
1日に数百から数千件のアラームを処理することは、多くの高ボリューム製造工場にとって今なお共通の課題です。この負荷に対応するためには、リアルタイムで大量のアラームを継続的に管理・対応する必要があります。工場内のアラームを効率的に管理するソリューションを導入することで、オペレーターは即時対応が必要な重要アラームに集中でき、重要度の低いアラームをフィルタリングすることが可能になります。
### SmartFactory Alarm Managementソリューション
SmartFactory Alarm Managementは、こうしたアラーム管理の課題にリアルタイムで対応するために開発されたソリューションです。図2は、アラームをルールに基づいてフィルタリングすることで、生産性が向上する様子を示しています。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/10/fig1-alarm-validity.png) 図2：ルールに基づくアラームのフィルタリングにより、オペレーターは有効なアラームに集中可能
### 主な機能
**エクスカーションの防止による歩留まりの向上:** アラームがフィルタリングされることで、オペレーターは重要なアラートをすばやく特定し、優先度の高い問題に迅速に対応でき、ウェハーの誤処理を防ぎます。
**装置のダウンタイム削減による稼働率の向上：** ターゲットを絞ったアラームへの迅速な対応により、技術者やエンジニアが適切なアクションをすばやく実行でき、装置の停止時間を最小限に抑えます。
**サイクルタイム短縮によるスループットの向上：** アラートノイズの削減とアラームデータの統合により、トラブルシューティングが迅速に行え、労働生産性と運用効率が向上します。
### まとめ
SmartFactory Alarm Managementは、工場内のアラームを効率的に管理し、運用の最適化を実現します。このソリューションは以下を可能にします： - リアルタイムアラーム処理を一元化
- 各種システムからのアラームを一貫した手順で管理
- アラームフィルタリング階層を適用し、最適なルールを選定
- アラームの重要度に応じた対応を実施
- 重複排除アルゴリズムによりアラートノイズを削減
- アラームデータを統合し、迅速なトラブルシューティングを実現
半導体メーカーは、重要なアラームに集中することで、時間とリソースをより有効に活用できます。
## よくある質問
#### Q：なぜアラームへの迅速な対応が必要なのですか？
A：対応が遅れると、装置が問題のある状態のまま長時間放置されたり、誤処理されたウェーハが検査されずに処理され続ける可能性があります。
#### Q：リアルタイムアラーム管理の利点は？
- 工具の停止時間を削減
- 製品品質リスクを低減
- 工場全体のアラーム処理を迅速化
#### Q：SmartFactory Alarm Managementはどのようにオペレーションを最適化しますか？
A：アラームを効率的に管理することで、アラートの特定・優先順位付け・対応を迅速に行い、適切なアクションを取ることができます。
SmartFactory Alarm Managementに関するご相談はこちら
[ お問い合わせ ](/ja/connect/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released
---
### [半導体先端パッケージにおけるMESインテリジェンスの最適化](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/semiconductor-advanced-packaging/)
**Published:** October 16, 2024
**Author:** Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®
**Excerpt:** SmartFactory MES for ATP（Advanced Packaging）は、ファンアウトパッケージング工程において、チップ（ダイ）のトラッキングとトレーサビリティ、および材料消費履歴の管理を可能にします。
**Content:**
## 本ブログの内容
- [ ユースケース①：チップ（ダイ）のトラッキング ](#index1)
- [ ユースケース②：チップ（ダイ）のトレーサビリティ ](#index2)
- [ メリット ](#index3)
- [ まとめ ](#index4)
- [ 次のステップ ](#index5)
半導体の先端パッケージ技術は、次世代デバイスの開発において極めて重要な役割を果たしています。技術の進化に伴い、従来のパッケージ手法ではサイズ、性能、消費電力の面で限界が生じています。先端パッケージは、これらの課題を解決し、機能性の向上、小型化による性能改善、低消費電力、高信頼性を実現します。
最近の技術革新の中でも、特にファンアウトパッケージはその汎用性とスケーラビリティの高さから急速に注目を集めています。ファンアウトパッケージは、プロセッサー、センサー、高帯域メモリ（HBM）など複数の半導体デバイスを1つの高性能パッケージに統合することが可能です。設計や形状の柔軟性も高く、機能性を維持しつつコストを抑えた小型モジュールの実現が可能です。
本ブログでは、MESがファンアウトパッケージ工程を最適化する2つの主要なユースケースを紹介します。
### ユースケース①：チップ（ダイ）のトラッキング
**課題**
ファンアウトパッケージング工程では、複数のチップ（ダイ）を基板に取り付ける際に、どのチップ（ダイ）がどの位置に、どの順序で取り付けられるかをモデル化することが重要です（下図の図1参照）。
ひとつの基板上の位置に、異なる種類のチップ（ダイ）が取り付けられる可能性があるため、正確なチップ（ダイ）取り付け順序の設定は非常に重要です。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure1-substrate-1.jpg) 図1：基板上の複数のチップ（ダイ）
SmartFactory MES for ATPは、各工程ステップにおいて適切なチップ（ダイ）とその取り付け順序を事前に定義できる柔軟なモデリング手法を提供します。（図2参照）
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure2-setup-die-attach-spec.png) 図2：チップ（ダイ）取り付け仕様を定義するUI画面
**メリット**
SmartFactory MES for ATPは、チップ（ダイ）が基板にどのように取り付けられるかをモデリングおよびトラッキングする機能を提供し、実行時のミス防止によって運用効率の向上を実現します。
さらに、事前定b義されたオートメーション化シナリオにより、各種製造装置との自動連携にかかる工数を最小限に抑えることができます。
### ユースケース②：チップ（ダイ）のトレーサビリティ
**課題**
ファンアウト工程では、各基板位置に取り付けられるチップ（ダイ）の数と順序の決定が非常に複雑になります。
そのため、どのチップ（ダイ）がどの基板で使用されたかを追跡するトレーサビリティ機能が不可欠です。
さらに、チップ（ダイ）の消費履歴を簡単に確認・評価できる柔軟なレポートツールも必要です。
SmartFactory MES for ATPは、どのアセンブリロットでどのチップ（ダイ）が使用されたかをレポート可能です（図3参照）。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure3-die-consume-info-1.png) 図3：アセンブリロットで使用されたチップ（ダイ）のレポート
作業指示ごとのチップ（ダイ）消費状況も確認でき（図4参照）、基板IDごとの消費量も把握可能です。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figur-4-die-lot-consume-report.png) 図4：作業指示ごとのチップ（ダイ）消費レポート
### メリット
SmartFactory MES for ATPは、消費されたチップ（ダイ）の数量およびチップ（ダイ）／基板の位置情報に関する包括的なトレーサビリティレポートを提供します。
本ソリューションは、製品の種類を問わず（AIプロセッサからHBMモジュールまで）、製造中に発生する問題の影響を最小限に抑え、根本原因の特定するための時間を短縮するのに必要な正確かつ詳細な情報を提供します。
### まとめ
The SmartFactory MES for ATP:
- 基板上のチップ（ダイ）の取り付け位置と順序をモデリングすることが可能で、これにより、ファンアウト工程全体にわたって、チップ（ダイ）・基板・ロットの包括的かつ正確なトレーサビリティが実現されます。
- 消費された材料、製造用治具の使用履歴、工程の系譜、および装置の稼働状況と保守履歴等に関する包括的なトレーサビリティ機能を提供します。
これにより、製造オペレーションの可視性と監査適合性が担保されます。
- ロットの移動を追跡し、生産の進捗を監視し、MESとオートメーション化された装置との間で正確なデータ同期を維持することで、ファンアウト工程全体の管理を実現します。
### 次のステップ
半導体の先端パッケージ技術は革新的かつ急速に進化しています。
SmartFactory MES for ATPがどのように多様なユースケースに対応しているかをぜひご覧ください。次回のブログでは、先端パッケージ工場における完全自動化の実現についてご紹介します。
SmartFactory MES for ATPの詳細については[こちら](/ja/connect)からお問い合わせください。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [生成AIで進化する産業エンジニアリングのワークフロー](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/integrating-generative-ai-into-industrial-engineering-workflow/)
**Published:** August 13, 2025
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 複雑さを明瞭さに変える可能性は、複雑なデータの管理を任されている産業エンジニアにとって、ゲームチェンジャーとなり得ます。
**Content:**
## 本ブログの内容
- [ データとの対話 ](#index1)
- [ 行動を起こす ](#index2)
- [ 自律的な洞察 ](#index3)
- [ まとめ ](#index4)
半導体製造は、あらゆる装置、工程、スケジュールが豊富で複雑な情報を生み出す、データの宝庫と言っても過言ではありません。しかし現在、データの収集自体はもはや課題ではなく、それを迅速に理解することこそが本当の課題です。特に産業エンジニアは大きな負担を抱えています。彼らは毎日、数十件、時には数百件ものトピックを管理しています。スケジュールの分析からキャパシティプランの評価まで、膨大なデータと意思決定の量にすぐに圧倒されてしまいます。現在のツールやシステムは確かに分析を支援してくれますが、変化の激しいファブ環境では、絶え間ない要求とスピードに追いつくのが精一杯です。
想像してみてください。もし産業エンジニアがデータと会話し、対話を通じて直接アクションを起こし、プロセスをより自律的にできたら？大規模言語モデルによる会話型支援は、産業エンジニアがデータと関わる方法を根本から変える可能性があります。
### データとの対話
産業エンジニアは、突発的な問題に迅速に対応しなければならない緊急事態にしばしば巻き込まれます。しかも問題は日によって異なり、装置の故障、生産のボトルネック、サプライチェーンの混乱、品質管理の課題など多岐にわたります。このよう「火消し」の対応は多くの時間とエネルギーを消耗します。レポートは支援のために用意されていますが、時には「別のレポートを説明するためのレポート」があるように感じることもあります。ダッシュボードやデータがあっても、産業エンジニアが本当に必要としているのは、「このデータセットには何台の装置が含まれていますか？」「1日あたりのロット開始数を見せてください」、このようなシンプルな質問に対するシンプルな答えです。
こうした質問に対して、クエリを書いたり、分析を構築したり、データの解釈ミスを心配したりすることなく、ただすぐに答えが欲しいのです。
自然な会話を通じて探索的データ分析（EDA）を行うという考え方は非常にシンプルです。しかし実際には、明確で直接的な質問をするだけで大きな効率向上が期待できます。
さらに、単純な質問だけでなく、仮定の検証やデータ品質の確認も可能です。たとえば、「データに負の処理時間は含まれていますか？」という質問です。信頼性の高いデータを維持することは常に課題であり、検証手順の標準化は困難です。状況に応じて、専門家は外れ値、欠損値、不整合など、深刻な問題の兆候を見抜く方法を知っています。データ品質チェックの効率化は、意思決定の迅速化に不可欠です。
### 行動を起こす
会話型支援はデータとの対話のための強力な手段ですが、会話だけでは不十分とは言えません。産業エンジニアは答えだけでなく、行動を求めています。対話を通じて直接アウトカムを生み出したいのです。
「UID: X を UID: Y に変更してください」といったシンプルなプロンプトでデータを更新したり、「機器ごとの認定資格を示す棒グラフを作成してください」と指示するだけで、簡単に洞察を生成したりできる場面を想像してみてください。ビューの即時切り替えも「代わりにこのデータを表形式で表示」といったコマンドに追加可能です。さらにシナリオの実行がどれほど容易になるか考えてみましょう：「エリア X の予防保全を日付 Y まで推進」といった操作が実現するのです。
こうした操作を、ソフトウェアの深い知識やUIの手順を覚えることなく、システムに話しかけるだけで実行できるのです。会話型AIの価値は、単なる利便性を超えて、対話がアクションにつながることで真の業務インパクトを生み出します。
### 自律的な洞察
では、AIが質問やコマンドに応答するだけでなく、日々のニーズを予測できたらどうでしょう？想像してみてください―たとえば、産業エンジニアがシフトを始めるとき、チェックリストではなく、AIが重要なタスクを自動的に提示してくれる。
「今日回復すべき重要な装置は？」と尋ねる代わりに、「こちらが今日回復すべき最重要装置です」とAIが教えてくれる。
さらに、「なぜこれらの装置が重要なの？」と尋ねることで、理由も明確に説明されます。優先順位が提示されるだけでなく、その根拠も理解できるため、AIシステムへの信頼が生まれます。この透明性は、変化を受け入れるための鍵となり、産業エンジニアが新しい働き方に自信を持って移行するために不可欠です。
### まとめ
工場がより俊敏で柔軟な運営を目指す中で、AIによる会話型インターフェースや自律型エージェントは、半導体製造のワークフローにますます組み込まれています。
しかし、高品質なデータ、詳細なドキュメント、専門知識やベストプラクティスの統合といった基盤が依然として重要です。最先端のシステムであっても、その効果はそれが構築される情報の質によって左右されます。これらの基盤がしっかりしていれば、生成AIは意思決定をさらに進化・加速させ続けられるでしょう。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [MES in the mask shop: A collaborative approach (Part 4 of 4)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimizing-reticle-delivery-wafer-manufacturing-collaborative-strategies/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Reticle delivery aligned with fab wafer schedules is far more effective than arbitrary purchasing-driven deadlines
**Content:**
[ Part 3: Key milestones ](/semiconductor-blog/manufacturing-execution/photomask-manufacturing-key-milestones)
## What’s Inside
- [ Collaboration ](#index1)
- [ The mask shop’s requirements ](#index2)
- [ A novel approach? ](#index3)
- [ The cost of inflexibility ](#index4)
- [ MES as the coordinator ](#index5)
In the semiconductor industry, timely delivery of reticles is crucial for wafer manufacturing. Traditionally, the relationship between a wafer fab and its photomask vendor is driven by purchasing departments as a customer-supplier relationship, focusing primarily on pricing and on-time delivery per a pre-defined, contractual lead-time. However, this often leads to misalignment between the wafer fab’s needs and the contractual obligations of the mask shop, resulting in reticle delivery later than the fab’s need and costly premiums for expedited shipping.
### Collaboration
A closer collaboration between wafer fab and mask shop can significantly improve reticle delivery to meet the fab’s wafer schedule without expedited shipping or price premiums. This approach is particularly beneficial for full reticle sets that support the manufacture of new products. The key to this collaboration is a shared understanding of the date reticles are needed in manufacturing (the “need date”) to meet the schedule of the lead lot, which is the first lot for the wafer fab’s new product.
Based on their experience with similar reticles, the customer’s reticle design team likely has a good idea of how long it will take to manufacture each reticle needed for the new product. They also know they must complete their internal design process for each reticle in time to allow the mask shop sufficient time to build and deliver the reticle to the wafer fab before the lead lot arrives at the process step in which it is used. The design team can predict their deadline, then, by working back from the expected wafer schedule created by their new product planning team.
### The mask shop’s requirements
From the mask shop’s perspective, three critical dates must be known in advance for each reticle in the new product’s process flow. The first of these is the expected “tapeout” date – the date the reticle order and its accompanying design data will be received from the customer. The second and third critical dates are the wafer fab’s need date and the time required to ship the finished reticle to the wafer fab.
Given these dates, the mask shop can determine the lead time available to manufacture the reticle and a.) mobilize the appropriate resources to ensure they’re able to manufacture and ship the reticle to meet the wafer fab’s need date, or b.) push back well in advance if the lead time provided by the customer is inadequate. Assuming the wafer processing schedule is fixed, increasing the lead time would require an earlier tapeout date.
This shared understanding – created well before the first reticle for the new product tapes out – requires a lot of coordinated planning. It helps both the mask shop and the wafer fab understand the timing, anticipate the needs, mobilize the necessary resources, and proactively adjust to schedule changes to ensure the wafer fab is able to meet their product development commitments.
### A novel approach?
But why is this a novel approach? One might expect this level of coordination to be standard practice to ensure the wafer fab gets what they need when they need it, just as they do with industrial chemicals, spare parts, cleanroom supplies, or any number of other manufacturing needs. It’s almost inconceivable that factory operations would be delayed or otherwise impacted because one of the fab’s suppliers didn’t deliver on time.
It’s the uniqueness of reticles that drives this paradox. There is no bulk supply that can be monitored and resupplied before it’s exhausted. There also isn’t a reserve inventory to draw upon when stocks get low. Each reticle is unique, ordered only when needed, and built to specification. [As noted previously](/semiconductor-blog/manufacturing-execution/semiconductor-mask-shop-economics-overview/), the relationship between a wafer fab and its photomask vendor is driven by the fab’s purchasing team as a customer-supplier relationship, focusing primarily on pricing and on-time delivery per a pre-defined contract. This contractual arrangement does not – and cannot – take wafer fab need date into account.
However, this inability to consider the wafer fab’s timing needs often results in delays that impact the wafer fab’s new product commitments. Consider the chart shown in Figure 1, where there is coordination between the wafer fab and mask shop. In this case, reticles are consistently delivered to the wafer fab on time before the need date.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/08/figure-1.webp) Figure 1 – Reticle manufacturing planning schedule for a new wafer fab product
### The cost of inflexibility
Consider what may happen, however, using typical, pre-defined contractual lead times that ignore the wafer fab’s actual needs. If we assume tapeout dates remain constant, as does the lead lot’s expected progress along its process flow, nearly every reticle delivery might be expected to be late, as shown in Figure 2. This requires the lead lot to wait, and as a result, delays new product development. This can have significant follow-on effects for the wafer fab customer, not the least of which is a delay in the revenue that the new product would bring.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/08/figure-2.webp) Figure 2 – Reticle manufacturing planning schedule with contractual commitments
Aligning reticle delivery with wafer manufacturing through a collaborative approach can significantly improve on-time delivery, reduce costs, and enhance performance of both the mask shop and the wafer fab.
Tracking reticle manufacturing progress against a coordinated schedule allows the mask shop to allocate the resources needed to ensure on-time delivery and helps proactively identify potential problems along the way.
### MES as the coordinator
A Manufacturing Execution System (MES) plays a critical role in furthering a mask shop’s on-time delivery goals. By integrating MES [planning and scheduling](/semiconductor-blog/planning/boosting-productivity-with-advanced-planning-scheduling-solutions/) information, real-time data can provide insights into production status, equipment availability, and process performance. This enables the mask shop to make informed decisions, quickly address issues, and optimize resource allocation.
An MES can also facilitate communication and coordination between the mask shop and wafer fab, ensuring that any changes in the wafer fab’s schedule are promptly reflected in the mask shop’s production plan. This dynamic adjustment capability helps maintain alignment with the wafer fab’s needs and improves the reliability of reticle delivery.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [MES in the mask shop: A brief overview of mask shop economics (Part 2 of 4)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/semiconductor-mask-shop-economics-overview/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** The wafer fab’s need for perfect reticles drives the mask shop’s distinct business model
**Content:**
[ Part 1: Round versus square ](/semiconductor-blog/manufacturing-execution/round-vs-square-differences-between-wafer-and-reticle-manufacturing/)
[ Part 3: Key milestones ](/semiconductor-blog/manufacturing-execution/photomask-manufacturing-key-milestones/)
## What’s Inside
- [ The cost of perfection ](#index1)
- [ Cycle time ](#index2)
- [ Product mix ](#index3)
- [ Unpredictable demand ](#index4)
- [ How an MES can help ](#index5)
Mask shops play a pivotal role in the semiconductor industry. Manufacturing reticles is a low-volume, almost artisanal endeavor where each reticle ordered is unique and has its own distinct manufacturing challenges. Unlike high-volume semiconductor manufacturing, where millions of identical computer chips are mass-manufactured, the wafer fab’s economy of scale simply doesn’t exist in the mask shop, nor is there the same degree of process learning that is the inevitable result of manufacturing the same thing over and over. This combination of uniqueness and customer demand for consistently perfect results shapes the mask shop’s business model in unusual and unexpected ways. (Read our [previous article ](/semiconductor-blog/manufacturing-execution/round-vs-square-differences-between-wafer-and-reticle-manufacturing/) to learn about key differences between mask and wafer manufacturing.)
### The cost of perfection
Expensive tools and the resulting depreciation expense are a primary cost driver in both mask shops and wafer fabs. However, high-volume manufacturing affords some mitigations to the wafer fab that don’t exist for the mask shop; these permit statistical sample plans that allow most lots to avoid metrology and inspection steps while still assuring a high degree of product quality. In the mask shop, the need to measure and inspect every reticle – driven by the requirement to consistently deliver a perfect product – amplifies capital and depreciation expenses, as more tools are required to achieve the necessary factory output.
In some situations, defective reticles can be repaired during manufacturing, but this too requires more specialized tools and results in higher costs and increased cycle time.
Reticles that cannot be repaired must be scrapped and a new “attempt” started because the mask shop must deliver a perfect reticle to its customer. This means higher material costs, because an additional mask blank must be consumed for each new attempt – an expense that ranges from hundreds of dollars for a commodity mask to tens of thousands of dollars for a high-end extreme ultraviolet (EUV) reticle.
### Cycle time
Manufacturing cycle time can also be a factor driving mask shop costs. Cycle time can vary significantly – even for reticles of similar technology – because of the unique nature of each reticle order. The mask shop can quote an expected cycle time when a reticle is ordered based on the processing history of masks using a similar process technology, but the actual cycle time can vary significantly depending on how many attempts it takes to build a perfect reticle. If manufacturing goes beyond the committed ship date, the mask shop may have to pay for expedited shipping to minimize the delay to the customer.
In cases where a prime customer has an urgent need, the mask shop may take a calculated risk and start multiple attempts in parallel, betting that one of them will finish quickly enough to meet the customer’s deadline. Needless to say, this also incurs additional material costs for the mask shop and reduces overall capacity, as manufacturing the additional reticle attempts consumes valuable tool processing time.
Cycle time is also influenced by numerous other variables, many of which are beyond the mask shop’s control. This includes hidden factors like mask data transfer time and data preparation time before manufacturing begins, and random shipping delays to the customer after manufacturing is complete. These also can significantly increase cycle time.
### Product mix
Capacity is a complex function of yield, number of process tools, processing time, the number of steps in a process flow and, in wafer fabs, the number of die per wafer. Optimizing these parameters can increase capacity which can, in turn, increase revenue. This makes sense if you define capacity as the number of things you can manufacture in a given amount of time – a good bet for high-volume wafer fabs with low product mix.
But mask shop capacity is less about the number of reticles manufactured and more about the mix of reticles manufactured. In general, there are two types of reticles: binary and phase shift. Binary reticles are simpler to build, require far fewer process steps (a third or less than the phase shift reticles), and have consistently higher yield (that is, less need for multiple attempts to manufacture a perfect reticle). If capacity is all about manufacturing the greatest number of reticles, you’d want all reticles ordered to be binary reticles.
Unfortunately, the price of a binary reticle is a fraction of the price of a phase shift reticle. Phase shift reticles can be sold for as much as 20 times that of binary reticles. A little arithmetic tells us that despite more process steps, longer processing times, and lower yield, a mask shop would likely have far greater revenue if they only manufactured phase shift reticles!
### Unpredictable demand
However, the order mix of relatively simple binary reticles and much more complex phase shift reticles is essentially random, impacting both mask shop capacity and revenue. This random order mix can also increase cycle time variability, making lead-time prediction unreliable. Lack of predictability can make managing capacity and cycle time a delicate balancing act within the mask shop.
### How an MES can help
A Manufacturing Executions System (MES) is crucial for achieving the mask shop’s critical performance and efficiency objectives. An MES provides [real-time data and insights](/semiconductor-blog/manufacturing-execution/message-bus/), enabling better decision-making and efficient management of production processes. By effectively utilizing the capabilities of an advanced MES, mask shops can optimize scheduling and tool utilization, reduce cycle times, and improve overall yield and efficiency, improving their ability to meet high customer standards for quality and timeliness.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [MES in the mask shop: Round versus square, wafer versus reticle (Part 1 of 4)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/round-vs-square-differences-between-wafer-and-reticle-manufacturing/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Comparing operational efficiency and product quality across two familiar manufacturing paradigms
**Content:**
[ Part 2: Mask shop economics ](/semiconductor-blog/manufacturing-execution/semiconductor-mask-shop-economics-overview/)
## What’s Inside
- [ Round world vs. square world ](#index1)
- [ Yield vs. efficiency ](#index2)
- [ Process efficiencies ](#index3)
- [ Process control ](#index4)
- [ The role of the MES ](#index5)
Given the importance of reticles in wafer manufacturing, mask shops are critical to the semiconductor industry. However, there are fundamental differences – even a fundamentally different paradigm – between wafer fab manufacturing and reticle manufacturing. While both are considered discrete manufacturing, that’s where the similarity ends.
### Round world vs. square world
Nowhere is the paradigm difference between wafer manufacturing and reticle manufacturing as obvious as in the very shape of the items being manufactured. Wafers are round. Reticles are square. Indeed, this characteristic led to the colloquial description of wafer manufacturing as “round world” and reticle manufacturing as “square world.”
The round world’s pervasive view of reticle manufacturing is a bit dismissive. After all, it only takes some tens of process steps to manufacture a reticle, whereas it takes many hundreds of process steps to manufacture a semiconductor device. So how hard could it be to manufacture reticles?
The comparison of manufacturing volume furthers this rather dismissive view; wafer fabs are typically high-volume manufacturing, building massive quantities of chips that are ultimately sold on the mass market. By contrast, mask shops operate as “job shops,” building a single unique reticle for each order. However, each of those reticles must be perfect, or the wafer fab’s yield will suffer. This is where square world manufacturing is severely underestimated.
### Yield vs. efficiency
Square world yield is binary; a reticle is either good or bad. Each reticle must be perfect when shipped to a wafer fab customer or it is scrapped and the process restarted until a perfect reticle is manufactured. Round world yield, on the other hand, is continuous. With hundreds of die per wafer and 25 wafers per lot, there are thousands of candidate die per lot that can be shipped to customers. It’s possible that even with several defective die on each wafer, the lot’s yield is still considered acceptable. It’s even possible that several wafers can be scrapped for the lot to have reasonably good yield.
However, while yield is important in round world, manufacturing efficiency is perhaps even more so, because wafer fab process flows commonly consist of many hundreds or even thousands of steps and cycle time is measured in months.
But the calculus is quite different in square world, where process flows are only a few tens of steps and [cycle time ](/semiconductor-blog/manufacturing-execution/mes-strategy/)is measured in hours or days. Here, the focus is on shipping a perfect reticle on time. That is the measure of efficiency and on time delivery is the key metric. The mask shop revolves around customers’ delivery deadlines and will go to great lengths to meet them – even to the extent of building multiple duplicate copies of a reticle with low expected yield simultaneously to improve the odds of meeting the deadline. To the mask shop’s wafer fab customers, a delayed reticle may mean that the wafer fab can’t expand production on time or that production of a new device is delayed waiting for a reticle, resulting in a potentially significant monetary impact.
### Process efficiencies
High manufacturing volume enables several round world process efficiencies. Not every wafer or every lot needs to be measured or inspected to ensure product quality, and this can significantly increase overall factory output. A statistical sample plan can define the fraction of lots that need to be measured or inspected to guarantee a statistically high probability of good overall product quality.
But that’s definitely not the case in square world. Given that each reticle is unique and the manufacturing volume is relatively small, at least compared to the wafer fab, every reticle must receive both metrology and inspection to guarantee that each is perfect before shipping to the wafer fab.This requirement for 100% metrology and 100% inspection not only means higher overall cycle time, but it also alters the basic economics of the mask shop because additional metrology and inspection tools are required to minimize the impact on cycle time and attain the expected factory output.
### Process control
Process control is another area where there are significant differences between round world and square world. To ensure that consistent process control is maintained in high-volume manufacturing, statistical process control (SPC) is used extensively in round world to monitor the metrology and inspection results of the fraction of wafers that pass through those steps. Traditional SPC rules can be used to determine if processes are in control or trending out of control. This provides an effective early warning system for the wafer fab to identify potential process problems and correct them before they become yield problems.
By contrast, SPC is of limited use in square world for two important reasons. The first is that the mask shop’s relatively low manufacturing volume doesn’t provide a large enough sample size to be statistically valid. Even if the manufacturing volume were high enough to exceed the threshold for a statistical sample size, the fact that each reticle is unique invalidates traditional SPC, which relies on the manufacture of identical items using identical processes.
### The role of the MES
Wafer manufacturing versus reticle manufacturing. Round world versus square world. Each has its own distinct manufacturing paradigm. For both, however, an advanced [Manufacturing Execution System (MES)](/semiconductor-blog/manufacturing-execution/mes-part-1/) can play a crucial role in improving operational efficiency and product quality by providing real-time data and insights into production processes.
For the mask shop, the MES facilitates seamless communication across the factory, optimizing resource allocation, minimizing delays, and ensuring on-time delivery. By facilitating the creation of detailed process flows and simplifying process flow optimizations in a structured, controlled manner, an MES also contributes to the efficient manufacture of perfect reticles.
An MES can help mask shops achieve higher throughput, improved quality, and better alignment with wafer fab customer expectations that perfect reticles will be shipped on time every time.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [MES in the mask shop: Key milestones in photomask manufacturing (Part 3 of 4)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/photomask-manufacturing-key-milestones/)
**Published:** August 8, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Critical milestones accommodate the different concerns of the mask shop and its customers
**Content:**
[ Part 2: Mask shop economics ](/semiconductor-blog/manufacturing-execution/semiconductor-mask-shop-economics-overview/)
[ Part 4: Collaborative approach ](/semiconductor-blog/manufacturing-execution/optimizing-reticle-delivery-wafer-manufacturing-collaborative-strategies/)
## What’s Inside
- [ Order-centric ](#index1)
- [ Manufacturing-centric ](#index2)
- [ Monitoring and managing milestones ](#index3)
In our blog: [A brief overview of mask shop economics](/semiconductor-blog/manufacturing-execution/semiconductor-mask-shop-economics-overview/), we discussed many of the challenges of reticle manufacturing, particularly the focus on consistently building and shipping perfect reticles on time. It is essential to track critical milestones within the mask shop to monitor reticle manufacturing efficiency and the ability to meet customers’ timing expectations. The end goal is to ensure high factory efficiency, product quality, and customer satisfaction.
Mask shop milestones can be divided into two main categories: order-centric and manufacturing-centric.
### Order-centric
Order-centric milestones focus on the customer’s perspective. A mask’s manufacturing journey begins when a reticle order is received from a customer and recorded within the [Manufacturing Execution System (MES)](/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/) as the Order Received Date. Key customer dates like the Contract Shipping Deadline and the Requested Shipping Deadline arrive with the order and accommodate both contractual obligations and special customer requests based on the specific date the reticle is needed within the wafer fab (commonly referred to as the wafer manufacturing need date). A set of manufacturing specifications also accompanies the order, indicating processing tolerances and limits that ensure the necessary quality of the finished product.
Perhaps the most important item arriving with the reticle order is the design data defining the reticle pattern itself. A reticle data file can be many gigabytes in size, and over a terabyte for advanced masks. Even when transferred over high-bandwidth commercial data networks, mask data transfer can take many hours. This is especially the case if there are multiple, competing data transfers occurring simultaneously. The Order Start Date is recorded when the data transfer is complete and this initiates the order’s cycle time clock. From the customer’s perspective, everything beyond this point is within control of the mask shop. The cycle time clock then ends when the finished reticle is shipped from the mask shop, as recorded by the Order Ship Date.
The mask shop and its customers sometimes disagree about how to measure cycle time. From the customer’s perspective, the cycle time clock should begin when they press the “Go” button to transfer the mask order and start the reticle data transfer and should end when the finished reticle is delivered to their factory.
However, the mask shop can’t control the data transfer time. This is a function of the customer’s reticle data size and, at least partially, of the bandwidth of the customer’s commercial data transfer pipe. The mask shop also cannot control the time it takes a shipper such as UPS or FedEx to physically deliver the reticle to the customer’s factory. Since these are all out of the mask shop’s control, they are out of bounds from a cycle time perspective.
### Manufacturing-centric milestones
Manufacturing-centric milestones focus on the mask shop’s manufacturing process – the things within the mask shop’s control.
Once the data transfer from a customer is complete, the data undergoes a process called “fracture,” that converts the raw design data into a format compatible with the mask shop’s patterning tools. The fracture process can also take hours, and its duration is recorded by the Fracture Start Date and Fracture End Date.
Physical processing begins once the fracture process is finished and the fractured data is transferred to the first tool in the manufacturing process, the one that writes the reticle pattern onto a mask blank. However, physical processing rarely begins right away. The reticle must wait until orders received ahead of it have completed processing on the write tool, a period commonly called the Write Queue Time. In mask shops manufacturing advanced masks this step also can last many hours or even days.
Once processing finally begins at the first manufacturing step, the Manufacturing Start Date is recorded and the manufacturing’s cycle time clock starts. From the mask shop’s perspective, everything before this point – data transfer time, fracture time, write queue time – is out of their control and irrelevant in evaluating manufacturing efficiency.
Within the manufacturing lifecycle of each reticle, the Track-In Date and Track-Out Date bookend each step in the process flow, and the Processing Start Date and Processing Complete Date record when physical processing begins and ends within each step.
Once again, a reticle may have to wait for previous reticles to finish processing before it can start. A reticle’s queue time is measured by the time between the Track-In Date and the Processing Start Date. Changes to the average queue time for individual steps in the process flow – the average time reticles wait at a step before beginning processing – can indicate that a specific process step may be a “bottleneck” process. This demands special attention from both the production and engineering staff to ensure tools performing that process remain available and running.
Where the Manufacturing Start Date starts manufacturing’s cycle time clock, the Manufacturing Complete Date marks the completion of physical mask processing and stops the clock. The average manufacturing time – the average time between these – is a critical metric indicating the mask shop’s operational efficiency. The lower, the better.
Finally, the Shipping Deadline – the sooner of the customer-specified Contract Shipping Deadline or Requested Shipping Deadline – defines when a mask must be shipped per the mask shop’s production plan to reach the customer’s factory using their chosen method of shipment. (The Ship Date records when the mask is handed off to the shipper for transport to the customer.)
### Monitoring and managing milestones
Monitoring and managing these milestones for each reticle ensures consistent on-time delivery. Furthermore, monitoring these milestones over time is a barometer into a mask shop’s overall health and manufacturing efficiency and can offer key insights into opportunities for improvement.
The Manufacturing Execution System (MES) provides real-time data on manufacturing processes, ensuring that each milestone, as well as other key manufacturing metrics, are accurately recorded and the insights made available to [optimize process flows, reduce cycle times, and enhance overall efficiency](/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/).
The MES also facilitates communication between everyone within the mask shop, ensuring that everyone is aligned with production goals and timelines to effectively meet customer expectations.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [通用数据模型支持快速部署生产效率解决方案——解决方案（第 2 部分，共3部分）](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-2/)
**Published:** March 28, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** 通用数据框架支持快速部署工厂生产效率和供应链解决方案
**Content:**
[ 第 1 部分：挑战 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-1/)
[ 第 3 部分：派工与报告 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-3/)
在当今半导体工厂中，为工厂生产效率解决方案生成有效的数据变得越来越困难和耗时。
为了弥合这一差距，应用材料公司正在开发一种通用数据模型，该模型使用应用材料公司APF（先级生产效率平台）软件环境中的提取、转换和映射 (ETL) 功能模块。
下图 1 显示了构建通用数据模型模式所涉及的步骤
### Smartfactory生产效率解决方案组件
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/step-involved-in-building-the-common-data-model-schema.jpg) 从派工到自动化的通用框架——基于Smartfactory平台 ETM， 通用数据模型 (CDM)，EngineeredWorks，解决方案 UI > 开箱即用解决方案
应用材料公司的解决方案利用开箱即用的 APF 适配器集成来自各种来源的数据，如 CIM 解决方案中的 MES、MCS 和其他应用程序。
图 2 显示了 APF 存储库中从各种解决方案中截获的数据
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/the-data-intercepted-from-various-solutions-in-APF-repository-.jpg)
数据在 APF 存储库被复制后，系统就会使用 APF 宏将其映射到通用数据模型架构，如图 3 所示
### 提取、转置和映射 (ETM)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/extract-transpose-map.jpg)
数据转换成通用数据模型格式后，就可以应用于各种工厂生产效率解决方案中。
图 4 显示了各种表的部分快照
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/the-some-of-the-snapshot-of-various-tables-2.jpg)
最近，应用材料公司一直使用这种方法，实现了在 6 个月内快速部署工厂生产效率解决方案。
[ 第 1 部分：挑战 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-1/)
[ 第 3 部分：派工与报告 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-3/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi, Semi, Common Data Models
---
### [通用数据模型支持快速部署生产效率解决方案——挑战（第 1 部分，共3部分）](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
**Published:** March 29, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** 快速部署工厂生产效率和供应链解决方案面临的数据挑战
**Content:**
[ 第 2 部分：解决方案 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-2/)
在当今的晶圆厂中，集成和协调来自不同 CIM（计算机集成制造）应用程序的数据变得越来越困难和耗时。 事实上，这是目前快速部署这些系统的主要障碍，由此也影响了晶圆厂快速实现目标生产效率的能力。
所有现代晶圆厂都面临着此项问题，该问题对于下列类型的公司来说尤其尖锐：(1) 建造半导体工厂的新公司，这些公司之前的经验有限，而且未获得快速部署所需的技术资源；(2) 外包半导体封装和测试 (OSAT) 或封装、测试和包装 (ATP) 公司，其业务运营的模式越来越像晶圆厂；(3) 持续受行业整合影响的公司。
此问题的根源在于制造商使用广泛的决策支持和制造执行系统 (MES) 来满足客户承诺。 典型的 CIM 应用系统包括规划、排程、派工、自动化和报表。 图 1 描述了这些系统的交互情况。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/cim-planning-hierarchy-for-semiconductor-manufacturing.jpg) 图 1：用于半导体制造的 CIM（计算机集成制造）规划层次结构
这些系统依赖于来自不同 CIM 组件的大量数据，并且随着设备尺寸的不断缩小和晶圆厂逐步采用新技术，数据需求正在持续增长。
这些系统中包含的数据涉及订单、产品、工艺步骤、设备和操作人员。 例如，与订单相关的数据可能包括产品名称、交货日期、客户名称、数量、物料清单等。 与工艺步骤相关的数据可能包括步骤名称、顺序、设备认证、处理时间、采样和其他相关信息。
与此同时，设备相关的信息可能包括设备名称/类型、位置、安装、批次规模和预防性维护 (PM) 时间表/持续时间。 此外，此类信息还可能包括辅助资源，如标线、探测卡等。 操作人员相关的数据，例如，也可能需要证书和轮班时间表。
通常，上述数据驻留在具有各自集成方法和数据结构模型的不同 CIM 组件中。 在某些情况下，数据不存在、不完整，或者是在某个人的笔记本电脑上手动维护。
此外，工厂车间的派工和排程决策正越来越多地利用来自先进过程控制 (APC) 系统的额外数据（run-to-run、故障检测和分类等）\[1\]。 自动化物料处理 (AMHS) 数据 \[2\] 也需要纳入决策过程，因为如今 300mm 工厂、200mm 工厂和 ATP 工厂都在利用自动导向车辆 (AGV) 和机器人来提高生产性能 \[3\]。
同时，移动应用程序\[4\] 正被用来促进生产效率提升，这些应用程序可能需要来自不同工厂来源的实时数据。
此外，ITRS 路线图 \[5\] 表明整体工厂排程在提高设备利用率、生产周期和按时交付方面起着关键作用，实现这一点意味着需要集成更多的数据。 路线图定义了对实时预测排程工具的需求，该工具将整合预测性维护 (PdM)、PM 排程、设备健康监控 \[EHM\] 和资源排程数据。
通常，所有這些系統的集成是其部署中最耗時的方面之一。 因为标准数据模型尚未定义，可能需要 6 到 12 个月的时间。 此外，还必须花费相当多的时间来验证和清理数据。
在过去，晶圆厂通常通过精确复制的方法来满足这些需求，厂里有很多有经验的技术人员可以将这些系统提升到最佳使用状态。
现在可能不再如此了，因此必须确定新的模型来维护和实现数据自动化。 人们已努力做了一些工作，来开发半导体晶圆厂的详细数据模型和框架 \[6\]，行业和学术机构已经表示需要对决策支持系统的数据模型进行标准化。 SEMATECH（半导体制造技术联盟）的建模数据标准 \[7\] 就是一个例子。
但这方面几乎没有任何进展。
为了弥合这一差距，应用材料公司正在开发一种通用数据模型，该模型使用应用材料公司 APF（先进生产效率平台）软件环境中的提取、转换和加载 (ETL) 功能模块。
除了通用数据模型，公司还在开发预先构建生产效率的工具，以帮助客户实现快速系统部署和生产效率更快速提升。
**引用：**
\[1\] Marcel Stehli, Daniel Zschabitz, Thomas Jaehnig, “Bridging the Gap – Integrating APC Constraints and WIP Flow Optimization to Enhance Automated Decision-Making in Semiconductor Manufacturing”, ASMC 2015
\[2\] Christian Hammel, Robert Schmaler, Thorsten Schmidt, Joerg Lubke, Matthias Schops, Ulrich Horn, Marcin Mosinski, “Empowering Existing Automated Material Handling Systems to Rising Requirements”, ASMC 2016
\[3\] Didier Chavet, Shekar Krishnaswamy, “Factory Automation is Key to Sustainable Manufacturing at Western Digital at Shanghai Assembly and Test facility”, Nanochip-Fab-Solutions/december-2016
\[4\] Didier Chavet, Shekar Krishnaswamy, “Mobile Applications to Enhance Manufacturing Productivity in Advanced Packaging”, IWLPC (Wafer-Level Packaging) 2014 conference proceedings
\[5\] International Technology Roadmap for Semiconductors 2.0, 2015 edition Factory Integration
\[6\] Heshan Li, Jose A. Ramirez-Hernandez, Emmanuel Fernandez, Charles R. McLean and Swee Leong, “A Framework for Standard Modular Simulation in Semiconductor Wafer Fabrication Facilities”, Proceedings of the 2005 winter simulation conference
\[7\] SEMATECH, “Modeling data standards, version 1.0”, Technical Report, SEMATCH Inc., Austin, TX, 1997
[ 第 2 部分：解决方案 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-2/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi, Common Data Models
---
### [通用数据模型支持快速部署生产效率解决方案 – 派工与报告（第 3 部分，共 3 部分）](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
**Published:** March 27, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** 借助 SmartFactory Dispatching解决方案，可在 6 个月内将生产周期缩短 10% 。
**Content:**
[ 第 2 部分：解决方案 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-2/)
不论是在半导体的前道晶圆厂，还是后道的封装、测试和包装（ATP）工 厂，高效灵活的车间生产派工对于提高生产效率来说至关重要。 派工是指决定接下来应进行哪一道工序（最好能够实时进行），然后将其分配至合适的设备或站点，并确保其能够在最短队列等待时间内抵达正确的设备或站点所在之处的流程。
虽然建立高效的派工系统至关重要，但快速实现关键的工厂生产效率和上市目标也同样重要。
实现这些目标的一种方式便是实现自动化派工流程。 应用材料公司 SmartFactory Dispatching & Reporting解决方案是一套自动化决策系统，其基于规则，能够为前道和 ATP 工厂执行先进的实时调度、排程和报表策略。 其部署于应用材料公司预构建的 EngineeredWorks™中，具备可开箱即用的自动化逻辑，运行于应用材料公司经验证的 APF 平台上，能够快速部署派工系统（图 1）
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/step-involved-in-building-the-common-data-model-schema.jpg) 图 1： SmartFactory 生产效率解决方案组件
### 案例 1：在 150mm 晶圆厂中部署派工系统
2015 年，一个在欧洲和亚洲拥有数家工厂的客户开始与应用材料公司合作，希望能够为其位于欧洲的一家工厂提高关键瓶颈解决工具的正常运行时间利用率。
从一开始，客户便决定要使用客制化的派工方案。 他们从应用材料公司购买了 APF 许可，然后利用应用材料公司所提供的按工时和按材料付费服务 (T&M)，实施了全球派工规则，该规则侧重各条生产线均衡，从而更好地为瓶颈解决工具提供服务。
首次实施花费了一年的时间。 开发工作本身持续了约 6 个月，而剩余的时间用于在晶圆厂推出派工规则，因为这对于生产人员来说是一个重大的变化。 我们还采取措施，提高了派工合规性，并收集各方意见，改进派工规则的功能。
然而，第二年，这家公司意识到需要额外的派工规则来管理队列等待时间控制和批处理，同时还需要对现有的派工规则进行改进。 然而，第二年，这家公司意识到需要额外的派工规则来管理队列等待时间控制和批处理，同时还需要对现有的派工规则进行改进。
此时，应用材料公司提议可以实施基于 EngineeredWorks 的派工规则，客户同意了。 如图 2 所示，项目范围包括开发一个 ETM（抽取、转换和映射）层来将工厂的 MES 系统映射到通用数据模型中，同时还要开发额外的派工规则和报表系统。
通过此方法，应用材料公司和客户得以对 基于EngineeredWorks 的派工规则进行客制化配置，从而在短短 3 个月内便能够满足工厂的需求。
在这一整年的推广和实施过程中，客户还决定在其亚洲的工厂使用基于EngineeredWorks 的派工规则。 在欧洲工厂成功实施之后，客户在一周之内便在亚洲工厂部署了相同的解决方案；与最初的全定制化部署花费了近乎两年的时间相比，部署时间大幅缩短。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/deployment-plan-new-min.png) 图 2： 部署方案：为客户的 150mm 前道晶圆厂实施开箱即用的 基于EngineeredWorks 的派工规则。
除了显著减少派工的部署时间外，整个晶圆厂正常运行时间利用率显著提高，该公司也从中获益。 图3显示了基于EngineeredWorks 的派工规则受到的影响。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/equipment-uptime.jpg) 图 3： 该图显示了在 150mm 前道晶圆厂实施基于EngineeredWorks 的派工规则之后，设备正常运行时间利用率得以改善。
### 案例 2：为封装、测试和包装工厂部署派工解决方案
如今，很多 ATP 工厂正在利用自动导引车 (AGV) 和机器人来提高生产效率。同时工厂也使用了许多移动应用来推动生产效率的提高，而这些应用都需要从不同工厂来源获取实时数据，以实现最佳性能。
一位应用材料公司的 ATP 客户在美国和亚洲有多家工厂，他们也遇到了类似的问题。 客户管理层选择了应用材料公司基于 EngineeredWorks 的派工规则，作为该公司迈向完全自动化的第一步， 希望在其所有工厂进行部署。该项目预计能够至少提高 8% 的工厂利用率。 实施这些功能的第一步便是要实现自动化派工决策。 基于EngineeredWorks 的派工规则的功能不仅可以做到以上这点，还能够为MES 界面、排程以及物料控制系统（MCS）软件（用于控制 AGV 设备）提供预构建的接口。
初期项目是 8 个月内在 4 家工厂部署基于 EngineeredWorks 的派工规则，该项目实施方案如图 4 所示。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/precursor-to-fully-automating.jpg) 图 4： 一位客户为其美国和亚洲的四家 ATP 工厂实现全自动化打造标杆，需要在这四家工厂部署应用材料公司的基于 EngineeredWorks 的派工规则。 上方的项目时间表显示了该项目如何在 8 个月内完成。
应用材料公司和客户共同制定该项目方案，由应用材料公司根据客户的需求牵头进行 EngineeredWorks 的开发和定制化工作，而客户则负责将其数据映射到通用数据模型中。 应用材料公司和客户共同负责该项目的落地推广，这能够让他们快速解决出现的任何问题。
所有开发工作和初始部署首先在其中一家重点工厂进行，成功实施之后，基于EngineeredWorks 的派工系统部署到其余三家工厂。 尽管这个方式颇具挑战性，因为这四家工厂处在不同的地理位置，但应用材料公司除了在第一家重点工厂提供开发和集成的专家资源之外，还能为其余每家工厂提供本地的部署资源。
初始部署本计划在几个月内完成，但由于数据可用性和准确性问题，花费了更长的时间。 但是，双方团队通力合作成功解决了这一问题，基于EngineeredWorks 的派工系统如期在 8 个月内于四家工厂成功部署。
此外，部署后初步调查结果表明，工厂的设备利用率提升达8% 以上。 客户现在正计划实施自动导引车运输解决方案。
[ 第 2 部分：解决方案 ](/zh-hans/semiconductor-blog/productivity-zh-hans/rapid-deployment-part-2/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi, Common Data Models
---
### [拉近和实际生产的距离](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
**Published:** January 14, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 推动“S 曲线”，使您的晶圆厂在整个生命周期内都能保持良好运营。
**Content:**
从开发到生产的过程中，随着设备质量和性能规范变得更加严格，工厂自动化解决方案，例如由应用材料公司自动化产品部 (APG) 开发的解决方案，能够助力客户实现重要的良率、产出和成本改善目标。
在本篇博客中，我会着重介绍利用“S 曲线”框架可以使一个新的晶圆厂实现盈利最大化的一些关键因素。本文说明了使用先进自动化软件解决方案，可以在晶圆厂生命周期的开发阶段和转至批量生产阶段带来价值。
### S 曲线是什么？
图 1 曲线被称为 S 曲线，展示了晶圆厂从生产第一个硅晶圆开始，通过持续改进，提升至全面释放生产潜力的生命周期。如图表所示，此生命周期的要素包括：
- **时间** (x 轴)。
- **良率**和**产出** (y 轴)。
- **生产目标** (绿色粗线), 或各个生产阶段的理想产出和良率提升情况。
- **实际生产情况** (橙色锯齿线) 必须由客户管理。
- **示例问题** (灰色椭圆) 这些问题会阻止晶圆厂达到目标产能和良率 (注意，这些只是示例；对于一些晶圆厂来说，根据产量和产品的不同，其他问题可能更为关键)。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/11/s-curve-figure1.png) 图 1. “S 曲线”，展示了生产目标（绿线）与实际生产情况（橙线）， 以及实现产能和良率目标面临的各种障碍（灰色椭圆）
### 推进 S 曲线
图 1 中未明确展示晶圆厂必须优化管理，以确保实际生产情况满足或超过生产目标的关键方面或因素。这些因素是： - 良率
- 成本
- 按时交付
- 产出
优化工作可以确保实际生产情况满足生产目标，这种工作被称为 **“推进 S 曲线”**。在您的晶圆厂，S 曲线推进的情况如何？ 成功推进曲线需要注意什么？
### 越早越好
S 曲线的要点是，良率学习和批量生产在 **新产品生命周期的早期** 比在 同一产品生命周期的后期更有价值。这是因为“新”半导体器件通常在其生命周期的早期就达到了较高的销售价格。对于造价 200 亿美元或更多的晶圆厂来说，绿色曲线和橙线之间的区域价值 **数亿美元甚至数十亿美元**。这代表着未实现的潜力，争取时间在这个过程中尤为宝贵；延迟意味着需要更长时间才能获得回报。
### 我们成功推进S曲线的秘诀
为了帮助晶圆厂实现这一隐藏的潜力，并成功推进 S 曲线，我们的 Applied SmartFactory™ 计算机集成制造 (CIM) 控制和生产力套件提供一种经过验证的成功部署方法，助力您管理晶圆厂生产，该方法可分两个阶段实施，帮助新晶圆厂实现：
- **首个硅晶圆制造。** 在此阶段，客户可以开始试产，缩短其生产计划和学习曲线，并提升其生产产能。
- **批量生产。** 在此阶段，客户可以减少工艺变化和晶圆报废，稳定良率，提高单位利率，优化产能盈利曲线。
这种方法的关键在于，要在需要时部署软件解决方案，使实际生产情况更接近目标（参见图 2）。通过在需要时部署软件，晶圆厂管理者可以处理和应对整个生产过程中的挑战，缩短上市时间、提高质量和降低报废率。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/11/s-curve-with-solutions-figure2.png) 图 2. S 曲线，展示了当需要让实际生产情况更接近目标时， 我们部署经过验证的软件自动化的方法
SmartFactory 解决方案构筑于超过 30 年的软件和晶圆制造经验，在世界上的先进晶圆厂得到了验证，并在以下方面具有优势： - **全面集成**组件，消除低效和脱节的系统，减少部署时间和 IT 支持成本
- **预先构建的自动化逻辑** 通过 Applied EngineeredWorks™ 可以帮助客户加速部署
- **开箱即用** 方法消除大量定制成本，并使用户能够完全控制晶圆厂生产行为
### 总结
无论哪个环节或产品，当今半导体制造面临严峻挑战。晶圆厂管理者必须满足业务发展和生产目标，并能够快速应对变革，以满足不断变化的业务模式和技术需求。
无论您是需要快速采用新工艺、运行新技术，还是更充分地利用您现有的设备，我们的软件应用广泛，可以帮助您“推进 S 曲线”，确保实际生产情况满足或超越您的生产目标。在这种环境下，CIM 自动化（如 Applied SmartFactory 套件所提供的功能）对于在晶圆厂生命周期每个步骤实现重要良率、产出和成本改善而言至关重要。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Popular
---
### [借助 AI/ML 技术解决生产效能和供应链问题](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/productivity-supply-chain-using-ai-ml/)
**Published:** September 25, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 预构建的 AI/ML 模型能够提高晶圆厂的生产效能、改进 KPI
**Content:**
SmartFactory AI Productivity 是当前生产环境中唯一可以与排程、派工和全自动化解决方案集成的工业 AI/ML 平台。通过与生产环境集成，半导体制造商有望在短期内以较低的投入来降低生产周期、提升利用率、增加产出并提高良率，当前任何其他平台都无法做到这一点。
### 文稿
今天，世界正迅速转向人工智能和机器学习技术，以满足每个商业领域的市场需求，制造业也不例外。对于更智能、更灵敏、更注重质量的需求，现在比以往任何时候都更加迫切。
应用材料公司全新推出 SmartFactory AI ，借助这个首次面向半导体行业高度集成 CIM 和 AI 的平台，建立您独有的竞争优势，使用智能算法帮助您应对来自生产力和供应链的挑战。通过流媒体和学习大数据、端到端模型开发和部署，优化您的多个目标。
SmartFactory AI 可解决影响晶圆厂生产效率和良率的两项关键挑战：第一，预测模型的不足，包括批次生产周期、动态瓶颈和良率预测；第二，寻找最佳逻辑或参数值，以更优的方式控制生产流程或设备的问题，同时考虑实时和未来状态。
SmartFactory AI 是唯一可以与排程、派工和全自动解决方案集成的工业 AI 平台，可帮助您实现前所未有的产出、生产周期、利用率和良率的改善。在生产中，SmartFactory AI 收集数据，训练模型，将其部署到生产环境中，并实时监控其性能以了解该模型的运行情况。如果模型的准确性出现波动，可自动进行重新训练。
UI 解决方案可显示模型评估和性能表现的结果。SmartFactory AI 通过提供自动化模型构建、培训和部署功能以及用户友好的 UI 解决方案来推动制造业生产力变革。这种高集成度的解决方案使制造商能够在短短六个月内完成部署——这是通常开发单个模型所需时间的四分之一。
SmartFactory AI 集成到现有的 SmartFactory ——Advanced Productivity Family——用户无需学习其他环境或开发语言。工程师可以使用预构建的机器学习模型或配置关键参数，集中应对晶圆厂的特定挑战，深度解决问题。利用 SmartFactory AI 提高您的生产效率，建立您的竞争优势。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [SmartFactory AI Productivity 可在更短时间内自动调整派工规则参数](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactory-ai-productivity/)
**Published:** October 16, 2023
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** 揭示智能制造对半导体运营的变革性影响——提升生产力、效率、决策能力和数据安全性。以小时而不是以天为单位找到最佳值。
**Content:**
半导体前道工厂和半导体后道封装、测试和包装工厂都会在部署本地派工规则和排程的同时部署全局派工规则，以提高生产效率。 通常，全局规则通过部署生产线平衡算法来确保满足交货日期并优化瓶颈解决工具的利用率。 这些生产线平衡算法具有不同的参数，需要根据工厂状态对给定的产品组合进行调整。 如今，这些参数是手动调整的，或者在某些情况下， [使用模拟建模功能](/zh-hans/blog/dispatching-scheduling-algorithms-impact/)。 很难计算这些参数对工厂中所有设备、所有产品和工艺步骤的影响。 因此，手动调整参数可能会对工厂 KPI 指标产生负面影响，而使用模拟技术找到一组最佳参数又会耗费大量时间。 本案例详细介绍我们如何使用 SmartFactory Productivity AI 在大幅缩短的时间内自动调整派工规则参数。
请看下图 1 中的示例。 根据全局规则，有四个参数用于确定瓶颈解决工具和生产线平衡阈值，以根据在制品 (WIP) 的小时数来判断设备是否处于不足、充足或高负荷状态。 表格显示了这些参数可能的取值范围。 要为给定的工厂状态找到这些参数的最佳值，一种方法是运行模拟模型。 在每次模拟中，我们选择不同的参数值组合，并测量由此产生的 KPI指标，这种方法在文献中被称为“网格搜索”。 每次运行都是为期 90 天的模拟，而一个模拟模型运行 90 天模拟并衡量按时交付率和生产周期等 KPI 指标，需要花费数天时间。 这在日常运营中并不实用。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/line-balance-parameters.jpg) 图 1：全局规则中的生产线平衡参数
为了解决这个问题，我们部署了 SmartFactory AI Productivity 和 Evolutionary Optimization，并结合模拟退火方法来同时找到按时交付和生产周期的最佳参数。 图 2 显示如何使用 SmartFactory AI Productivity（包括 Simulation AutoSched 和 Fusion 模块以及 RTD 和 Activity Manager）部署该算法。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/algorithm.jpg) 图 2：算法部署
使用这种方法，我们能够在几小时内找到最佳参数值，而不是花费数天。 在每次迭代中，我们都改变生产线平衡参数值和瓶颈站点系列的组合。 如图 3 所示，以前需要迭代 300 次网格搜索才能找到 86.90% 的最佳按时交付率，而我们只需迭代 10 次模型运行就能够达到 98.83% 的按时交付率。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/modeling-1.jpg) 图 3：按时交付率建模
如图 4 所示，在以生产周期为 KPI 指标进行迭代时，使用我们的方法运行模型的第四次迭代达到了 886 小时的 KPI 指标；相比之下，网格搜索的 KPI 指标为992 小时。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/cycle-time-1.jpg) 图 4：生产周期建模
如图 5 所示，一旦获得最佳设置，就可以将其与现有的派工规则和排程应用程序集成，并在工厂的日常运营中整合和重新计算结果。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/production.jpg) 图 5：生产部署
在瓶颈设备上运行总搬运量的本地 KPI 指标，仅用 4 次迭代就找到最佳瓶颈阈值和生产线平衡阈值，达到 20,181 次的搬运量。
模拟优化是实现派工和排程参数自动化的第一步；我们计划进一步改进，通过使用强化学习方法来实现这些参数的自动化。
## 内容概览
- [ 派工规则类型 ](#index1)
- [ 利用算法优化关键绩效指标 (KPI) ](#index2)
- [ 手动调参的局限性 ](#index3)
- [ 部署我们的 AI 解决方案 ](#index4)
- [ 快速识别更优按时交付率 ](#index5)
- [ 生产周期建模 ](#index6)
- [ 将优化成果应用于日常运营 ](#index7)
- [ 瓶颈与产线平衡阈值 ](#index8)
- [ 结论 ](#index9)
- [ 常见问题解答 ](#index10)
本案例详细介绍我们如何使用 SmartFactory AI Productivity 在大幅缩短的时间内自动调整派工规则参数。
### 派工规则类型
派工规则在整个工厂范围内实施，通常分为全局规则和**局部规则**。**全局规则**包含产线平衡逻辑，用于管理客户订单交付；而局部规则则针对特定区域（如光刻）添加额外逻辑以优化生产效率。半导体前道工厂和半导体后道封装、测试和包装工厂都会在部署本地派工规则和排程的同时部署全局派工规则，以提高生产效率。
### 利用算法优化关键绩效指标 (KPI)
通常，全局规则通过部署生产线平衡算法来确保满足交货日期并优化瓶颈解决工具的利用率。这些生产线平衡算法具有不同的参数，需要根据工厂状态对给定的产品组合进行调整。
如今，这些参数是手动调整的，或者在某些情况下，[使用模拟建模功能](/zh-hans/semiconductor-blog/dispatching-scheduling-algorithms-impact/)。很难计算这些参数对工厂中所有设备、所有产品和工艺步骤的影响。因此，手动调整参数可能会对工厂 KPI 指标产生负面影响，而使用模拟技术找到一组最佳参数又会耗费大量时间。
### 手动调参的局限性
请看下图 1 中的示例。根据全局规则，有四个参数用于确定瓶颈解决工具和生产线平衡阈值，以根据在制品 (WIP) 的小时数来判断设备是否处于不足、充足或高负荷状态。
表格显示了这些参数可能的取值范围。要为给定的工厂状态找到这些参数的最佳值，一种方法是运行模拟模型。在每次模拟中，我们选择不同的参数值组合，并测量由此产生的 KPI指标，这种方法在文献中被称为“网格搜索”。每次运行都是为期 90 天的模拟，而一个模拟模型运行 90 天模拟并衡量按时交付率和生产周期等 KPI 指标，需要花费数天时间。这在日常运营中并不实用。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/line-balance-parameters.jpg) 图1：全局规则中的生产线平衡参数
### 部署我们的 AI 解决方案
为了解决这个问题，我们部署了 SmartFactory AI Productivity 和 Evolutionary Optimization，并结合模拟退火方法来同时找到按时交付和生产周期的最佳参数。
图 2 显示如何使用 SmartFactory AI Productivity（包括 Simulation AutoSched™ 和 Fusion 模块以及 RTD 和 Activity Manager™）部署该算法。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/algorithm.jpg) 图2：算法部署
### 快速识别更优按时交付率
使用这种方法，我们能够在几小时内找到最佳参数值，而不是花费数天。在每次迭代中，我们都改变生产线平衡参数值和瓶颈站点系列的组合。如图3所示，以前需要迭代 300 次网格搜索才能找到 86.90% 的最佳按时交付率，而我们只需迭代 10 次模型运行就能够达到 98.83% 的按时交付率。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/modeling-1.jpg) 图3：按时交付率建模
### 生产周期建模
如图4所示，在以生产周期为 KPI 指标进行迭代时，使用我们的方法运行模型的第四次迭代达到了 886 小时的 KPI 指标；相比之下，网格搜索的 KPI 指标为992 小时。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/cycle-time-1.jpg) 图4：生产周期建模
### 将优化成果应用于日常运营
如图5所示，一旦获得最佳设置，就可以将其与现有的派工规则和排程应用程序集成，并在工厂的日常运营中整合和重新计算结果。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/production.jpg) 图5：生产部署
### 瓶颈与产线平衡阈值
在瓶颈设备上运行总搬运量的本地 KPI 指标，仅用 4 次迭代就找到最佳瓶颈阈值和生产线平衡阈值，达到 20,181 次的搬运量。
### 结论
模拟使制造商在不干扰生产的情况下，测试多种参数组合并评估其对关键绩效指标 (KPI) 的影响。然而，即使采用模拟手段，寻找最优参数值仍耗时费力，难以满足日常运营需求。通过部署 SmartFactory AI Productivity 和 Evolutionary Optimization，并结合模拟退火方法，我们能够在更符合日常运营需求的时间范围内，快速确定最优参数配置。
模拟优化是实现派工和排程参数自动化的第一步；我们计划进一步改进，通过使用强化学习方法来实现这些参数的自动化。
## 常见问题解答
#### 半导体晶圆厂中的“派工”是指什么？
派工指的是在特定设备上实时处理批次加工的顺序。
#### 使用派工规则有何优势？
派工规则能够快速确定解决方案，并优先安排批次进入设备加工，从而提升生产效率。
#### 是否需要同时使用排程方案和派工方案？
是的。由于工厂车间的生产状态实时变化，系统每5-10分钟就会生成新的排程方案。这些动态变化可能导致排程决策出现模糊或不一致的情况。而派工方案能够有效应对部分排程挑战，从而保持或提升生产效率。欲了解更多派工方案详情，请阅读我们的博客 [《使用 SmartFactory 派工解决方案，让产出增加5-10%》](/zh-hans/semiconductor-blog/smartfactory-dispatching-solutions/)。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [更快更准地解决批次生产周期预测难题](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/prediction-accuracy/)
**Published:** August 7, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 基于我们先进的 APF 平台，这一 AI 驱动的方案将模型准确性从 75% 提升至 95%，同时大幅简化部署流程，加速落地应用。
**Content:**
### 文稿
通过解决批次生产周期预测问题，您可以保持领先优势。通过 SmartFactory AI Productivity解决方案，我们的客户正实现更准确的预测，和更高的订单交付率。SmartFactory AI Productivity 将提升上下游的产能的可见度，并为解决供应链管理的挑战提供帮助。
使用统计和模拟模型，需要持续的监督，而且由于不能代表实时动态，会导致准确率的下降。我们的机器学习 (ML) 预测模型将根据工厂和数据历史训练，并根据计划周期运行，包括按小时、天或班次运行，并学习整个生产周期内的批次流程和当前晶圆厂行为。通过机器学习 (ML) 自动的重训练，模型的准确度可以从 70-75% 提高到 85-95%。
这样水平的准确率将在无人为干预的情况下保持，伴随约 10% 的准确率提升，还带来 2% 按时交付率的提升及 2% 库存维护成本的降低。应用材料公司 SmartFactory AI Productivity 解决方案可以轻松地在您当前的 APF (Advanced Productivity Family) 平台基础上构建，它不仅是一个更快、更简单、更准确解决所有预测挑战的方案，更是行业的变革者。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [揭示强化学习的优势](https://appliedsmartfactory.com/semiconductor-blog/productivity/advantages-of-reinforcement-learning/)
**Published:** February 9, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 探索强化学习如何利用现实世界数据，为半导体制造中的复杂排程与派工挑战提供革命性解决方案。
**Content:**
## 内容概览
- [ 工作原理 ](#index1)
- [ 定义奖励与惩罚机制 ](#index2)
- [ 适应性 ](#index3)
- [ 高效决策制定 ](#index4)
- [ 响应速度 ](#index5)
- [ 结论 ](#index6)
强化学习 (Reinforcement Learning) 已成为一种强大的技术，使算法能够通过自身的经验进行学习。作为一种机器学习方法，强化学习通过与环境交互来训练决策能力——系统接收“奖励”或“惩罚”的反馈信号，并不断优化长期累积奖励。
这项人工智能技术已为机器人、游戏开发和自动驾驶等领域带来革命性突破。本文将重点解析强化学习的核心优势，并论证其如何有效解决半导体制造在排程与派工环节中的关键性挑战。
### 工作原理
算法的目标是实现长期累积奖励最大化。对算法而言，“奖励”代表算法期望获得的行为或状态——即接近或达成预设目标的结果。例如，提升特定关键绩效指标 (KPI)，或减少制程中的设备换线次数，均可设置为奖励条件。
同时，算法会从惩罚机制中学习。这些负向奖励标志着非期望行为或状态。当算法因某种行动导致不良结果时，惩罚信号会抑制其未来重复类似行为。通过这种反馈机制，系统能主动规避次优或错误的决策路径。
### 定义奖励与惩罚机制
为了更好地理解算法如何解读奖励与惩罚，我们可以参考以下示例（摘自我们的白皮书[《用于半导体制造中 Q-time 管理的深度强化学习》](/zh-hans/semiconductor-blog/deep-reinforcement-learning/)）：
在半导体制造中，队列时间约束 (Queue-time Constraints，简称 QTC) 规定了一个批次在连续工艺步骤之间的最大等待时长。若超出 QTC 限制，就会发生队列时间违规，进而导致良率损失（例如部件腐蚀）。如图1所示，生产线上的任意两个步骤之间都可能存在 QTC 限制。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/02/qtc-between-step-A-and-step-B.jpg) 图1：展示了步骤 A 与步骤 B 之间的队列时间约束 (QTC)，表示当批次完成步骤 A 后，必须在800分钟内进入步骤 B 进行加工。
在这个示例中，我们的目标是构建一个强化学习算法，使其能够学习在队列时间约束下何时释放批次。算法会将“最小化队列时间违规”和“最大化产出”视为奖励信号，并持续采取能够实现这些目标的行动。而队列时间违规将作为惩罚信号，促使算法避免导致违规的操作步骤。
如需了解强化学习在实际应用中的另一个案例，请参阅[《SmartFactory AI Productivity 可在更短时间内自动调整派工规则参数》](/zh-hans/semiconductor-blog/smartfactory-ai-productivity)。
以下是使用真实数据以这种方式带来的一些主要优势。
### 适应性
强化学习具备在动态环境中的适应与学习能力。与依赖假设的基于仿真的方法不同，强化学习可以直接从现实数据中学习，并有效应对复杂多变的情况。它通过实时交互学习并利用反馈优化决策，因此在动态环境中表现卓越。
对于排程与派工而言，这种适应性至关重要。新订单、设备故障以及其他各类突发事件都会影响排程与派工决策，此时强化学习快速适应的能力就显得尤为关键。此外，半导体制造涉及多设备协同、差异化处理时间及复杂工序依赖的精密工作流，进一步增加了复杂性。强化学习的动态调整力能使其能够理解并优化这些工作流，从而实现更高效的决策。
### 高效决策制定
在排程与派工中，自主决策能力（无需人工干预）对提升生产效率至关重要。传统半导体制造依赖多套派工规则和特定区域的排程来管理设备限制并优化生产流程。这些规则通常涉及多个参数，需要用户定期手动调整。
相比之下，强化学习通过在离线训练环境中学习最大化累积奖励，实现自主决策。通过“探索-利用”机制，强化学习算法能够自主学习并发现高效的运行策略，从而在实际生产环境中实现预期目标。强化学习算法能够自主适应并优化系统性能，无需依赖人工参数修改，显著减少频繁认为干预的需求，节省时间、人力和成本。
### 响应速度
实时排程与派工系统对制造运营至关重要，能够帮助产线满足时效性要求（如客户交付期限）。这类系统可有效识别生产瓶颈、平衡工作负载并优化资源配置，从而提升运营效率与整体产出。强化学习算法凭借其实时学习特性，能够快速适应并即时做出决策。这一优势使其能够及时响应环境变化，持续提升生产效率。
此外，强化学习具备迁移学习能力，可将从一个任务或环境获得的知识应用于其他场景。这一特性使算法能够基于既有经验快速建立专业能力。通过迁移已掌握的知识，当转换至不同派工区域时，强化学习可大幅缩短适应过程所需时间。
### 结论
强化学习技术展现出多方面的显著优势。其自主决策能力、实时学习特性和持续进化特点，使其成为极具发展前景的技术方向。随着这一人工智能方法的不断进步，其在解决实际半导体制造中复杂的排程与派工难题方面展现出巨大潜力。
通过应用强化学习算法，半导体制造商能够有效缩短生产周期、提升产出效率，并实现整体生产效能的持续优化。
## FAQs
#### Why is data preparation for AI considered a challenge in semiconductor manufacturing?
Data preparation for AI can be expensive in terms of time and resources, making it a barrier, especially for smaller companies. Historical data may also be insufficient due to evolving environments.
#### How does simulation help overcome data collection challenges for AI deployment?
Simulation allows for the creation of synthetic data, eliminating the need for extensive data cleaning. It provides an efficient way to generate diverse and high-quality data for AI training.
#### What are some practical benefits of using simulation in AI deployment?
Simulation enables the exploration of AI in essential use cases without resource limitations. It accelerates projects, reduces costs, and quantifies the impact of changes before implementation, reducing risks.
#### What role does simulation play in scenarios like Reinforcement Learning (RL) and Machine Learning (ML) in semiconductor manufacturing?
Simulation plays a crucial role in RL by providing a detailed environment for agents to learn and make decisions. In ML, it allows models to be trained on rich datasets, leading to operational efficiency gains and KPI comparisons.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [借助 SmartFactory AI Productivity 建立您的竞争优势](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactoryai-competitive-advantage/)
**Published:** November 23, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 利用预构建的人工智能/机器学习模型提高生产力
**Content:**
半导体制造业的迫切需求，对于那些有能力进一步提高生产力和效率的晶圆厂来说，意味着巨大的机会。然而，现有的工具和方法限制了生产效率或 KPI 的提升水平。SmartFactory AI 可以助您一臂之力。借助该系统，晶圆厂可以通过端到端 AI/ML 模型的开发和部署，形成独特的竞争优势，进而使用新一代先进智能算法应对来自生产力和供应链的挑战。
SmartFactory AI 可解决影响晶圆厂生产效率和良率的两项关键挑战：第一，与预测模型相关的挑战，比如批次生产周期、动态瓶颈和良率预测；第二，寻找最佳逻辑或参数值，以更优的方式控制生产流程或设备的问题，同时考虑生产的实时和未来状态。它是当前的制造环境中唯一可以与排程、派工和全自动生产解决方案集成的工业 AI/ML 平台。
### 主要优势
它的主要优势之一是无需为每个生产步骤手动开发模型。该系统采用自动化任务工具和解决方案 Solution UI，使得开发一个适用于整个生产周期的 AI/ML 系统变得更为简单，最短只需六个月时间。与数据准备、机器学习模型训练和评估、部署以及生产监控等阶段开发各自独立的模型所花的时间相比，这大约是其四分之一。
### 增强现有的 APF 套件
通过引入特定功能来实现自动化部署和对 AI/ML 模型的监控，该平台增强了现有的 Applied APF (Advanced Productivity Family) 套件。通过此项集成，工程师可以使用预构建的机器学习模型或配置关键参数，使模型集中解决晶圆厂的特定问题和挑战。用户无需学习其他环境或开发语言。
在生产中，SmartFactory AI 收集数据，训练模型，将其部署到生产环境中，并实时监控其性能可了解该模型的运行情况。如果模型的准确性出现波动，可自动进行重新训练。
通过将SmartFactory AI 与生产环境集成（例如 Applied APF 和 E3 平台），半导体制造商有望实现生产周期、利用率、产出和良率的改善。任何其他平台都无法在投入如此少的时间和资源的情况下实现此效果。
如需详细了解 SmartFactory AI 如何助力企业达成目标
[ 请与我们联系 ](/zh-hans/connect/)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [实现准确的批次生产周期预测，提高按时交付率](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/achieve-accurate-lot-time/)
**Published:** January 6, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 借助人工智能/机器学习 (AI/ML) 提高批次生产预测的准确性
**Content:**
目前预测批次生产周期的统计方法平均只能达到 70% 的准确率，对于希望提高生产效率、产线忙碌的晶圆厂而言，该准确度无法满足其需求。最终，由于统计模型无法体现晶圆厂的实时生产动态，因此晶圆厂的团队每天都要花费大量时间核查预测数据，并重新进行预测以获得准确的数据。这表明晶圆厂需要采用一种更快速、简单、准确的解决方案来预测每 14 天为一周期的批次生产周期。在最近的一个客户应用中，SmartFactory AI Productivity 解决方案和 Engineered Works™ 被证明可以将生产预测的准确率提高到 85%。
通过一些实验研究，我们确定最适合该客户需求的ML 模型是基于梯度提升树的机器学习模型，特别是基于轻量梯度提升机的模型部署。该框架在行业中已得到广泛应用。由于该框架用于对表格数据进行预测，对未知数据具有很强的生成属性，同时抗噪声能力強，因此非常适合该客户。
借助 SmartFactory AI Productivity解决方案，根据之前 24 个月的工厂数据，我们对 ML 模型进行了训练。对于特征计算，我们定义了多个可表示批次流程和晶圆厂生产行为的特征，例如工作站统计数据和 WIP（在制品）特征，我们每天都会根据批次优先级，并针对每个路线或部件的站点对这些特征进行计算。我们使用 Clickhouse 数据库来存储特征数据。
该 ML 模型建立在当前工作系统之上，因此该 ML 模块和当前 RTD 或排程解决方案可相互协作和通信。该 ML 模型已被训练为可基于排程（包括每小时、每天或按班次）运行，并且已学习了从任一站点到最终站点的批次流程和当前晶圆厂生产行为。它将为每个站点创建一个模型，以预测最终站点的生产周期。例如，如果在站点 A 有一个批次，并且在生产完成之前还有 12 个站点，则将生成 12 个模型，一个模型对应一个站点，以预测到最后一个站点的生产周期。每个模型都将接受各项训练，包括历史特征数据、从当前站点到最终站点的 WIP 概况、利用率、设备可用性和批次优先级。这些模型被保存在磁盘的 pickle 文件中，并聚合到一个主 pickle 文件中供 Formatter 程序使用。可将这些模型部署到生产中。图 1 显示了部署的详细信息和结果。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/01/figure-1-shows-details-of-deployment-and-results.jpg) 图 1：显示部署的详细信息和结果
如当前 RTD 或排程解决方案系统需要某种预测，它会参考 ML 模块已经做出的预测。ML 模型可基于之前训练数据中未涵盖的条件自动重新训练，并会对预测做出修改，使结果更加准确。
有了准确的工厂生产预测模型，晶圆厂可以更好地确定造成批次延误的原因，提高订单交付速度，例如可通过更改派工规则参数来加快延迟批次的生产。
训练完成后，我们会基于测试数据集对面向客户开发的 ML 模型进行评估。我们对模型评估和准确性定义做出如下指标，并以此作为关键性能指标：均方根误差 (RMSE) 和平均绝对误差 (MAE)。我们将准确度指标定义为 1 平均绝对百分比误差，即每批次预测准确度的平均值。我们的准确性比较的结果显示，ML 模型的结果比基线模型要准确 5% 至 13%。准确性提高约 10% 可使按时交付率 (OTD) 提高 2%，库存维护成本降低 2%。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Integrating Generative AI into the industrial engineering workflow](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/integrating-generative-ai-into-industrial-engineering-workflow/)
**Published:** August 13, 2025
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** The potential to turn complexity into clarity could be a game changer for industrial engineers tasked with managing complex data.
**Content:**
## What’s Inside
- [ Chatting with data ](#index1)
- [ Take actions ](#index2)
- [ Autonomous insight ](#index3)
- [ Conclusion ](#index4)
Semiconductor manufacturing is a data goldmine—every tool, process, and schedule generates rich, complex information. In today’s world, collecting data is no longer the challenge but, rather, making sense of it quickly seems to be the real hurdle. Industrial engineers in particular don’t have it easy —they are managing dozens, sometimes hundreds, of topics each day. From analyzing schedules to evaluating capacity plans, the sheer volume of data and decisions can quickly become overwhelming. Current tools and systems obviously support their data analysis efforts, but often the relentless pace and constant demands of a dynamic fab environment leave them scrambling to keep up.
Imagine if industrial engineers could simply chat with their data, take actions directly through conversation, and then make their processes more autonomous. Conversational assistance powered by large language models could redefine how industrial engineers interact with their data.
### Chatting with data
At times, industrial engineers find themselves pulled into urgent situations where they must quickly resolve unexpected issues. The issues could also vary on any given day – from equipment failures, production bottlenecks, or supply chain disruptions, to quality control problems. This reactive mode, commonly referred to as ‘firefighting,’ can consume a lot of time and energy. While reports are available to support their efforts, it can sometimes feel like there are reports just to explain other reports. And despite all the data and dashboards, what industrial engineers often need is simply a direct answer to a direct question. To do this they don’t want to write a query, build an analytic, or worry about misinterpreting the data. They just want a quick answer to a question such as, “How many tools are in the dataset?” or “Show me the lot starts per day?”
Chatting with data for better understanding —essentially doing Exploratory Data Analysis (EDA) through natural conversation —is a very simple concept. Yet, there is actually a lot to be gained in efficiency by simply asking clear, direct questions.
Furthermore, it doesn’t have to stop with simple questions. Industrial engineers might want to validate assumptions or check data quality, too. For example, consider the following inquiry: “Are there any negative processing times in the data?” Ensuring clean, reliable data is a constant challenge and standardizing validation procedures is difficult. For different situations, experts typically know what to look for, whether it’s outliers, missing values, or inconsistencies that could signal deeper issues. Streamlining data quality checks is critical to ensuring efficient decision-making.
### Take actions
While conversational assistance is a powerful way to interact with data, chat alone might not be enough. Industrial engineers don’t just want answers, they want action. They might want to move beyond dialogue and drive outcomes directly through conversation.
Imagine updating data with a simple prompt like, “Change UID: X to UID: Y,” or effortlessly generating insights with, “Create a bar chart showing certifications per equipment.” Switching views instantly can be added to the commands, “Show this data in a table instead.” Even consider how conducting scenarios could become easier: “Push preventative maintenance for area X to date Y.”
Instead of relying on deep software knowledge or remembering specific UI steps, industrial engineers can simply talk to a system. The value of conversational AI moves beyond convenience into true operational impact when dialogue leads to action.
### Autonomous insight
Now, what if AI didn’t just respond to questions and commands but actually anticipated daily needs? For example, imagine an industrial engineer starting their shift and already knowing exactly what needs to be done—and by when—not because of a checklist, but because an AI automated system proactively surfaced the tasks that matter most.
Instead of asking “What are the most important tools to be recovered today?” the AI simply and automatically tells you: “Here are the most critical tools to recover.”
Industrial engineers could again take this even further where they are looping back to the chatting with data concept. They could ask, “Why are these tools considered critical?” and receive a clear explanation. Here priorities are not only surfaced, but the reasoning behind the output is explained; industrial engineers can understand the why behind the what. This level of transparency is essential. It builds trust in an automated AI-driven system. Beyond trust, it also plays a vital role in effective change management as industrial engineers can confidently embrace a new way of working.
### Conclusion
As factories are seeking more agile and responsive operations, AI-driven conversational interfaces and autonomous AI agents are increasingly being added into semiconductor manufacturing workflows. However, maintaining a strong foundation of high-quality data, detailed documentation, and integrating expert knowledge or best-known practices remains essential. Even the most advanced systems are only as effective as the information they are built upon. However, when these foundational elements are strong, Generative AI can truly continue to evolve and accelerate decision-making.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [AI 集成正重塑生产制造关键绩效指标](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-transforming-manufacturing-kpis/)
**Published:** April 16, 2025
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** 半导体制造商正加速提升工厂效能，并开拓全新商业机遇。
**Content:**
## 内容概览
- [ AI引发的范式变革 ](#index1)
- [ 成熟技术，全新颠覆 ](#index2)
- [ 不可或缺的人为因素 ](#index3)
- [ 经济效益考量 ](#index4)
- [ 进阶优势解析 ](#index5)
### AI引发的范式变革
无论是采用现有的集成软件解决方案，还是基于自动化智能 (AI) 的技术方案，制造商的核心目标始终如一：全面提升制造环节的效率与质量。然而，传统解决方案的效能提升已触及天花板，而 AI 却能实现前所未有的学习能力和数据处理水平。这项颠覆性技术的引入催生了根本性变革——制造商得以用全新视角审视质量、生产力、产能、设备正常运行时间等传统关键绩效指标 (KPI) 。
### 成熟技术，全新颠覆
人工智能 (AI) 并非全新技术——早在20世纪50年代这一术语便已诞生。真正的变革在于，随着支持性软件和先进算力的发展，AI 技术已实现主流化应用和普及。这一突破为人类如何使用快速发展的AI认知铺平了道路，正彻底重塑产业格局：它不仅持续提升工厂效能，更不断创造全新商业机遇。
对制造商而言，这场 AI 革命的核心在于前所未有的技术市场化速度。传统模式下，企业可能需要长达九个月才能完成产品设计并导入产线；而 AI 技术可将这一周期缩短至颠覆性的三个月。这种兼顾高精尖产品开发、成本效益提升、质量与产能优化的能力，将深刻改变企业运营模式——包括获取以往难以企及的高利润订单。
以半导体行业为例，目前仅有少量巨头能持续向市场推出革新性产品，并在一段时间内享有可观利润。借助 AI 技术，原本不具备这种竞争力的企业将实现一至两代的技术跨越，达到更高效能水平。
AI 系统所需的数据范式也在发生变革。过去，只有掌握海量数据的行业巨头才能训练有效模型，而如今合成数据生成技术正逐步弥合这一差距。未来焦点将集中在：实现工厂中不同产品间的认知迁移。产品转换将变得更加无缝，并使我们能够更高效管控生产差异。这些进步将显著提高管理产线差异的能力。随着 AI 相关技术的持续突破，下一阶段革命的重点在于：构建可复制、可扩展且真正有价值的落地方法论。
### 不可或缺的人为因素
尽管 AI 是一项技术创新，但其潜力的真正释放与新范式的推动，始终离不开人的核心作用。目前，充分发挥 AI 效能所需的技能组合分散于两类人才，一类是精通 AI 及相关技术数据科学专家，另一类是深谙半导体制造机理的工艺专家。他们需要通力合作，以最大化 AI 的影响力，并优化面向特定应用场景的模型训练方式。
制造商也将利用 AI 技术来克服人类的局限性。例如，AI 可以同时执行16项分析任务，并在数秒内得出结果。相比之下，人类容易因疲劳和偏见导致失误，分析耗时更长，且不可避免地会加入主观判断。
AI 改善人类局限性的另一个方面体现在信息留存能力上。人类存在记忆差异、培训差异和经验差异，导致处理问题和学习信息的方式各不相同，AI 则是一种有效的替代方案。关键差异点在于信息获取方式，AI 可完整捕获学习过程，从而在整个系统中实现全面统一的理解，并能够实时关联所需的所有数据集。
AI 还能有效解决制造业中的知识传承难题，特别是在经验丰富的工人退休而新人加入的情况下。AI 保存的知识可以即时在整个工厂共享，帮助指导新进人才。我们实际上可以构建一个学习系统——这将是革命性的改变！
### 经济效益考量
AI 技术在制造业的应用不仅受技术和人为因素影响，经济因素同样起着关键作用。不同类型的晶圆厂有着截然不同的商业考量。一家300mm先进制程代工厂、一家200mm车规芯片制造商、一家150mm MEMS 工厂，他们的业务结构各异，投资意愿和需求也完全不同。以150mm MEMS 工厂为例，虽然利润可观，但必须有足够说服力的理由才会考虑变革或投资，必须获得足以改变其业务格局的实质性成果，否则没有动力投资 AI。这类工厂更倾向于投资能直接提升效率的方案。
AI 集成将率先在300mm晶圆制造中实现突破。虽然这不是铁律，但很难想象传统制程工厂会进行大规模 AI 投资（尽管过去也有意外案例）。AI 技术将在高混合小批量的应用场景中发挥巨大作用，并将助力新产品快速市场化。
半导体制造商当前最担忧的问题之一，是伴随着老龄化员工退休而流失的宝贵经验。他们担心当那些唯一经历过每三年左右才发生一次的灾难性事件的老员工离开后，这类事件该如何处理。AI 将帮助弥合这一断层，既能保留知识资产又能为新员工所用，还能更高效地培训新人技能。这正是制造商投资 AI 最具实质意义的动因之一。
最终，围绕 AI 的经济性决策将随着工厂的运营效益和市场动态而逐步变化。
### 进阶优势解析
半导体制造商在优化 AI 开发与部署时，需综合考量人力、技术及经济等多重因素。AI 将催生全新的商业思维模式——通过洞见以往无法理解或掌握的生产规律，重新定义业务需求与发展潜力。其带来的效能跃升，犹如从校队竞技直接晋级至奥运水准的跨越式突破。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [より迅速かつ高精度にロットサイクルタイム予測の課題を解決](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/prediction-accuracy/)
**Published:** March 28, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 当社の先進的なAPFプラットフォームを基盤に構築されたこのAIを活用したアプローチは、モデルの精度を75%から95%に向上させるとともに、展開を迅速かつ容易にします。
**Content:**
### 字幕（全文）
ロットのサイクルタイム予測に関する課題を解決し、競争優位性を維持しましょう。SmartFactory AI Productivityを活用することで、より正確な予測が可能となり、注文から納品までのリードタイムを改善できます。また、川上・川下の生産性やサプライチェーン管理における課題の可視化にも貢献します。
従来の統計モデルやシミュレーションモデルでは、常時監視が必要でリアルタイムの変動を反映できず、予測精度が低下する傾向があります。SmartFactory AI Productivityの機械学習（ML）モデルは、工場の履歴データを学習し、時間単位・日単位・シフト単位などのスケジュールに基づいて実行され、ロットの流れやファブ全体の挙動を把握します。MLによる自動再学習により、モデルの予測精度は75%から最大95%まで向上します。
この高精度は人手を介さずに維持されます。約10%の精度向上は、納期遵守率の2%向上と在庫維持コストの2%削減にもつながります。既存のAPFプラットフォーム上に簡単に構築できるApplied SmartFactory AI Productivityは、すべての予測課題に対して、より高速で簡単、かつ高精度なソリューションであるだけでなく、業界に変革をもたらすゲームチェンジャーです。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [SmartFactory Monitorで、大きな損失につながる想定外のダウンタイムを削減](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/smartfactory-monitor/)
**Published:** March 19, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** 製造にかかわるソフトウェアとシステムパフォーマンスを世界中どこからでもモニタリングが可能
**Content:**
#### 字幕（全文）
製造現場が直面する課題は至るところに存在しており、工程上の問題から設備の不具合まで多岐にわたります。その中でも、手遅れになるまで見過ごされがちな課題のひとつが、工場の運用を支える重要なソフトウェアやサーバーに関する問題です。一つの製造装置が停止すれば、それは確かに一つの問題ですが、
例えばMES（製造実行システム）が停止すれば、工場全体が止まってしまいます。このビデオでは、「SmartFactory Monitor」をご紹介します。
「SmartFactory Monitor」は、工場の稼働を支える各種ソフトウェアシステムを監視し、ダウンタイムを防ぎ、スムーズな運用を維持するために特化してデザインされたシステムです。工場の稼働時間は非常に重要で、ほとんどの工場ではそれを監視するための指標や、品質向上のためのプログラムが導入されているはずです。
製品を正しく処理し、途切れることなく工場内で流し続けることは、企業の収益性に直結し、それらを支える製造関連のソフトウェアシステムは、生産性と品質の両方において重要な役割を果たしています。しかし、それらが正常に動作しなくなった瞬間、すべてが止まってしまいます。
誰もが経験したくない事態ですが、実際には時々発生します。サーバーがダウンしたり、ネットワークに問題が発生したり、あるいは近くで行われていた装置の設置作業の影響で、サーバールーム全体の電源が落ちてしまうこともあります。その結果、工場全体が予期せぬダウンタイムに見舞われます。
これは、ビジネスにとって非常に大きな損失です。貴社の工場では、これまでにこうしたことは発生しましたでしょうか？その時、ITチームが問題に対応し、復旧するまでにどれくらいの時間がかかりましたか？その結果、生産にどのような影響が出ましたか？
そして最も重要なのは、それが貴社の利益にどれほどの影響を与えたかということです。この影響は決して小さくありません。たとえば、比較的小規模なウェーハ工場でも、1時間の予期せぬダウンタイムで1万ドルの損失が発生する可能性があります。
中規模の工場では10万ドル、最先端の大規模工場では、なんと100万ドルに達することもあります。では、こうした予期せぬダウンタイムをどうすれば減らせるのか、あるいは回避できるのか？
その答えが「SmartFactory Monitor」です。
SmartFactory Monitor は、リアルタイムでシステムを監視し、問題を早期に特定し、製造システムに影響が出る前に是正措置を可能にするソフトウェアソリューションです。基本機能として、現在のシステム状態をわかりやすく表示するカスタマイズ可能なダッシュボードを提供し、
非常に小さな問題も可視化し、問題が発生した際には即座に通知を送ることができます。カスタマイズ性は大きな特長のひとつで、パフォーマンスの傾向を時系列で可視化することも可能です。
さらに、予測分析機能により、問題が実際に発生する前に異常を検知することができます。SmartFactory Monitor は、軽量なシステムリソース内で動作し、貴社に適したOSも選択可能です。そして何より、そのほかのSmartFactory ソフトウェア製品との親和性が高くそのまま連携することが可能です。
SmartFactory Monitorは、製造現場が直面する多くのシステム課題に対応するための包括的な監視機能を提供します。
このソリューションの大きな目的は、様々なシステムの問題を迅速に特定・解決することで、工場の予期せぬダウンタイムを削減し、さらにはパフォーマンス傾向分析や予測分析を通じて、問題の発生そのものを未然に防ぐことにあります。その結果、システムとアプリケーションの可用性が向上し、業務運用効率が改善され、最終的には企業の収益性も高まります。
SmartFactory Monitor は、システム状態とパフォーマンス傾向の可視化、障害の迅速な検出と予測、リモート監視をささえる24時間365日のグローバルサポート、そして製造業を深く理解する信頼できるチームによって支えられた、理想的な監視ソリューションです。
ご興味をお持ちいただけましたか？追加の情報提供が必要であればぜひご連絡ください。あるいは貴社のITチームとの意見交換する場を持たせていただき、貴社のシステムやパフォーマンス上の課題について詳しくお話をお伺いできればと思います。SmartFactory Monitorの導入をご検討いただけると幸いです。
SmartFactory Monitor — 理想的なソリューションです。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [SmartFactory AI Productivityで独自の競争優位性を構築](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactoryai-competitive-advantage/)
**Published:** October 12, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 事前構築済みのAI/MLモデルで生産性を最大化
**Content:**
半導体業界では、製造能力の向上がこれまで以上に求められています。生産性と効率を高めることができるファブには、大きなビジネスチャンスが広がっています。しかし、従来のツールや手法では、改善のスピードや効果に限界があるのも事実です。SmartFactory AI は「改善」を可能にします。先進的でインテリジェントなアルゴリズムの次世代アプローチを用いて、生産性とサプライチェーンの課題を解決するエンド・ツー・エンドのAI/MLモデル開発と展開を実現することで、ファブは独自の競争優位性を生み出すことができます。
SmartFactory AIは、ファブの生産性と歩留まりに影響を与える2つの主要な課題に対応します。1. ロットのサイクルタイム、動的ボトルネック、歩留まり予測などの予測モデルに関する課題。2. 生産フローや装置の運用を、リアルタイムおよび将来の状況を考慮して最適化するための最適な制御ロジックやパラメータの探索に関する課題。SmartFactory AIは、現在の製造環境において、スケジューリング、ディスパッチング、フルオートソリューションと統合できる唯一の産業用AI/MLプラットフォームです。
### SmartFactory AI の導入メリット
SmartFactory AI の大きな利点のひとつは、製造の各工程ごとに手動でモデルを開発する必要がないことです。代わりに、タスク自動化ツールとソリューションUIを活用し、AI/MLシステム全体をわずか6か月で構築可能です。これは、データ準備、モデル学習・評価、導入、モニタリングといった各段階を個別に開発する場合の約4分の1の期間です。
### 既存のAPFスイートを強化
このプラットフォームは、当社の既存のAPF（Advanced Productivity Family）スイートを強化し、AI/MLモデルの導入とモニタリングを自動化する特別な機能を提供します。エンジニアは、あらかじめ構築されたMLモデルを使用したり、ファブ固有の課題に焦点を当てるための主要パラメータを設定したりできます。追加の環境やプログラミング言語を学ぶ必要はありません。
SmartFactory AIは、生産現場でデータを収集し、モデルを学習させ、それを導入し、リアルタイムでパフォーマンスを監視します。モデルの精度に変動があれば、自動的に再学習が行われます。
SmartFactory AIをAPFやE3プラットフォームなどの生産環境と統合することで、半導体メーカーはサイクルタイム、装置稼働率、スループット、歩留まりの改善が期待できます。これほど短期間かつ少ない労力でこれを実現できるプラットフォームは他にありません。
SmartFactory AIがどのように貴社の目標達成を支援できるか、詳しくはお問い合わせください。
[ お問い合わせ ](/ja/connect/)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Next-Generation of Advanced Automation Solutions](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/advanced-automation-solutions/)
**Published:** March 13, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Increasing quality and productivity in factories of any size with Applied SmartFactory integrated automation solutions for semiconductor manufacturers
**Content:**
#### Transcript
From simple home appliances and online billing to the complexity of robotics and autonomous vehicles, automation is everywhere, making life easier, workplaces safer, and production more efficient. The computer chips that enable this automation are manufactured in the most complex environments imaginable. As these environments become more advanced, creating more data and demanding more decisions at each step, automation systems need more speed and power to keep up.
Imagine the difference in complexity between running a baggage carousel at the airport and running the entire airport and its operations. With the re-entrant processes required to run today’s semiconductor factories, you need an advanced, comprehensive suite of automation solutions that can predict and solve high-value problems in real time and an expert team to deploy the solutions. Enter Applied Materials, the global leader in automation software, services, and equipment for the semiconductor industry.
With so many factors like fast yield ramp, spec conformance, new product introductions, and changing equipment conditions, meeting your customer on-time delivery is a challenge. That’s why Applied SmartFactory Solutions are designed to work together seamlessly in your factory. An integrated system to improve operations, increase yield, and drive profit.
SmartFactory’s proven automation solutions improve your factory KPIs at each stage of the factory’s life. SmartFactory Solutions enable you to meet your factory productivity targets with higher quality, increased yield, and shorter cycle times. That’s why virtually every semiconductor fab in the world uses Applied SmartFactory. So don’t wait.
Contact us at and begin your journey toward creating a world-class factory.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [塑造未来智能工厂](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/shaping-the-future-to-create-intelligent-factories/)
**Published:** November 25, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 制造商依赖SmartFactory解决方案来提高工艺质量、提升生产效率并最大化发挥设备效能。
**Content:**
制造商依赖SmartFactory解决方案来提高工艺质量、提升生产效率并最大化发挥设备效能。
## 文稿
我们推动成就，用智慧和数据提供更高的良率。我们推动成果，用实时决策系统帮助工厂按时交货。我们推动准确性，帮助工厂实现优化流程和产线控制。我们推动行为，提供移动解决方案的决策。应用材料公司 SmartFactory 为您提供完全自动化的软件方案。
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [迈向全自动化生产](https://appliedsmartfactory.com/semiconductor-blog/productivity/move-to-full-automation/)
**Published:** November 25, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 最大化发挥您工厂的全部潜能：提高质量、缩短生产周期和提升资产利用率。
**Content:**
最大化发挥您工厂的全部潜能：提高质量、缩短生产周期和提升资产利用率。
## 文稿
实现工厂各级自动化（涵盖生产计划、排程、工厂设备及控制环节），可显著减少资源浪费，从而优化生产周期、提高工厂产出、降低成本及改善客户及时交付率。迈向全自动化的第一步是“检测”，目前已有诸多成熟先进的检测系统可供采用。
其中包括统计过程控制和故障检测系统。
因此，我们正与客户合作，努力帮助他们实现电子化，从而缩短他们在识别问题后的平均解决时间。
这使企业能够整体审视工厂资源，减少因分析和验证在制品 (WIP) 管理策略（如派工与排程）变更所产生的生产中断、延误及成本，并为产能规划场景构建贴近实际的“假设分析”模型。
在产品生命周期的特定阶段，客户必须在正确的地点、恰当的时间，以合适的利润率生产出高质量的产品。
这种成果归根结底取决于现场工程团队的主动性与驱动力。卓越的企业懂得赋能工程师，并为其提供必要的工具。自动化系统正是这幅宏伟蓝图中至关重要的组成部分。
这些正是应用材料公司助力客户成就卓越的部分举措。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [新一代先进自动化解决方案](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/advanced-automation-solutions/)
**Published:** March 13, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 应用材料公司 SmartFactory 集成自动化解决方案助力半导体制造商全面提升各类规模工厂的质量与生产效率。
**Content:**
#### 文稿
从简单的家用电器和在线计费，到复杂的机器人技术和自动驾驶交通工具，自动化无处不在——它使生活变得更轻松、工作场所更安全、生产效率更高。而实现这种自动化的计算机芯片，是在能够想象到的最复杂的环境中制造的。由于这些环境越来越先进，每个步骤中创建的数据越来越多，并且要求更多的决策，因此自动化系统需要更快的速度和更强大的能力才能跟上步伐。
想象一下在机场运行行李传送带，和运行整个机场及其操作之间的复杂性差异。鉴于如今半导体工厂运行所需的可重入流程，您需要一套先进的、全面的自动化解决方案来实时预测和解决高价值问题，以及一个专家团队来部署解决方案。应用材料公司简介：全球半导体行业自动化软件、服务和设备的领军企业。
由于诸如快速提高产量、规格一致性、引入新产品以及设备条件变更等诸多因素，按客户要求准时交付越来越难。因此，应用材料公司 SmartFactory 解决方案旨在与工厂中的集成系统无缝协作，以改善运营状况，提高良率和利润。
SmartFactory 的自动化解决方案已久经验证，可有效提高工厂生命周期中每个阶段的关键业绩指标 (KPI)。SmartFactory 解决方案使您能够以更优质量、更高良率和更短周期来实现工厂的生产效率目标。因此，应用材料公司 SmartFactory 解决方案受到全球几乎每个工厂的青睐。所以，别再等啦。
赶快通过 与我们联系，开始创建世界一流工厂的旅程吧！
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [迈向智能制造的新台阶](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/moving-to-a-new-level-of-intelligent-manufacturing/)
**Published:** November 25, 2021
**Author:** David Hanny
**Excerpt:** 半导体制造业经历了数代演变，目前，这个行业正在经历另一场巨大变革.
**Content:**
半导体制造业经历了数代演变，目前，这个行业正在经历另一场巨大变革.
[pdf-embedder url=”/wp-content/uploads/2022/04/moving-to-a-new-level-of-intelligent-manufacturing_Chinese.pdf” height=”1000″]
[ 下载PDF文件 ](/wp-content/uploads/2022/04/moving-to-a-new-level-of-intelligent-manufacturing_Chinese.pdf)
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [What can smart manufacturing do for you?](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/smart-manufacturing-benefits/)
**Published:** September 7, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Top benefits for innovative semiconductor manufacturers
**Content:**
Smart manufacturing is a term widely used in many industries. As commonplace as the term has become, it’s not always easy to identify exactly what makes it smart and what it means specifically for semiconductor manufacturers. Essentially, smart manufacturing is an approach that integrates multiple factory systems (such as those that track lots, processes, scheduling, and distribution) to improve the accuracy and quality of data and communication. The following are seven key benefits you can get from smart manufacturing solutions in semiconductor manufacturing.
### Improved productivity through collaboration
Smart manufacturing can connect people who normally don’t work together with data from machines that don’t usually interact with each other. Smart manufacturing solutions integrate data from multiple sources and make it easily accessible to all users via dashboards that enable collaboration across the floor, manufacturing sites, and the company.
Smart manufacturing creates new communication and data links between humans and equipment
### Actionable insights
Digital information derived from real-time insights leads to better use of resources and optimized factory performance. Knowing what’s happening on the line in real-time—including instant notification of problems and their causes – allows for better problem solving, less downtime and greater productivity.
### Improved efficiency
Having accurate insights into equipment and process state lets you predict downtime and failures. Predictive and prescriptive maintenance enables you to plan optimum maintenance intervals. And, with automated data capture and analysis, systems can identify when a problem arises, notify the appropriate stakeholders and recommend (or even implement) the appropriate intervention.
### Quick, good decisions
Integration of systems, real-time data and user-friendly interfaces create opportunities for faster, more informed problem solving that can improve overall quality.
### Continual improvement
The wealth of data provided by smart manufacturing lets you spot trends, identify areas for improvement, and put plans in place. Once implemented, real-time data will provide insight into how your actions impacted your KPIs so you can then focus on improvements in other areas.
### Accurate, on-time delivery
With better insight and control over lot cycle time and output, as well as better utilization of resources, smart manufacturing helps predict an accurate delivery schedule and stick to it.
### Secure options
Options to store data on-premises, on a secure cloud or in a hybrid of the two lets you decide what is best for your performance and data requirements.
Most importantly, smart manufacturing can vary depending on the size of the factory and the priorities of the business. Consider the KPIs that mean the most to you and adopt a solution that aligns with your needs and the needs of your customers.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [将人工操作自动化：半导体制造中的耐用品管理](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/durables-management-for-semiconductor-manufacturing/)
**Published:** April 22, 2024
**Author:** Selim Nahas, Yoram Barak
**Excerpt:** 使用 SmartFactory Durables Management 系统进行封装、测试和包装老化测试用例场景
**Content:**
## 内容概览
- [ 耐用品管理 (DM) 简介 ](#index1)
- [ 封装、测试和包装老化测试用例示例 ](#index2)
- [ 优化重测用例 ](#index3)
- [ 资产性能用例 ](#index4)
- [ 集成 ](#index5)
- [ 用户体验/用户界面成功要素 ](#index6)
- [ 总结 ](#index7)
### 耐用品管理 (DM) 简介
在半导体制造中，耐用品是生产过程中会用到的关键资产，如光罩、载具、探针卡、泵或阀门、腔室、夹具、机器人及其他设备。可以将耐用品视为制造设备的可移动扩展部分。因此，耐用品管理是指对这些资产的全面管理。其中包括追踪、监控和优化这些资产的使用、维护与生命周期，以确保工厂运营顺畅并最大限度提高生产力。
耐用品管理对于半导体企业的产品质量极为重要，原因如下：
**成本效益：**半导体制造涉及高价值设备，而有效管理这些资产有助于降低与维护、维修和更换相关的成本。通过追踪耐用品的使用情况和状况，半导体制造企业可以及时发现并解决问题，从而避免代价高昂的故障或不必要的库存。
**运营效率：** 高效利用耐用品对于保持生产计划一致性至关重要。有效的耐用品管理可确保设备在需要时随时可用，从而最大程度地减少生产延误并提高产量。
**流程优化：** 通过监控耐用品的性能和运行状况，半导体制造企业可以收集宝贵的数据和洞见。这些数据可用于抓住特征、优化设备参数和提高整体流程效率。耐用品管理软件可提供实时分析功能和具有指导意义的见解，进而推动持续改进计划。
**维护计划：** 耐用品管理软件可追踪资产使用情况并预测维护需求，从而制定积极主动的维护计划。预测性维护策略可以利用耐用品管理系统提供的生命周期数据。
**质量控制：** 耐用品管理软件通过监测和控制关键资产的性能，来帮助确保产品质量一致性。通过追踪设备性能指标，半导体制造商可以找出偏差并采取纠正措施，从而保持产品质量和良率。
SmartFactory Durables Management 通过可追溯性、状态模型和集成性这三方面的优势，直接解决半导体制造中面临的挑战，从而带来诸多益处，如图 1 所示。这是一个自动化耐用品管理系统，能够正确管理耐用品在其整个生命周期中的状态和位置，这对于实现高标准的产品质量、缩短生产周期和提高设备利用率至关重要。将这些功能与 SmartFactory Real Time Dispatching (RTD) 相结合，可创造出一个无与伦比的强大机制，使资产高效运行。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/04/figure-1-The-benefits-of-SmartFactory-Durables-Management.jpg) 图 1：SmartFactory Durables Management 的优势
### 封装、测试和包装 (ATP) 老化测试用例示例
在过去三年中，自动化产品部致力于开发、更新和改进耐用品管理功能，这些功能可以普遍应用于客户的制造执行系统。后段的根本区别在于，许多操作通常都是手动进行的。首先感兴趣的项目是一个后段老化测试设施。该设施负责测试已封装并可交付给客户的器件。这些器件被装载在老化测试板（有时被称为 BIB，见图 2）上。这些测试板将在被称为“老化测试加载单元”(BLUs) 的装载设备之间循环，然后送入老化测试烘箱，该烘箱对 BIB 和器件进行加热，同时对它们进行参数测试。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/04/figure-2-1.jpg) 图 2：BIB (a) 和插座 (b) 示例。这些器件可以进入实体烘箱或无烘箱环境 （即，通过高压和高电流直接在插座中产生热量）
业界一直在寻找管理这些资产的方法，以便对器件进行可靠的测试，并管理在设施中维护这些耐用品的费用。手动处理这类活动将极具挑战性。公平地说，从人类的角度来看，追踪如此多的耐用品是一项艰巨的任务。例如，据估计，一个设施中仅一种类型的耐用品数量就可多达 2 万件或更多。BIB 上布满插座，单个 BIB 可以包含多达 150 个插座。如果将插座也定义为耐用品，那么我们现在可能需要管理的耐用品数量就会大大增加。这不仅是运行状况管理问题，也是物流问题。老化测试设施负责测试器件，并将因各种原因而失效的器件隔离出来，同时确保失效是源于器件本身，而非 BIB 和/或插座。这类设施需具备的一个功能是，能够在器件出现故障时管理重新测量方案。如果能够追踪和追溯板卡及其上插座的位置和性能，就能极大地促进这些活动的开展。
### 优化重测用例
在封装、测试与包装 (ATP) 市场中，一个优化机会的例子是对最初出现故障的器件进行重新测量，通过将其转移到适当的备用板卡来确保它们的有效性。因为我们了解插座和板卡的性能，调度员可以为出现故障的器件选择最佳的板卡和插座。
### 资产性能用例
使用耐用品管理系统可以显著提高资产性能评估效果。通过追踪使用情况、移动、周期等，我们能够对资产绘制统计数据。确保了解资产的使用情况及性能表现，可以加强对优秀资产利用方法的理解。从维护和使用的角度来看，这一方法是正确的。
### 集成
需要更多自动化功能来简化耐用品管理，使负责人能够更轻松应对管理耐用品时面临的挑战。要实现这种自动化，就必须有一个可以连接设备集成的耐用品应用程序。此外，还必须提供人工界面，因为许多这样的设施仍然依赖操作员来加载和卸载设备。这就意味着，定义板卡、设备和人员之间关系的能力是耐用品管理系统的重要组成部分。同样重要的是能够定义用于评估耐用品运行状况的追踪标准。最后但同样重要的是，在一种耐用品和另一种耐用品可能相互包含或彼此影响的情况下，必须建立两者之间的关系。举例来说，一个被视为耐用品的容器可能包含另一个耐用品，如前端工厂中的晶圆盒和光罩，或后段工厂中的 BIB 和插座。这些耐用品预计会在一天中移动多次，通常会放入设备中或取出以进行维修，在许多情况下还会移动到设施之外。为此，一个现代化的耐用品管理系统需要能够定义和管理设施内外部的各种关系。
所有耐用品必须能够维护一个状态模型，以定义特定耐用品的相应业务流程。该业务流程将包括计数器和自定义字段等简单元素，以及来自检测设备或其他校准设备的参数结果。所有这些元素都必须能够影响状态模型的行为。
### 用户体验/用户界面成功要素
一个经过深思熟虑的产品将为自动化数据录入提供支持，通常由应用编程接口 (API) 支持。同样重要的是人机界面，这可能允许通过键盘、鼠标、条码枪、平板电脑或手机进行录入。成功部署耐用品管理系统的关键要素是尽可能不影响最终用户的使用，同时能够支持未来提高自动化程度。这意味着，随着任务的自动执行，可以轻松地调整自动化行为。同样重要的是，要为用户社区提供可视化元素。
为此，SmartFactory Durables Management 采用下列几项指导原则：
- 导航功能和直观设计是帮助用户成功采用耐用品管理系统的重要因素。
- 为该应用程序提供支持的所有界面都需要采用精益高效原则。
- 这类界面必须经过精心设计，以便于用户自然而然地进行思考，并能以简单明了的方式处理单个操作或批量操作。
- 如果界面能够以人类行为自然延伸的方式支持这些操作，那将是最理想的。
- 所有这些不同元素都必须支持输入功能，以驱动状态模型的行为。
- 设备界面或 RFID 标签也有助于在设施中实现耐用品可追溯性。
- 完善的用户界面让用户能够在宏观层面上直观地看到相应耐用品，如 BIB。此外，通过该可视化界面深入查看单个插座的能力也很有必要。（参见图 3。）
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/04/figure-3-scaled.jpg) 图 3：SmartFactory Durables Management 具有现代用户界面和卓越用户体验。
### 总结
SmartFactory Durables Management 的实施对于在从源头到抵达设施的整个制造过程中追踪资产至关重要。这使半导体制造商能够有效管理资产的运行状况、成本和性能，并轻松找到它们。借助 Durables Management 系统，可以实现更优化的操作流程。通过追踪和追溯资产的运行状况和位置，可以执行排程和分期等更复杂的活动，从而确保在特定任务中有效利用耐用品。此外，得益于向后追溯供应商的能力，还能提升供应商质量，使管理层能够根据耐用品的性能和供货情况做出关于修改业务流程的明智决策，从而为生产需求提供支持。
## 关于作者
Selim Nahas，全球工艺质量总监
Selim Nahas 负责领导工艺质量团队。他在半导体工厂自动化系统领域拥有29年丰富经验，是专注于开发提升半导体制造质量的新解决方案与方法的专业技术营销专家。其领导的工艺质量团队汇聚了多领域专业人才与技术资源，致力于开发和部署面向在线测试与电性测试的统计过程控制 (SPC)，以及故障检测、实时运行控制 (Run to Run) 和配方管理系统。整套技术方案与业内最先进的知识管理系统紧密整合。
Yoram Barak，战略营销部
在2020年加入应用材料公司自动化产品事业部之前，Yoram 曾担任巴斯夫人类营养业务部的全球市场经理，更早之前是巴斯夫生物科学研发部门的创新经理。Yoram 拥有耶路撒冷希伯来大学动物科学博士学位，并在其职业生涯中专注于生物技术领域。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [智能制造能为您带来什么益处？](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/smart-manufacturing-benefits/)
**Published:** April 23, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 为创新型半导体制造带企业带来的显著益处
**Content:**
智能制造是一个在许多行业中被广泛使用的术语。 智能制造是一个在许多行业中被广泛使用的术语。虽然这个词已经变得司空见惯，但要准确识别它的智能之处以及它对半导体制造企业具体意味着什么却并非易事。 从本质上讲，智能制造是一种集成了多个工厂系统（如批次跟踪、工艺、排程和配送系统）的方法，以提高数据和通信的准确性和质量。 以下是智能制造解决方案为半导体制造带来的七大好处。
### 通过协作提高生产力
智能制造可以将通常不在一起工作的人员以及通常不交互的设备数据连接起来。 智能制造解决方案整合来自多个来源的数据，使得所有用户都能通过仪表面板轻松访问，从而实现车间、生产基地和公司之间的协作。
Smart manufacturing creates new communication and data links between humans and equipment
### Actionable insights
实时洞察提供的数字信息能更好地利用资源，并优化工厂绩效。 实时了解生产线上发生的情况，包括问题及其原因的即时通知，有助于更好地解决问题，减少停机时间，提高生产效率。
### 提高效率
准确了解设备和工艺状态可让您预测停机时间和故障。 采用预测性和规范性维护，使您能够计划最佳维护周期。 此外，通过自动数据捕获和分析，系统可以识别问题何时出现，通知相关人员并推荐（甚至实施）适当的干预措施。
### 快速做出正确的决定
系统集成、实时数据和用户友好的界面能帮助您更快、更明智地解决问题，从而提高整体质量。
### 持续改进
智能制造提供的大量数据可以让您发现趋势、确定需要改进的领域，并制定计划。 一旦实施，实时数据可以让您深入了解您的操作如何影响了您的关键绩效指标，如此您就可以专注于其他领域的改进。
### 准确并按时交付
通过更好地洞察和控制批次生产周期和产量，以及更好地利用资源，智能制造有助于准确预测交付时间表并严格执行。
### 安全选项
您可以选择在企业内部、安全云端或选用两者混合的方式存储数据，以满足您的工厂运营和数据需求。
最重要的是，智能制造的实施方式可根据工厂规模和业务优先级而有所不同。 具体的解决方案取决于您最关注的关键绩效指标，以及您和客户的需求。
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [Shaping the future to create intelligent factories](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/shaping-the-future-to-create-intelligent-factories/)
**Published:** October 18, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Manufacturers rely on SmartFactory solutions to improve process quality, increase factory performance, and maximize performance of equipment.
**Content:**
Manufacturers rely on SmartFactory solutions to improve process quality, increase factory performance, and maximize performance of equipment.
#### Transcript
We Power Achievement, using intelligence and data to deliver higher yield. We Power Accomplishment, real-time decisions, helping factories deliver product on time. We Power Accuracy, helping factories optimize process and line control. We Power Action, providing solutions to make on-the-move edge decisions. Applied SmartFactory, your complete Automation Software Solution.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [将人工操作自动化：半导体制造的耗材管理](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/management-for-semiconductor-manufacturing/)
**Published:** September 12, 2024
**Author:** Yoram Barak, Global Product Manager
**Excerpt:** 耗材——生产车间里的无名英雄
**Content:**
## 内容概览
- [ 耗材管理挑战概述 ](#index1)
- [ 耗材的生命周期管理 ](#index2)
- [ 耗材管理系统解析 ](#index3)
- [ 耗材管理中的难点痛点 ](#index4)
- [ 应用场景案例 ](#index5)
- [ 结论 ](#index6)
### 耗材管理挑战概述
在我们之前的[博客](/zh-hans/semiconductor-blog/manufacturing-execution/durables-management-for-semiconductor-manufacturing/)中，我们深入探讨了半导体制造中耐用品管理所面临的挑战与机遇，重点分析了这些可移动扩展组件在制造流程中的关键作用。本文将聚焦耗材管理这一全新挑战领域。与耐用品不同，耗材会在生产过程中被消耗掉，因此需要建立完善的管理系统来追踪其从采购到废弃的整个生命周期。对于化学品、气体、靶材等耗材的高效管理至关重要，任何疏漏都可能导致生产延误、成本上升乃至产品质量问题。在这篇后续讨论中，我们将解析耗材管理的复杂性，并探讨如何通过创新软件解决方案应对这些挑战。
生产车间常用耗材示例（更多类型参见下方图1）：
**洁净气体 (Clean Gas)：**制造过程中维持无污染环境的关键材料。
**湿法化学品 (Wet Chemical)：**晶圆制造中用于清洗、蚀刻和去胶的化学溶液。
**显影液 (Developer)：**光刻工艺中将电路图像显影至晶圆表面的化学制剂。
**扩散材料 (Diffusion Materials)：**包含改变硅片电学特性的掺杂剂。
**蚀刻气体 (Etch Gas)：**用于蚀刻去除多余材料以形成电路图案的特种气体。
**流体分配材料 (Fluid Dispense)：**制造过程中各类工艺流体的分配系统耗材。
**光刻胶 (Photoresist)：**涂在晶圆表面的一种感光材料，用于形成图案涂层。
**CMP 抛光垫 (CMP Pads)**：化学机械平坦化工艺中确保晶圆平整度的核心耗材。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/09/figure-1-examples-of-consumable-used-in-semiconductor-manufacturing.png) 图1：半导体制造中使用的耗材示例
这些耗材各司其职，都是半导体制造工艺中不可或缺的组成部分。接下来的章节我们将深入探讨耗材的生命周期、管理系统，以及在管理过程中所面临的挑战。
### 耗材的生命周期管理
从耗材抵达制造商的收货平台开始，到入库存储、投入产线使用，直至最终废弃处理或补充更换，每一个环节都需要被精确追踪和严格管控。耗材管理不当可能造成重大经济损失，导致大量废品产生，并严重影响客户订单的交付时效。耗材生命周期的关键阶段如下（如图2所示）：
**到货与存储：**耗材送达后，需立即录入库存管理系统，记录有效期、储存条件等关键参数。
**生产使用：**耗材在严格受控的生产环境中使用，以防止污染。例如热敏化学品等特殊耗材，其使用环境将直接影响耗材的兼容性、质量和保质期。
**消耗与补货：**随着耗材的消耗，系统自动发出低库存预警并协助补货，避免生产中断。通过与供应商系统对接，可实现耗材的持续补充。
**废弃处理：**使用后的耗材需按照环保和安全规范进行处置。
这一循环机制确保了耗材能够在正确的时间以理想的状态及时供应，对于维持半导体制造的高标准要求至关重要。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/09/figure-2-example-of-a-chemical-consumable-lifecycle-.png) 图2：化学类耗材生命周期示例
### 耗材管理中的难点痛点
在耗材管理过程中，主要存在以下几大挑战：
- **质量管控：**确保耗材质量至关重要，劣质材料会导致生产缺陷和良率损失。为此，必须严格把控供应商质量、加强供应商管理能力，并建立清晰可追溯的审计机制。更进一步，若能实现耗材在设备使用层面的精准追踪，并提供参数化上下文（如 SPC 统计过程控制图），将为工艺质量提升带来显著效益。
- **库存精度：**精确维护“符合规格”耗材的库存水平极为关键。
- **成本控制：**需要在高质量耗材需求与成本限制之间取得平衡。
要确保稳定高效的半导体制造，亟需一套能全面应对这些挑战、并能与其他系统无缝集成的解决方案。
### 理想的耗材管理系统
专业的软件系统可实现耗材的高效管理，这些系统需要与制造执行系统 (MES 系统)、生产排程系统、统计过程控制 (SPC) 等其他系统无缝集成。一个完善的耗材管理系统应具备以下功能：
1. **实时追踪：**监控耗材的实时位置和使用情况
2. **库存管理：**自动化库存控制，包括低库存预警和有效期提醒
3. **使用分析：**通过分析耗材的流转路径、处理过程及批次关联等数据，优化耗材使用并减少浪费
4. **合规与报告：**确保符合行业标准，并生成审计与质量控制所需报告
借助这些系统，制造商能够在运营效率与成本管理之间实现协调平衡。
### 应用场景案例
**光刻胶化学品**
在芯片制造过程中，光刻胶、湿化学品和洁净气体等耗材的作用至关重要。以某半导体制造商面临的光刻胶管理挑战为例：这类化学品对环境条件敏感且保质期有限，管理难度较大。
**问题：**制造商光刻工艺出现不一致性，导致电路图案缺陷。
**理想解决方案：**提供以下功能的软件系统：
- **环境控制：**软件与生产车间的设备、存储以及运输过程中的环境控制系统集成，确保光刻胶的储存条件始终处于最佳状态。
- **库存监控：**实时追踪光刻胶的数量和保质期，在到期前和/或库存达到临界水平时发出警报。
- **使用追踪：**监控使用模式，使制造商能够优化订购计划，减少浪费和成本。
- **质量保障：**软件记录每批耗材的性能表现，使制造商能够将缺陷追溯到特定的化学品批次，并与供应商解决质量问题。
**物理气相沉积 (PVD) 工艺靶材**
在 PVD 工艺中，靶材作为关键组件，是通过汽化沉积在基板上形成薄膜的源材料。靶材可由多种材料制成，包括金属、合金和陶瓷。确保其清洁度并管理靶材腐蚀是一大挑战，污染物和不均匀腐蚀会严重影响薄膜的质量和一致性。
**问题：**目前缺乏完善的系统来追踪靶材使用情况，无法在需要时将其送去翻新并重新投入使用。另一个挑战是如何根据参数数据判断靶材从“使用中”转为“报废”。此外，也没有完善的系统能根据分析证书 (CofA) 验收标准来淘汰不合格靶材并退回供应商（即供应商质量管理）。
**理想解决方案：** 提供以下功能的软件系统：
- **生命周期管理：**软件与 PVD 设备、维修车间、仓库等其他位置集成，实现这些状态变更的可追溯性管理。状态模型变更基于来自个制造系统的计数器、计时器和测量数据，也可在系统中预先配置。
- **使用至报废转换：**基于供应商建议的使用寿命、参数条件或现场操作员/工程师的手动更改决策，提供最大化灵活性来追踪使用情况。
- **供应商质量管理：**软件可配置为遵循 CofA 指标，并在不满足参数要求时通过明确的状态转换（如退回供应商）来淘汰靶材。
借助此类解决方案，半导体制造商可以提高良率、减少浪费并提升整体生产效率。
### 结论
半导体制造中耗材管理面临一系列独特挑战，这些挑战直接影响着制造质量、生产效率和良率。SmartFactory Durables Management 是一款生命周期管理工具，能够有效管理多种生产资产。此类系统在追踪制造过程中资产状态和位置方面已变得至关重要。将 Durables Management 能力扩展至耗材管理领域，满足耗材特有的管理需求，显然是实现半导体制造商资产生命周期一体化管理的理想解决方案。通过这种方式，制造商将能够实现更卓越的制造质量。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Manufacturing automation software helps achieve efficiency and sustainability goals](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/achieve-efficiency-and-sustainability-goals/)
**Published:** September 12, 2024
**Author:** Cindy McVey, Contributor to SmartFactory Blogs
**Excerpt:** Advance factory automation to optimize manufacturing processes and reduce waste
**Content:**
## What’s Inside
- [ Improved productivity ](#index1)
- [ Use simulation to maximize processes ](#index2)
- [ Optimize use of resources ](#index3)
- [ Hit quality goals and avoid reruns ](#index4)
- [ Strive for full-circle sustainability ](#index5)
Semiconductors are critical components in the technology necessary to achieve carbon neutrality, from electric vehicles to renewable energy systems. These technologies have driven advancements in chip designs and placed higher volume demands on semiconductor manufacturers. Ironically, this need for more chips of higher complexity has increased the amount of energy required to produce semiconductors. This may seem daunting in the face of global sustainability goals, but there are steps semiconductor manufacturers can take to make production more efficient while improving quality and yield.
According to an article in [Forbes](https://www.forbes.com/councils/forbesbusinessdevelopmentcouncil/2023/09/08/the-future-of-renewable-energy-is-built-on-semiconductors/#:~:text=Overall%2C%20the%20number%20of%20power,10%25%20from%20now%20to%202027.), “Overall, the number of power semiconductors used in the global renewable energy market is expected to grow with a compound annual growth rate (CAGR) of 8% to 10% from now to 2027.” The semiconductor industry can use automated manufacturing solutions that integrate multiple factory systems to more sustainably meet these demands through increased efficiency and quality, which reduces energy use and waste as well as costly reruns.
### Improved productivity
Manufacturers need to improve productivity to achieve greater efficiency in their fabs and automation software can help them do so in several ways. The software can be deployed to work with multiple production processes, such as lot tracking, scheduling, and distribution, and can integrate and process data. Automation software can help manage the supply chain to identify and reduce bottlenecks, reduce planning time and increase planner productivity, and improve on-time delivery and capacity usage. It also facilitates easier communication between different people in the factory to speed decision-making.
Additionally, semiconductor manufacturers achieve more efficient production by deploying AI and ML technologies with advanced and intelligent algorithms to solve quality, productivity and supply chain challenges.
### Use simulation to maximize processes
Manufacturing simulation software can predict the impact of a particular change to the manufacturing process before it is made live in the production environment. This can identify potential problems to address prior to implementation, as well as help manufacturers find the most advantageous solutions. For example, [SmartFactory Simulation AutoSched®](/semiconductor-blog/use-cases/avalign-technologies-case-study/) is a capacity planning system that enables simulation of complex workflows to identify hidden and wasted factory capacity. It allows users to create a virtual model of a fab to analyze, predict, and optimize operations, enabling experiments with scheduling rules, equipment, and operator cycles offline.
### Optimize use of resources
Sustainability goals are easier to reach when manufacturers make the best use of equipment. When equipment use isn’t optimized, energy is wasted, and manufacturers face costly repairs and replacement parts. Faulty equipment can also lead to defective products and production reruns.
A manufacturing [scheduling system](/scheduling-faqs/) helps semiconductor manufacturers make the best use of their equipment and personnel resources. A quality factory scheduling solution can improve equipment efficiency and increase product quality and on-time delivery of products.
Additionally, [automating maintenance management](/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/) can help more efficiently manage the expensive assets of a fab while reducing the cost of repairs, parts and downtime waiting for equipment repair.
Predictive maintenance can make sure processes, equipment, and inspection systems are operating at peak efficiency, which reduces the risk of energy-intensive failures.
### Hit quality goals and avoid reruns
Wasted material negatively impacts the manufacturer’s carbon footprint both in the energy used to manufacture replacement products and in their space in landfills. Fortunately, there are many automated manufacturing solutions that can help improve quality and reduce waste.
For example, [statistical process control (SPC)](/webinars/semiconductor/smartfactory-spc-mastering-quality/) tools can help manufacturers move from a detection-based quality control method to a prevention-based one. By identifying problems early, manufacturers can take actions to correct or prevent issues with process or quality before any product is impacted. These tools also provide valuable information to help them develop overall process improvement strategies.
Recipe management systems store recipes in a secure, central repository and reduce errors, improve efficiency, increase wafer output and provide traceability.
### Strive for full-circle sustainability
Ultimately, semiconductors are vital to reducing the global carbon footprint and demand for them in these roles will likely grow. As the technology is deployed to bring innovative solutions to the world’s problem, manufacturers have many advanced automation options that can help them produce semiconductors more sustainably.
## About Cindy McVey
Cindy McVey, Contributor to the SmartFactory Blog for Semiconductor and Pharmaceutical Manufacturers
Cindy is an essential writer for our SmartFactory Blog, focusing on feature stories that highlight automation experts and their contributions to helping semiconductor and pharmaceutical manufacturers stay ahead. Her engaging content explores how these experts navigate market dynamics, technology, and people to deploy innovative factory automation solutions. Cindy's insightful writing showcases the valuable insights and expertise these professionals bring to the semiconductor and pharmaceutical manufacturing industry.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [制造效能提速50%？如何实现？](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactory-ai-transforming-manufacturing-productivity/)
**Published:** March 27, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 通过集成化的排程与数据分析技术，制造商可大幅优化运营流程，最快6个月即可见证显著成效。
**Content:**
## 文稿
今天，世界正迅速转向人工智能和机器学习技术，以满足每个商业领域的市场需求，制造业也不例外。对于更智能、更灵敏、更注重质量的需求，现在比以往任何时候都更加迫切。
应用材料公司全新推出 SmartFactory AI，借助这个首次面向半导体行业高度集成 CIM 和 AI 的平台，建立您独有的竞争优势，使用智能算法帮助您应对来自生产力和供应链的挑战。通过流媒体和学习大数据、端到端模型开发和部署，优化您的多个目标。
SmartFactory AI 可解决影响晶圆厂生产效率和良率的两项关键挑战。第一，预测模型的不足，包括批次生产周期、动态瓶颈和良率预测；第二，寻找最佳逻辑或参数值，以更优的方式控制生产流程或设备的问题，同时考虑实时和未来状态。
SmartFactory AI 是唯一可以与排程、派工和全自动解决方案集成的工业 AI 平台，可帮助您实现前所未有的产出、生产周期、利用率和良率的改善。在生产中，SmartFactory AI 收集数据，训练模型，将其部署到生产环境中，并实时监控其性能以了解该模型的运行情况。如果模型的准确性出现波动，可自动进行重新训练。
UI 解决方案可显示模型评估和性能表现的结果。SmartFactory AI 通过提供自动化模型构建、培训和部署功能以及用户友好的 UI 解决方案来推动制造业生产力变革。这种高集成度的解决方案使制造商能够在短短六个月内完成部署——这是通常开发单个模型所需时间的四分之一。
SmartFactory AI 集成到现有的 SmartFactory APF (Advanced Productivity Family) ，用户无需学习其他环境或开发语言。工程师可以使用预构建的机器学习模型或配置关键参数，集中应对晶圆厂的特定挑战，深度解决问题。利用 SmartFactory AI 提高您的生产力，建立您的竞争优势。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Catch and fix defects faster](https://appliedsmartfactory.com/semiconductor-blog/quality/defect-management/)
**Published:** August 1, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Quickly determine root cause of failures using complete, integrated defect analysis solution
**Content:**
In your fab, how reliable are your defect classifications? Do you still rely on manual processes to determine the root cause of failures? To help prevent costly yield excursions, Applied SmartFactory® Defect Management quickly identifies the origin and location of defects, classifies defects, analyzes them, and provides informed decisions for next steps.
Powered by xDMS, the system offers a total solution for tracking, identification, and classification, resulting in reduced yield loss, time to identify yield limiters, and manufacturing cost.
For details on our solution, check out our solution brief:
\[pdf-embedder url=”/wp-content/uploads/2022/08/SmartFactory-Defect-Management-Solution-Brief.pdf” height=”1000″\]
[ Download this PDF ](/wp-content/uploads/2022/08/SmartFactory-Defect-Management-Solution-Brief.pdf)
Ready to contact us to learn more about defect management and other solutions?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Enhancing decision-making in real-time scheduling: leveraging data and AI technology (Part 1/4)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** This blog series focuses on the role of data in helping semiconductor manufacturers achieve greater benefits in productivity and quality.
**Content:**
[ Part 2: Understanding and defining AI and ML ](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-2/)
## What's Inside
- [ Data in scheduling and dispatching ](#index1)
- [ Push and pull interventions ](#index2)
- [ Event handling by rule-based systems ](#index3)
- [ Moving to predictive systems ](#index4)
- [ Impact of data ](#index5)
- [ Conclusion ](#index6)
Renowned influencer James Moyne joins Samantha Duchscherer in an engaging discussion exploring the importance of integrating additional information and advanced technologies like Artificial intelligence (AI) into the semiconductor industry’s scheduling and dispatching process. The comprehensive series consists of four parts focusing on various subjects such as the importance and advantages of data, AI, and human involvement. It also delves into the obstacles faced and offers insights into the role of digital twin technology.
In this first article of the series, they focus on the current situation for scheduling and dispatching.
Sam: Why is Industry 4.0 so important to the semiconductor manufacturing industry, and how relevant is data for [scheduling](/semiconductor-blog/smartfactory-dispatching-solutions/) and dispatching?
James: The semiconductor industry leads all other industries in schedule and dispatch because semi manufacturing is a highly automated, fast-moving, flexible system. They need to make decisions quickly and in an automated fashion.
So far, the real time aspect of schedule dispatch is almost exclusive to semiconductor manufacturing. Over the past five years, this has been moving into industries like pharmaceutical and aerospace, but these industries are still behind. In fact, they are looking to semiconductor manufacturing to learn what they did so they can replicate it.
Sam: Which schedule and dispatch interventions are commonly used in the semiconductor industry today, and how do they work?
James: Right now, schedule and dispatch are [rules-based systems](/semiconductor-blog/scheduling-solutions-for-semiconductor-factories/). Using experts and data, they try to control actions such as, “When this happens along with A, B, and C, I want to make a decision and route something to a particular place.”
There are both push and pull effects. In push, the focus is on how wafers get routed from a higher-level system to resources down the line. This is essentially, ‘I have wafers and I know which piece of equipment to send them to.’
In the case of pull, the order of the processing is decided. For instance, a piece of equipment has been given four wafers to process and needs to know in what order to process them. Push and pull work together and use things like APF RTD® to do it, which is a rules-based solution.
Sam: There are many unexpected events that can occur in manufacturing. How are these events currently handled by these rule-based systems?
James: The current systems are currently both predictive and reactive. They are reactive in the sense that the system doesn’t have a predetermined or automated next step for events it didn’t predict. It sort of throws its hands up in the face of the unexpected. This is where a manual intervention by a subject matter expert is needed. That person comes in and determines either they need to add a new rule because this is the type of thing that could happen in the future or, if they deem it a one-time thing, how to resolve it in that instance.
They are predictive in that they take into consideration the types of rules you want to have, the way you want the equipment to operate, the throughput you want to get, and the quality, and then make decisions such as, ‘I want to route some of the more expensive wafers to a higher producing piece of equipment.’
Sam: What is needed to make these systems more predictive and advance these systems to the next level?
James: We have started adding this predictive aspect into scheduling and dispatching, and this is where data comes in. You first need to collect a lot of data not just about scheduling and dispatch, but about things that may impact them. A good example of this is maintenance. If you collect a lot of data, you may realize there are maintenance trends associated with a piece of equipment. You start to understand when it’s going to go down, how often, and more importantly, the variability of those numbers. You can then start to incorporate that into your scheduling and dispatch.
How quickly you can feel confident in your predictive maintenance depends on how much historical data you have. If you have a lot, you can see the patterns in history. If, for example, you have two years of maintenance logs for a piece of equipment, you can determine the behavior of the maintenance for this tool and use that moving forward. Without this type of historical data, you need to start from scratch and develop confidence in your predictive maintenance as you go. So, it’s kind of a function of how long your data archives are, how reliable they are, how good the data quality is, how dynamic or changing the behavior patterns are over time, and things like that.
Sam: Where are you finding data is having the most impact in predicting scheduling and dispatching events?
James: What we’re finding in some of the research is that you can break this predictive aspect into two pieces, the first being dealing with minor glitches. An example of this is when everything is going great, but maybe the processing time of a piece of equipment varies from one minute to one minute ten seconds; some decisions can be made based on that prediction and variability.
The second piece is in predicting more show-stopper types of events. This is where, for instance, unscheduled downtime is predicted and that is conveyed to scheduling dispatch. This enables more important decisions, such as rerouting, to be made. You can see where the data driven aspect steers that second piece, the catastrophic or large-scale changes you must make to your scheduling dispatch decisions.
It’s important to note data isn’t just driving schedule dispatch directly. It’s affecting applications whose outputs will affect schedule dispatch, such as predictive maintenance and run-to-run control, which is trying to make your process run more efficiently and produce better quality wafers. If you know that the run-to-run controller is producing better quality wafers on tool A versus tool B, that’s important for scheduling.
What we’re just starting to do now is roll that type of information into schedule dispatch. There are a lot of opportunities for data-driven things to impact schedule dispatch in the future, such as [integrating AI](/ai/), ML, and digital twin.
### Conclusion
The semiconductor manufacturing industry is a leader in real time scheduling and dispatching. As other industries turn to it as a benchmark for how to implement this, the semiconductor industry is beginning to take advantage of the opportunities data provides to have more predictive scheduling and dispatch systems that can improve productivity and quality.
In our next article, we’ll define AI and ML.
## About Dr. Moyne
Dr. James Moyne is an Associate Research Scientist at the University of Michigan. He specializes in improving decision-making by bringing more information into the scheduling and dispatching area. Dr. Moyne is experienced in prediction technologies such as predictive maintenance, model-based process control, virtual metrology, and yield prediction. He also focuses on smart manufacturing concepts like digital twin and analytics, working towards the implementation of smart manufacturing in the microelectronics industry.
Dr. Moyne actively supports advanced process control through his co-chairing efforts in industry associations and leadership roles, including the IMA-APC Council, the International Roadmap for Devices and Systems (IRDS) Factory Integration focus group, the SEMI Information and Control Standards committee, and the annual APC-SM Conference in the United States.
With his extensive experience and expertise, Dr. Moyne is highly regarded as a consultant for standards and technology. He has made significant contributions to the field of smart manufacturing, prediction, and big data technologies.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [用于半导体制造中 Q-time 管理的深度强化学习 (RL)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/deep-reinforcement-learning/)
**Published:** April 10, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 使用深度强化学习 (RL) 透过自动控制 Q-time 管理将良率损失降至最低
**Content:**
队列等待时间约束 (QTC) 是指一个批次在流程中两个流程步骤之间允许等待的时间限值。 在半导体制造中，超过该时间限值的批次会导致良率损失，需要返工，或予以报废。 QTC 很难进行排程，因为批次需要一直等到最后步骤的加工有可用产能时，才能放行进入第一个流程步骤。 然而，精确计算是否有足够产能的计算成本很高。
在本研究中，我们提出一种深度强化学习 (RL) 方法来管理放行批次进入队列等待约束。 我们分析了该强化学习方法的性能，并将其与七种基线解决方案进行比较。 我们的实证评估显示，该强化学习方法在队列等待超时次数和完工时间等五项性能指标上均优于基线解决方案，而需要的在线计算时间可忽略不计。
了解更多详细信息，请查阅或下载这篇 PDF 文件：
\[pdf-embedder url=”/wp-content/uploads/2024/04/DEEP-REINFORCEMENT-LEARNING-FOR-QUEUE-TIME-MANAGEMENT-IN-SEMICONDUCTOR-MANUFACTURING-rev2\_CN.pdf” height=”1000″\]
[ 下载 PDF 文件 ](https://appliedsmartfactory.com/wp-content/uploads/2024/04/DEEP-REINFORCEMENT-LEARNING-FOR-QUEUE-TIME-MANAGEMENT-IN-SEMICONDUCTOR-MANUFACTURING-rev2_CN.pdf)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [人工智能：革命性改变工厂自动化，重塑生产体验](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 与我们的技术领导 David Hanny、Selim Nahas、Madhav Kidambi 和 Dan Meier 一起，探索 AI 如何加速新一代工厂自动化发展，并深刻改变我们的生产生活方式。
**Content:**
#### 文稿
接下来让我们稍微聚焦一下人工智能的话题。你刚才简要提到了晶圆制造环境日益增长的复杂性。最近我接触了一位客户，我们非常简短地讨论了 AI。客户打趣说，我不需要 AI。
我需要的是“为什么”，我需要能解释问题根源的系统，我需要能真正解决制造业业务痛点的方案。
在座各位有多少人对 ChatGPT 的上市速度感到惊讶？没错，我的意思是，我们都知道技术会进步，但谁能料到它的成熟度如此惊人？这是有史以来发展最快的科技产品。确实如此。
现在做个小小预测，如果制造业出现类似的突破，将彻底颠覆现有市场格局。目前还没有任何技术能达到这种程度。
问题在于，谁具备这样的实力？有没有人在这个领域真正有能力实现这一技术突破？就我个人而言，我是有偏向的。我认为我们可以。因为如果你想做。过去就有很多公司有这样的想法，他们认为我们可以做到这一点，对吧？他们有种信念，觉得我们什么都能做到。查看数据，挖掘数据，并结合 AI 原理来挖掘数据的价值。
但是他们忽略了最基本的原则，数据内涵是什么？清晰度如何？分辨率怎样？实际意义何在？但如果我们希望进入一个在产能上真正超越当前工厂的阶段，除非基础非常扎实，否则是不可能实现的。为了做到这一点，就必须有能力提供完整的计算机集成制造系统 (CIM)。
这些能力我们都已经具备。目前，SmartFactory 实现系统之间的互联互通。举个例子，我们可以实现机器人驾驶或执行相关行动，这正是 SmartFactory 的独特之处。可以启用 AI 设备，基于 AI 的设备在工厂中自主行动。
我们今天已经看到了这一点，对吧？其次，是基于机器学习的能力，识别异常模式或者预测故障模型等关键指标的应用。我们在这方面已经取得很大进展。SmartFactory 的另一个独特价值体现在，我们之前谈到的集成能力，我们可以从工厂生产系统、MES 和 E3 平台获取数据，并利用这些数据构建更好的机器学习模型。
所以，我们实际上讨论的是非常具体的 AI 应用模型，对吧？比如管理晶圆良率的 AI，管理生产效率或生产周期或产能的 AI，或设备负载管理的 AI，对吧？我认为，通过 SmartFactory 软件套件，我们正在构建一个多方位的基础架构，为未来的 AI 发展奠定根基。是的，我们需要在各个组件中植入 AI 能力。但当我们迈向下一个阶段，实现通用人工智能 (AGI) 时，就能打造真正掌控整个工厂的 AI 系统。
这让我感到无比振奋，展位未来 5 到 10 年的发展蓝图，将生产力提升至前所未有的高度。目前，我们已经在工厂的各个子系统层面实现了局部优化，而通过工厂级 AI 整合所有独立组件，实现智能排程和精准控制，就能以极少的资源创造最大化的价值。
这个前景令人无比期待。
**Semiconductor Category:** Smartclips, Panel
**Semiconductor Tag:** Smartclips
---
### [效能释放：晶圆厂优化之道](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Amnon Shenfeld 分享其提升晶圆厂效能的独到方法，揭秘 SmartFactory 解决方案脱颖而出的创新实践。
**Content:**
#### 文稿
我是 Amnon Shenfeld，现任应用材料公司自动化产品事业部的首席技术官。我认为，从技术角度来看，应用材料公司 SmartFactory 解决方案的核心优势在于其对设计思维的专注。这本质上意味着，我们始终将可用性放在首位，我们真正关心客户，并努力思考他们所面临的各种挑战，以及我们能为客户带来的全部价值。
目前，大多数在晶圆厂运行的软件主要关注于设备本身。而在某些情况下，这种做法可能忽略了“人”的因素。在当今市场上，分析技术与大数据显然已成为提升效率和优化晶圆厂工艺流程学习的关键要素。而我们坚持以人为本的理念，即使我们现在掌握的制造技术已走在世界前端，以人为本的理念始终是我们关注和聚焦的重点。
应用材料公司 SmartFactory 解决方案作为行业领军者，已在半导体制造领域深耕多年。我们开始思考，如何通过优化软件功能和运行方式降低整体拥有成本。在对系统架构进行深入分析后，我们发现其中存在若干可优化的模块，具备现代化升级的潜力。这些改造不仅提升了系统的运行效率，也为未来的扩展性和云原生部署奠定了基础。这是我们独有的技术优势，如果您采用云原生架构，在大多数情况下可实现更高算力，也就意味着更高效的晶圆厂运行效率，同时保持原有的安全性与冗余性。就像以前一样，而无需再依赖大量硬件资源来“待命”，等待故障发生。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Smartclips, Semi
---
### [Reduce production noise and boost operation efficiency](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
**Published:** October 11, 2022
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** SmartFactory team unveils new solution for handling alarms
**Content:**
## What’s Inside
- [ SmartFactory Alarm Management solution ](#index1)
- [ Key features ](#index2)
- [ Conclusion ](#index3)
Did you know that the number of alarms raised by various systems or devices can reach up to 1000 per second in high-volume manufacturing factories? In fact, managing numerous concurrent alarms or alerts becomes a major distraction for operators, which means they can miss critical alarms that can cause scrapped wafers or excursions. When operators experience these issues, they become de-sensitized, getting overwhelmed with alarm spam. As a result, responses to alarms are delayed, leaving tools in a problematic state for extended periods of time, or misprocessed wafers continue to run without being inspected. (See figure 1 for an alarm management overview.)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/10/alarm-management-works.jpg) Figure 1: An overview of how alarm management works.
Handling hundreds and thousands of alarms per day is still a common operational challenge for many high-volume manufacturing factories. In fact, to handle the load, manufacturers must consistently manage and respond to large numbers of alarms in real-time. Relying on a solution to efficiently manage alarms in the factory to optimize operations means operators are empowered to focus on critical alarms that need immediate attention and filter out the less important alarms.
### SmartFactory Alarm Management solution
SmartFactory Alarm Management, is a solution built to address these alarm management challenges in real-time. Figure 2 shows how filtering alarms improves productivity.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/10/fig1-alarm-validity.png) Figure 2: Alarms are filtered based on rules, enabling operators to focus on valid alarms
### Key features
**Excursion prevention to improve yield:** Since alarms are filtered, operators can quickly identify the critical alerts, making it easier for them to address priority issues quickly and avoid misprocessing wafers.
**Reduced tool downtime to increase tool utilization:** Faster responses to targeted alarms enable technicians and engineers to take quicker and appropriate action and save tool time that otherwise would be lost.
**Reduced cycle time to increase throughput:** Reduced production noise and alarm data consolidation enables users to troubleshoot production issues quickly. Resulting in labor productivity improvements and operations efficiency.
### Conclusion
SmartFactory Alarm Management efficiently manages alarms in the factory to optimize operations. The solution will: - Centralize real-time alarm handling in one single location.
- Streamline management of alarms from various systems through consistent procedures.
- Apply alarm filtering hierarchy to choose the best alarm rules.
- Apply alarm criticality hierarchy to take the best alarm actions.
- Reduce production noise with a de-duplication algorithm.
- Consolidate alarm data for fast troubleshooting and resolution.
Semiconductor manufacturers can direct their attention to the critical alarms for better use of time and resources.
## FAQs
#### Why is quick response to alarms necessary?
If response to alarms takes too long, tools remain in a problematic state for a long time or the amount of misprocessed wafers continues to build up without being inspected.
#### What are the benefits of real-time alarm management?
- Saves lost tool time
- Reduces product quality risks
- Fast-tracks factory wide alarms
#### How does SmartFactory Alarm Management optimize operations?
By efficiently managing alarms, SmartFactory Alarm Management helps you more quickly identify, prioritize and respond to alerts and take appropriate action.
Ready to contact us to learn more about our SmartFactory Alarm Management?
[ Connect with us here ](/connect)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released
---
### [Smarter alarm management: from chaos to control](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/smart-alarm-management-for-semiconductor-industry/)
**Published:** June 6, 2025
**Author:** Yoram Barak, Global Product Manager
**Excerpt:** The right alarms at the right time, to the right people
**Content:**
## What’s Inside
- [ The problem: alarm overload and its consequences ](#index1)
- [ The research: data-driven insights into alarm performance ](#index2)
- [ The solution: SmartFactory Alarm Management ](#index3)
- [ The payoff: quality, efficiency, and peace of mind ](#index4)
- [ Use case example ](#index5)
- [ Conclusion ](#index6)
Quality and uptime are paramount in semiconductor manufacturing, making alarm systems both a lifeline and a liability. When managed well, they safeguard quality and productivity. When mismanaged, they flood operators with noise and obscure critical issues, as well as contribute to costly downtime and scrap. This blog explores how a modern alarm management system can address this challenge.
### The problem: alarm overload and its consequences
Semiconductor fabs are complex ecosystems. A single process deviation can trigger a cascade of alarms across multiple systems. Operators are often inundated with notifications—many of them false, redundant, or low-priority (see Figure 1). In fact, a study at STMicroelectronics revealed that more than 95% of alarms were low-priority, and only about 4% of alarms triggered any action \[Al-kharaz et al., 2019\][1](#references). Worse, a small subset of alarms (just 100 out of more than 5,000) accounted for 70% of all alarm activity.
This “alarm noise” leads to:
- Delayed responses to critical issues.
- Operator desensitization, increasing the risk of missed alarms.
- Reduced productivity and increased scrap rates.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/06/figure-1-alarm.jpg) Figure 1: Alarms come from many sources. The ability to quickly alert the right people on the floor with the most critical alarms and suppress the nuisance alarms is an advantage.
### The research: data-driven insights into alarm performance
Academic studies reinforce the need for smarter alarm systems. Key findings include: - **Alarm floods**—bursts of alarms in short timeframes—are often caused by chattering or repeating alarms and can obscure critical issues.
- **Nuisance alarms** (e.g., stale or standing alarms) contribute significantly to operator overload and should be reclassified or removed.
- **Machine learning models** can predict product scrap based on alarm patterns, achieving up to 75% accuracy (Al-kharaz et al., 2021)[2](#references). This opens the door to predictive quality control using alarm data.
### The solution: SmartFactory Alarm Management
SmartFactory Alarm Management addresses these challenges head-on. It offers a centralized, automated, and integrated approach to alarm handling:
- **Automated filtering and prioritization:** Only meaningful alarms are forwarded, with duplicates and false alarms suppressed.
- **Configurable notifications:** Alerts are sent only to relevant staff, via email or SMS, with escalation paths if unacknowledged.
- **Action automation:** Alarms can trigger predefined actions like putting a lot on hold or logging a tool down across MES, equipment automation, and other systems.
- **Comprehensive dashboarding:** A real-time, factory-wide view of active alarms, plus historical analysis for root cause investigation.
### The payoff: quality, efficiency, and peace of mind
By integrating alarm management into the broader SmartFactory ecosystem, manufacturers can:
- **Reduce downtime** by accelerating root cause analysis.
- **Improve yield** by catching quality-impacting issues earlier.
- **Empower operators** with actionable, relevant alerts.
- **Streamline compliance** with ISA and EEMUA standards.
### Use case example
The SmartFactory Alarm Management 3.4.0 release included the integration of SmartFactory [Knowledge Advisor](/semiconductor-blog/quality/spc-and-fdc-violations/) (KA), which supports both containment actions (e.g., stopping a tool to prevent further issues) and corrective actions (e.g., steps to fix the underlying problem and return the tool to production). The integration of KA into the Alarm Management Solution (AMS) provides structured workflows for resolving alarms; Alarm Management identifies alarms from various tools and systems, and KA offers detailed action plans to address them. This improves efficiency of alarm management workflows, ensuring that alarms are not only identified, but also resolved promptly and effectively.
So how does it work? AMS identifies critical alarms, contains the event, and notifies users, but it does not provide steps for resolution. KA fills this gap by offering action plans that guide users through the resolution process, ensuring that alarms are addressed systematically. The application can support both automated and manual corrective actions. For example, an alarm can trigger an automated response to stop a tool, or it can generate a manual action plan for a user to follow. This streamlines the user experience by consolidating alarm management and resolution for E2E containment and correction and improves workflow efficiency.
### Conclusion
Alarm management is not just about silencing the noise—it’s about amplifying the signal. With the right tools and data-driven strategies, semiconductor manufacturers can turn alarms from a source of frustration into a foundation for smarter, safer, and more efficient operations. If you’re ready to rethink how your fab handles alarms, [reach out](/connect). You might be surprised at the benefits a smarter Alarm Management system can bring to your factory.
### References
\[1\] Al-Kharaz et al., 2019 – Evaluation of Alarm System Performance and Management in Semiconductor Manufacturing. 6th International Conference on Control, Decision and Information Technologies (CoDIT’19).
[2] Al-Kharaz et al., 2021 – From Alarm System Events Towards Quality Inspection of The Final Product: Application to a Semiconductor Industry. 2021 European Control Conference (ECC)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [智能制造：进化中的竞争优势](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Phil Walker 探讨了 SmartFactory 解决方案在智能制造发展中的关键作用，并揭示了塑造行业未来的尖端技术进展。
**Content:**
#### 文稿
大家好！我是 Phil Walker。我在应用材料公司负责维护与持续性收益产品业务，我在制造业已有多年经验。回想刚入行时，作为一名年轻工程师，现在回头看甚至觉得有些难以置信，我们当时的制造流程竟然全靠秒表和纸质记录表来完成。
我们会观察制造流程的每个步骤，用秒表测量每个步骤时长，在笔记本上记录数据，再整理到电子表格中进行分析。在当时，这已经算是相当“智能“的工厂了。显然，技术已经今非昔比。我们现在有各种系统，可以更快地采集数据，更快地分析数据，更快地实现可视化。说实话，相比不久前的过去，这一切已经发生了翻天覆地的变化。这堪称一场彻底的变革。
现在我们的分析周期大幅缩短，工艺优化效率也显著提升。在下一波智能工厂的发展浪潮中，我们将实现之前提到的所有基础工序的全面自动化。
在未来的智能工厂中，机器学习与人工智能不仅会协助制定数据采集和分析方案，更能自主完成数据获取工作，真正实现 AI 自主运作。制造业即将迎来的变革是，过去那些基础工作，包括信息采集和处理的基准流程，绝大部分都将由智能系统代劳。这些系统已经在思考如何更好地收集和分析信息，但这仍然需要工程师去理解这些信息。利用系统提供的基础数据和洞察，再加入工程师的创新思维和创造力，从而实现质的飞跃。
这就是 SmartFactory 解决方案的核心价值，这也是让我对参与应用材料公司这项工作感到如此振奋的原因。我们倾注全力开发的创新技术，不仅致力于为工程师提供更多有价值的基础数据，更参与到全球尖端制造的最前沿。我们拥有得天独厚的优势，能够持续推动制造业和智能工厂迈向新高度。
这正是让我对应用材料公司的研发工作感到振奋的原因，以及我们对制造业未来所能带来的无限可能
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Smartclips, Semi
---
### [What if you could improve manufacturing performance in half the time?](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactory-ai-transforming-manufacturing-productivity/)
**Published:** March 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** With integrated scheduling and analytics, manufacturers are streamlining operations and seeing results in as little as six months.
**Content:**
### Transcript
Today, the world is rapidly moving to artificial intelligence and machine learning to service the demands of the market in every business sector. The world of manufacturing is no different. The necessity to be more intelligent, more responsive, and more quality-driven is needed more than ever before.
Introducing Applied Materials SmartFactory AI. Create your own competitive advantage with the first CIM-integrated AI platform for semiconductors, helping expedite solutions for your productivity and supply chain challenges using intelligent algorithms. Optimize your multiple objectives through streaming and learning from big data, end-to-end model development and deployment.
SmartFactory AI addresses two main problems that affect fab productivity and yield. One, the shortcomings of the prediction model, including lot cycle time, dynamic bottlenecks and yield forecasting. And two, the problem of finding the best logic or parameter values to control production flow or equipment operations in an optimal way, considering real-time and future status.
SmartFactory AI is the only industrial AI platform that can integrate with scheduling, dispatching, and full-auto solutions to help you achieve improved throughput, cycle times, utilization, and yield like never before. In production, SmartFactory AI collects data, trains a model, deploys it to the production environment, and monitors its performance in real-time to see how the model is performing. If there are fluctuations in the model’s accuracy, it is automatically retrained.
The solution UI shows results of the model evaluation and performance. SmartFactory AI is transforming manufacturing productivity by providing automated model building, training, and deployment capabilities, as well as user-friendly solution UI. This fully integrated solution is enabling manufacturers to manage deployments in as little as six months, a quarter of the time it typically takes them to develop individual models.
SmartFactory AI is integrated into the existing SmartFactory Advanced Productivity family, and there is no need for users to learn additional environments or languages. Engineers can use pre-built ML models or configure key parameters to help focus on a fab’s particular challenges and expands the depth of problem-solving. Start amplifying your productivity and create your own competitive advantage with SmartFactory AI.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [SmartFactory 解决方案: 驱动制造业未来](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 聆听技术专家 David Hanny、Selim Nahas、Madhav Kidambi 和 Dan Meier 的深度解析，了解 SmartFactory 自动化解决方案如何重塑各类规模工厂的生产效率与产品质量。
**Content:**
#### 文稿
我们经常被问到一个问题，什么是 SmartFactory 解决方案？对你来说意味着什么？ 我猜你们对此都有不同的看法？是的。在我看来，SmartFactory 解决方案意味着一套完全集成化、可互联协作的制造系统。可以帮助你实时获取物理设备数据，这样你就可以快速响应，制定更优策略以提升产品质量、提高产量，并重点实现工厂运行的可预测性。
现代生产设施涉及多种不同的软件：排程软件、良率控制软件、批次追踪软件等。关键在于这些软件如何实现深度集成，形成一个共生体系。对我来说，这正是 SmartFactory 软件套件在业界的独特优势。SmartFactory 套件的集成水平无可比拟，对于我来说，集成正是其核心价值。
真正的集成体现在多个系统一起协同解决问题，系统之间的智能触发，这意味着不仅仅是一个数据管道，更是数据的共享。
有时还包括逻辑共享，实现系统间交互操作。共同解决制造难题这种深度集成，很可能是智能制造三大核心要素之一。我的理解聚焦在已知与未知领域。具体而言，智能工厂的环境应支持制造知识挖掘，并将洞察转化为生产行为，那么它就是一个智能工厂。因为它帮助我，首先发现未知规律；其次是将新知识转化为自动化系统行为，持续扩展认知边界，优化现有工艺规范，最终实现工厂现场的实时闭环优化。这种行为对工厂运行产生实时影响。
当前我们手头的数据利用率是不足的，没错。这是首要改进点。若能识别关键数据特征，可丢弃大量今天仍保留的数据，却没有明确目的。核心命题是能否构建支持制造认知进化的环境，实现原本不可行的创新？这正是我对 SmartFactory 解决方案的解读。
SmartFactory 的本质是将软件功能映射到工厂核心指标，提升运营效率、优化工艺质量、提高生产效率。这些至关重要。
**Semiconductor Category:** Smartclips, Panel
**Semiconductor Tag:** Smartclips
---
### [Using a framework to validate factory scheduling solution systems (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-2/)
**Published:** November 14, 2023
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** Make more advanced validations and fine tune the schedule generated by a factory schedule solution system to get the most from your semiconductor factory
**Content:**
In [Part 1](/blog/scheduling-solution-systems-part-1/) of **“Using a framework to validate factory scheduling solution systems,”** we looked at how a validation framework lets manufacturers determine the validity of a schedule that has been produced by a [factory scheduling solution system](/semiconductor/productivity-solutions/scheduling/). Methods for basic and secondary level validations, as well as evaluation of the input data, were discussed. We’ll now look at the next step, conducting advanced validations and fine tuning the factory schedule.
### Factory schedule debugging and traceability
To validate, understand and fine tune a factory scheduling solution, you need to be able to explain and understand the decision making that went into the solution. When an end user configures a scheduler, they do so with expectations and assumptions for how it should behave. When that doesn’t happen, manufacturers need to be able to find out why by testing and validating those assumptions. (This is also part of the factory schedule fine tuning process.) The following information will help you understand that decision making:
- Lot Assignment: Why is a particular lot assigned to a particular tool in a schedule? This explanation can be encoded visually in the form of a score, weightage, criteria, percentage, and/or list of tool and lot attributes.
- Companies often continue the use of existing tools and methods to avoid ‘rocking the boat’ in manufacturing, despite the development of improved platforms that go well beyond Excel.
- Winners and losers: The details of the lots that competed with any assigned or selected lot and lost out. In a factory with a lot of active work in process (WIP), and when the schedule horizon is not able to accommodate all the active lots in the schedule, you should be able to find details of unselected lots which lost out to the winning lots.
### Advanced validation: quality of the schedule
Depending on the factory, the schedule is set up to automatically refresh from every five minutes up to one hour. The stability and reliability of the factory schedule run after run and over a rolling period needs to be tracked as part of solution validation, as it mimics the actual production environment at the customer factory. What constitutes a good schedule can be based on quantitative criteria and KPIs, but there is also a subjective component to the evaluation based on factory physics tradeoffs which again can be linked back to KPIs. Depending on the use case, some of the KPIs that, when tracked, would indicate the efficacy of a scheduling solution are:
- **Schedule compliance**: Lagging indicator of assignment compliance to measure lots ran on the tools to which they were assigned during dispatch.
- **Projected moves and outs:** Leading indicator of projected moves and outs by the scheduler by end of shift or day is a measure of the throughput of the factory.
- **Tool utilization:** Standby time (SBY) with WIP (leading to avoidable white space in a schedule) and SBY without WIP (which can lead to bottleneck tools being starved of work). Standby time in a tool is a measure of the unutilized capacity available in the tool and, in typical use cases, the scheduler is designed to minimize this component of total tool time.
- **Finished lot cycle time:** Tracking the finished lot cycle over a period is a lagging indicator for the effectiveness of the schedule. If the product mix, starts, and equipment qualification matrix did not dramatically change, then there should be a downward trend of finished lot cycle time before and after the deployment of the scheduler.
- **Factory X factor, DPML, CT pace or WIP overturns:** Tracking the trend of leading cycle time measures like Days Per Masking Layer, or X factor, or WIP turns is an indicator for the effectiveness of the schedule. If the product mix, starts, and equipment qualification matrix did not dramatically change, then there should be a downward trend of these KPIs before and after the deployment of the scheduler.
- On time delivery percentage or lagging lots percentage: In factories where lot due dates matter and this is a core objective, scheduler behavior is expected to improve the OTD metrics.
- Average train size: In factories where setup minimization is a core objective of the scheduling solution, average train size is a measure that can evaluate the quality of the schedule.
These KPIs also need to be generated on a forward-looking basis as part of the factory scheduling output. This will allow the end users to gain an understanding of the outcomes predicted by scheduling and validate the schedule.
### Role in successful implementation
A validation framework enables a structured way of conducting a thorough evaluation of the factory schedules generated by the solution. Both the software vendor and the customer need to be aligned on this to manage expectations, as well as for the successful deployment and management of the solution. There is no such thing as a ‘perfect schedule.’ Fine tuning is by default a part of making a factory scheduling solution work for an end user in the absence of AI/ML based methods which can automate the fine-tuning process to realize the theoretically achievable productivity gains.
## What’s Inside
- [ Schedule debugging and traceability ](#index1)
- [ Advanced validation: quality of the schedule ](#index2)
- [ Role in successful implementation ](#index3)
In [Part 1](/semiconductor-blog/scheduling-solution-systems-part-1/) of “Using a framework to validate factory scheduling solution systems,” we looked at how a validation framework lets manufacturers determine the validity of a schedule that has been produced by a [factory scheduling solution system](/semiconductor/productivity-solutions/scheduling/). Methods for basic and secondary level validations, as well as evaluation of the input data, were discussed. We’ll now look at the next step, conducting advanced validations and fine tuning the schedule.
### Schedule debugging and traceability
To validate, understand and fine tune a scheduling solution, you need to be able to explain and understand the decision making that went into the solution. When an end user configures a scheduler, they do so with expectations and assumptions for how it should behave. When that doesn’t happen, manufacturers need to be able to find out why by testing and validating those assumptions. (This is also part of the schedule fine tuning process.) The following information will help you understand that decision making: - Lot Assignment: Why is a particular lot assigned to a particular tool in a schedule? This explanation can be encoded visually in the form of a score, weightage, criteria, percentage, and/or list of tool and lot attributes.
- Lot sequence position: Why a particular lot is assigned and scheduled ahead or behind another lot in a schedule, or the position in the sequence for a tool. This explanation can be encoded visually in the form of a score, weightage, criteria, percentage, and/or list of tool and lot attributes.
- Winners and losers: The details of the lots that competed with any assigned or selected lot and lost out. In a factory with a lot of active work in process (WIP), and when the schedule horizon is not able to accommodate all the active lots in the schedule, you should be able to find details of unselected lots which lost out to the winning lots.
### Advanced validation: quality of the schedule
Depending on the factory, the schedule is set up to automatically refresh anywhere between every five minutes to one hour. The stability and reliability of the schedule run to run and over a rolling period needs to be tracked as part of solution validation, as it mimics the actual production environment at the customer factory. What constitutes a good schedule can be based on quantitative criteria and KPIs, but there is also a subjective component to the evaluation based on factory physics tradeoffs which again can be linked back to KPIs.
Based on the use case, some of the KPIs that when tracked would indicate the efficacy of a scheduling solution are:
- Schedule compliance: Lagging indicator of assignment compliance to measure if, in actual production, lots ran on the tools to which they were assigned at the time of dispatch.
- Projected moves and outs: Leading indicator of projected moves and outs by the scheduler by end of shift or day is a measure of the throughput of the factory.
- Tool utilization: Standby time (SBY) with WIP (leading to avoidable white space in a schedule) and SBY without WIP (which can lead to bottleneck tools being starved of work). Standby time in a tool is a measure of the unutilized capacity available in the tool and, in typical use cases, the scheduler is designed to minimize this component of total tool time.
- Finished lot cycle time: Tracking the finished lot cycle over a period is a lagging indicator for the effectiveness of the schedule. If the product mix, starts and equipment qualification matrix did not dramatically change, then there should be a downward trend of finished lot cycle time before and after the deployment of the scheduler.
- Factory X factor, DPML, CT pace or WIP overturns: Tracking the trend of leading cycle time measures like Days Per Masking Layer or X factor or WIP turns is an indicator for the effectiveness of the schedule. If the product mix, starts, and equipment qualification matrix did not dramatically change, then there should be a downward trend of these KPIs before and after the deployment of the scheduler.
- On time delivery percentage or lagging lots percentage: In factories where lot due dates matter and this is a core objective, scheduler behavior is expected to improve the OTD metrics.
- Average train size: In factories where setup minimization is a core objective of the scheduling solution, average train size is a measure that can evaluate the quality of the schedule.
These KPIs also need to be generated on a forward-looking basis as part of the scheduling output. This will allow the end users to gain an understanding of the outcomes predicted by scheduling and validate the schedule.
### Role in successful implementation
A validation framework enables a structured way of conducting a thorough evaluation of the schedules generated by the solution. Both the software vendor and the customer need to be aligned on this to manage expectations, as well as for the successful deployment and management of the solution. There is no such thing as a ‘perfect schedule.’ Fine tuning is by default a part of making a scheduling solution work for an end user in the absence of AI/ML based methods which can automate the fine-tuning process to realize the theoretically achievable productivity gains.
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [SmartFactory AI 解决方案概述](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/smartfactory-ai-overview/)
**Published:** November 27, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 了解 SmartFactory AI 解决方案如何推动创新、优化绩效并提升实时数据可访问性，助力半导体制造实现无缝运营。
**Content:**
#### 文字稿
欢迎来到人工智能驱动的制造业未来。
我们的 SmartFactory 解决方案团队正在引领创新，持续提升客户业务运营价值。依托 AI 驱动的解决方案，我们实现了认知体系的统一，让实时数据触手可及。
现在，让我们见证 AI 如何重塑制造业。想象一下，AI 处理海量数据集，即时生成深度洞察，助力决策更快速、更精准。这不仅是生产力的提升，更是整个制造业格局的变革。
为何现在就要行动？因为您的竞争对手从未停歇。要理解这场变革，让我们聚焦 AI 系统的核心能力。环境感知、输入解析、经验学习和纠错决策。
这些能力为制造商带来显著效益。合理运用 AI 可提升良率、加速产出、降低成本。AI 驱动的系统能延长设备正常运行时间、预测性维护设备，并优化供应链管理，从而减少中断、提升效率。
通过整合传感器、设备和人员数据，AI 依托更庞大的数据量提升决策精度，同时加速决策流程。让我们看看 AI 在制造业的实际应用。AI 可以预测设备故障，减少停机损失。
AI 可以优化生产流程，提升产线利用率，通过实时缺陷检测，确保精准品控。此外，AI 还能优化规划决策，识别环境隐患以提升安全性。通过协作机器人等系统，增强人与机器之间的协作。尽管优势显著，AI 应用仍面临挑战。
数据安全与质量问题是首要障碍，其他常见挑战包括解决方案可解释性，数据匮乏和技术异构型。最后，准确评估 AI 应用的商业价值至关重要。
突破这些挑战，AI 在制造业的未来充满希望。携手 SmartFactory AI，共创未来，保持领先。
欢迎访问 [AppliedSmartFactory.com](/zh-hans/)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [MES 系统集成：SmartFactory 解决方案的独特优势](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Dan Meier 揭秘 SmartFactory MES 系统集成的差异化优势，了解这些能重新定义您生产运营的独特解决方案。
**Content:**
#### 文稿
我是 Dan Meier，担任应用材料公司 MES 系统战略总监。MES 系统的全称为 “制造执行系统”。
作为制造软件系统的核心枢纽，MES 系统始终贯彻整个制造流程。应用材料公司 SmartFactory 解决方案在业内具有独特性。虽然许多公司都拥有适用于制造的软件方案以及诸多各类功能模块，如统计过程控制 (SPC) 或良率管理系统等，但 SmartFactory 软件套件的真正优势在于其全系统的深度集成能力。
我们不仅在制造业各个软件类别中拥有业界领先的能力，而且在整个软件套件的整合方面也同样出类拔萃。事实上，没有比这更好的整合了。通常情况下，制造商需要单独购买各类软件，由他们的软件工程师编写中间层代码，将这些软件整合在一起，实现某种程度的系统集成。这些中间层的开发成本极高，且耗时良久。而且一旦软件提供商更新系统版本，制造商自建的这些中间层就可能失效。SmartFactory 软件套件的优势在于，我们提供了所有用于系统集成的中间层，确保系统无缝对接，而且这些中间层不会出问题，真正实现一体化运作。我认为这具有极其重要的价值。
MES 系统的核心优势在于，它能高效整合制造过程中的所有环节。虽然我这么说可能有些绝对，实际上它的功能远不止于这一点。MES 系统不仅定义工艺流程，还定义执行各工序所需的资源，包括使用的设备、在特定工艺步骤中设备所需的工艺配方。它还定义了每个工序所需的零部件、材料或化学品的配置。MES 系统将所有要素进行有序管理，实现产品制造的一致性和准确性。
这正是企业所追求的目标。因此，MES 系统实质上构成了我们称之为“计算机集成制造系统 (CIM)” 的核心，该系统不仅包含 MES 系统，还整合了诸多其他功能模块。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [SmartFactory 制造执行系统 (MES) 自动化解决方案赋能卓越制造](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 聆听技术专家 David Hanny、Selim Nahas、Madhav Kidambi 和 Dan Meier 解读SmartFactory 制造执行系统 (MES) 自动化解决方案如何通过全面集成能力引领工厂自动化升级。
**Content:**
#### 文稿
我们经常被问到这个问题，MES 系统能带来什么价值？如果用简洁的方式概括，我们应该从哪些方面着手？首先，它能帮助你优化工厂资产配置，突破产线关键瓶颈，优化这些环节的产出效率，从而显著提升整体产出。其次，借助 SmartFactory 的集成能力，我们可以快速响应工厂突发事件。总体而言，这将提升工厂生产力。
另一个关键价值是“可预测性”，这能从供应链层面带来显著效益。随着供应链日趋复杂，企业需要快速响应客户需求的动态变化，并优化设备利用率。 在某些场景下，可以利用预测性能力，通过设备优化实现节能降本等目标。我认为 MES 系统对制造业的价值主要体现在三个方面。
这就像三脚凳的三个支点，第一是一致性。确保每次生产都能遵循相同标准。
从 MES 系统的角度看，我们需要明确定义，工艺流程按步执行、加工设备按需送达、程序参数依标配置，以及工艺配方参数，确保每次执行的一致性。第二是在保证一致性的前提下，提升生产效率，这是生产效率的部分。
如何提升生产效率？具体包括缩短生产周期、优化工序时间、识别并缓解瓶颈。第三条是在实现一致性和高速量产的同时，确保产品质量。必须提升品质，因为高速量产中存在的不良品，会造成严重后果。
我觉得这就像凳子的三个支点，由此衍生出许多方面，我们有许多系统来处理这些领域。
关键在于这些系统的集成协同，如何将它们整合在一起？这就是三个基本支柱。从更全球化的视角看，超越 MES 系统和工厂生产力本身。归根结底，自动化决策要服务于商业目标，客户盈利的关键在于交付符合规格的产品。
企业需要建立多维评估体系，其中两个核心指标是：第一，是否越来越接近零缺陷？第二，我在资产、设备、人员和工艺方面投入了大量资金，是否从中获得了最佳回报？我认为，我们必须牢记智能制造的最终目的是创造商业价值，这包括我们已经讨论过的系统集成和多平台协同运作。
这是第一点，第二是引入可提升生产效率的先进技术，能让我们做得比以往更多。当工厂发生任何事件时，无论是好是坏，都能快速决策，这将让你有效提高生产效率。正如 Madhav 所说，让你的工厂更具可预测性。
我认为主要体现在：首先 SmartFactory 让你能够实现传统方式无法完成的生产。这些生产本身成本太高，且不可持续。
第二是人员要素、学习要素。如果人员缺乏认知，将难以推进，所以需要抓住这一点。技术要素包括我们讨论过的系统集成、平台的可扩展性和合理成本控制。因为在某些情况下，你审视问题时会发现：我们无法解决这个问题。
某些问题成本过高，无需解决。所以 SmartFactory 实现了我在评估任何系统时都会关注的三个基本要素：人员、技术和经济性三要素的平衡。
**Semiconductor Category:** Smartclips, Panel
**Semiconductor Tag:** Smartclips
---
### [AI integration is transforming manufacturing KPIs](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/ai-transforming-manufacturing-kpis/)
**Published:** April 16, 2025
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** Semi manufacturers are accelerating factory performance and uncovering new business opportunities
**Content:**
## What’s Inside
- [ AI’s paradigm shift ](#index1)
- [ Proven technology, fresh disruption ](#index2)
- [ The human element ](#index3)
- [ Economic considerations ](#index4)
- [ Next-level advantages ](#index5)
### AI’s paradigm shift
Whether working with existing integrated software solutions or automated intelligence (AI)-based solutions, the objectives for manufacturers are fundamentally the same: to gain efficiency and quality improvements across all manufacturing processes. However, while existing solutions have plateaued in what they can accomplish, AI enables an unprecedented level of learning and data processing. The introduction of this disruptive technology created a paradigm shift through which manufacturers can gain a new perspective on traditional KPIs such as quality, productivity, throughput, and uptime.
### Proven technology, fresh disruption
Artificial intelligence is not new or revolutionary when you consider that the term AI was coined in the ’50s. What is new is the mainstream application of and accessibility to AI, enabled by the development of software and advanced processing power to support it. This has paved the way for a particularly disruptive force in the rapidly evolving human understanding of how to use AI—and this is completely changing the landscape. It is increasing performance levels and creating new business opportunities.
For manufacturers, the AI revolution is the ability to bring technologies to market at a much faster rate than ever before. Whereas once a business might have the ability to design something and put it into their production line in nine months, AI could enable them to do so in a game-changing three. This ability to focus on more advanced products, more cost-effectively, and with gains in quality and throughput, can significantly change a business. This includes creating opportunities to pursue high margin contracts previously beyond reach.
In the semiconductor industry, for example, there are only a few companies capable of introducing innovative, improved products to the market; they enjoy remarkable margins on those products for a period of time. With AI, companies not previously able to compete in this way will be able to leapfrog one or two generations forward and perform at higher levels.
The data needed to teach AI systems is also changing. Once considered only possible for the large players that have access to vast oceans of data, new techniques in generating synthetic data are helping bridge the gap. We will see a focus on the ability to bridge the understanding between different products in the factory. Product changeover will become more seamless and will allow us to manage the variance more effectively. This, in turn, will profoundly improve the ability to manage line variance. With the technological advancements surrounding AI, the next step in the revolution is learning how to implement it in a repeatable, scalable and meaningful way.
### The human element
As much as AI is a technological innovation, it’s the human component that will help it realize its potential and drive the new paradigms. Currently, the skillset needed to fully optimize AI is shared by two different groups of people, the data science experts who are familiar with AI and related technologies, and the process experts who thoroughly understand semiconductor manufacturing. They will need to collaborate to maximize AI’s impact and the methods by which models are trained for specific applications.
Manufacturers also will use AI to overcome human limitations. For example, AI can be tasked with running 16 analyses simultaneously and will derive a response within seconds. Conversely, a human is prone to fatigue and bias that may lead to missteps, takes much longer to process these analyses, and will inherently add their own interpretation to the result.
Another way AI will improve upon human limitations is around retention. While memory, training and experience variations in humans result in each person addressing a problem or learning information differently, AI is an effective alternative. The difference between how AI and people work with information is the way that learning can be captured, resulting in unified understanding across the board and the ability to associate all the data sets required in real time.
AI can also address the challenge of knowledge retention in manufacturing, especially as experienced workers retire and new ones enter the workforce. Knowledge retained by AI can be instantly available across the factory to help mentor incoming talent. We can essentially build a learning system. That’s new!
### Economic considerations
The integration of AI in manufacturing is influenced by economic factors as much as it is by technological and human factors. A 300mm foundry that’s doing advanced nodes, a 200mm automotive manufacturer and a 150mm MEMS factory each have a different business outlook. Their structures are different and their willingness and need to spend is driven by something entirely different from one another. For instance, the 150mm factory has significant margins, but needs a compelling reason to change something or invest in something. They must be able to get meaningful results that will change their business or there is no incentive for them to invest in AI. These types of factories will invest in efficiency gains.
Instead, AI integration will be developed at the 300mm manufacturing level. While that’s not a hard rule, it would be difficult to envision a major spend in a legacy factory (I have been surprised before). AI is going to play a huge role in the high mix, low volume scenarios and will be incredibly powerful bringing new products to market.
One of the things semiconductor manufacturers are most concerned about is the aging population that’s retiring and the experience that will walk out the door with them. They’re worried about how to manage things like potentially catastrophic events that only happen once every three years or so when the only people who have ever experienced them are gone. AI is going to help bridge that gap, to retain knowledge and make it available for the newer workers. It will also help companies teach people their trade more efficiently. This is among the most meaningful reasons manufacturers will have for investing in AI.
Ultimately, the economic decision around AI will move over time based on the economics of the factory and the market forces on it.
### Next-level advantages
There are many considerations – human, technological and economic—semiconductor manufacturers must take into account to optimize AI development and deployment. It will spark a new way of thinking about business needs and potential, because of the opportunities to learn things never previously understood or managed. The difference in performance levels from ‘before AI’ to ‘after’ will be akin to competing at the junior varsity versus Olympic level.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [效能先锋：工厂创新实践](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/performance-pioneers-factory-innovations/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Chris Reeves 分享提升工厂质量与效能的革新策略，带您获取半导体制造前沿的创新经验。
**Content:**
#### 文稿
我叫 Chris Reeves，是应用材料公司 E3 工艺控制平台的产品经理。E3 是一项技术，专注于为我们的工艺质量管理套件，包括异常检测、批次间控制、统计过程控制 (SPC)，以及智能诊断模块“Knowledge Advisor”。
应用材料公司 SmartFactory 是一套软件解决方案，旨在提升客户的设备互联能力，并通过自动化增强客户的生产效能。该解决方案的关键优势之一，在于其实现了全产品线的统一操作界面、一致使用体验和无缝系统集成。E3 平台的核心优势之一，在于其工艺控制模块间的智能互联能力，以及超越模块本身的扩展性。
通过与客户沟通，我们发现一个关键需求是实现数据共享能力，无论这些数据是来自异常检测、SPC还是批次间控制。实现跨模块数据整合应用，不仅能显著提升异常检测效率，还能加速响应速度，最终帮助客户大幅优化生产效率， 将工艺控制水平提升至全新高度。就价值评估而言，客户最关注的是工厂的整体运营效能。
这具体体现在：设备产能、单机台材料处理能力、工艺异常及报废率，以及工厂的综合运营成本。通过采用 E3 平台及集成化解决方案，客户能够显著提升异常检测速度，优化异常响应决策质量，最终实现运营成本降低，全面提升工厂绩效。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [Efficiency Unleashed: Optimizing the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/optimizing-efficiency-in-the-fab/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Amnon Shenfeld shares his unique approach to maximizing efficiency in the fab. Discover the innovative methods that set SmartFactory apart.
**Content:**
#### Transcript
I’m Amnon Shenfeld, I’m the CTO for automation products group at Applied Materials. So I think that the value of Applied SmartFactory from the technological perspective is in our focus on design thinking, which essentially means that we focus on usability first. We truly care about our customers and we try to think about all the challenges and value that we bring our customers.
Mostly, software that is running in fabs is focusing on the machines and by doing that, in some cases, we miss the human element. In today’s market, it’s very obvious that analytics and big data are becoming a major aspect of efficiency and learning how to improve the processes in the fab. And for us being human-centric, even though we’re dealing with the most advanced technologies, manufacturing technologies on the planet, is something that we care about and focus on.
Applied SmartFactory, in terms of market leadership, has been around for quite a while. So, we started looking at how to reduce cost of ownership through optimization of the way that the software is functioning and running, and we identified pieces of our architecture that can be modernized. That is a capability that we’re unique in offering. If you have a cloud-native architecture, in most cases you can actually reach a higher compute, which means a more efficient run, in the fab while still having the same level of safety and security for redundancy that you had previously—only without having to waste hardware to simply stand by and wait for something to break.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi, Smartclips
---
### [Human-Centric Solutions: SmartFactory's Approach](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Selim Nahas discusses SmartFactory's commitment to making people an essential part of the solution. Embrace the human element in smart manufacturing solutions.
**Content:**
#### Transcript
Okay, so my name is Selim Nahas. I’m the director of process quality automation at Applied Materials. I’ve been in the industry since 1995.
SmartFactory is essentially the development and investment that we made into building an ecosystem that allows you to capture, learn, and embed the behavior into automation of all the things that you need to do, to manage a process in a factory. So ultimately, I’m big on highlighting the fact that without people and understanding, you can’t get anywhere. And so I think it’s about questioning, how do we do that? How do we basically build an ecosystem that helps people build an understanding of the processes, the intricacies of the process, and how do we ultimately decide what we’re going to put back into an automation behavior in the factory itself? The truth is, every time we’ve ever gone through an exercise of figuring out how we can step-by-step discern something or automate something, we realize, oh goodness, we really can automate this.
That, I think, is the biggest differentiator of what we do. And that is not possible with just any system. That’s something that’s very specific to the way this platform is architected, how we’re looking to connect things, how we’re looking to make them tangible.
That’s the innovation, in my opinion. So it’s broad. It’s not a singular thing.
It’s across-the-board for a lot of things. The industry is not the same across the board. So the world is not the same to everybody.
I think that where the customer really recognizes the SmartFactory value is in realizing that it’s not a point solution. It’s a roadmap to a whole bunch of solutions that when you sum them all up, they’re much more than a quarter of a percent or half a percent. And that’s when they start to see it. And they recognize that because they know that historically, they’ve done it in fragments. And now they have a roadmap that they can pursue. So it’s more consolidated. It’s the investment, is with one vendor. Therefore, they have a lot more sway and say on what goes into that roadmap. And therefore, they also understand what to expect, when to roll it out, what it’s going to cost to roll it out, and so on.
So predictability, stability, and the ability to continue to grow and maintain it as they need. So they don’t have to spend all the time unless they foresee the need to do so. That’s the value that they really gain.
It’s not a technical value only. It’s a relationship value. And that’s only possible with players that are large enough to basically invest in and develop things over many customers and many years.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi
---
### [MES Integration: Uniquely SmartFactory](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/unique-mes-integration-capabilities/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Dan Meier dives into what makes SmartFactory's MES integration capabilities stand out. Learn about the unique solutions that can redefine your manufacturing operations.
**Content:**
#### Transcript
I’m Dan Meier. I’m the Director of MES Strategy at Applied Materials. MES stands for Manufacturing Execution System.
This is the software system that really is at the hub, the core of manufacturing software systems throughout manufacturing. So the Applied SmartFactory, I think, is really interesting in that it’s unique among the industry. A lot of companies have software that is useful for manufacturing and a lot of individual capabilities, statistical process control or yield management or things like that, but what really sets the SmartFactory suite of software apart is the integration between all of these pieces.
We have not only best of class capabilities within each of the software categories within manufacturing, but we also have best of class, in fact there’s no better, integration across all of the products within the suite. Normally a manufacturer would have to purchase individual products and then write glue layers, have their software engineers glue these together to create some kind of integration between all of them. And these glue layers are very expensive and very time consuming to write and whenever the software vendor makes a change to their software, it can actually break these glue layers that the manufacturers are creating for themselves.
One of the advantages of the SmartFactory software suite is that we provide all the glue layers to create that integration and it doesn’t break. It acts as an integrated whole. I think that’s very very important.
So MES, it does one thing very very well and that’s to organize everything that’s happening in manufacturing. And I say that kind of hyperbolic, it’s more than just one thing, obviously. The MES defines processes, but it also defines the resources that are used for those processes,
the equipment that’s used, the process recipes that are used on the individual equipment at particular process steps. It also defines if you need to use any parts or other kinds of materials or chemicals at each individual process step. It keeps all of that organized, it keeps it all sorted out, it keeps it all straight so that you can manufacture your product repeatably and correctly every time.
That’s what companies are looking for. So the MES is really at the core, of the heart of what we would call a larger Computer Integrated Manufacturing system that includes the MES and a lot of other capabilities as well.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi
---
### [SPC Strategies: Realizing Excellence](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Vishali Ragam unveils how SmartFactory's Statistical Process Control is driving quality improvements for customers. Learn the secrets to achieving excellence in quality management.
**Content:**
#### Transcript
Hi, my name is Vishali Ragam. I am the SPC product manager within the Process Quality APG group. One of the most innovative solutions that Applied SmartFactory SPC has to offer is its ability to readily bring in artificial intelligence and machine learning algorithms.
Customers do not need to have a specialized skill set when they’re playing with machine learning models. This has helped our customers tremendously to improve their overall quality and bring in advanced analytics into their factories. Many of our customers measure value by looking at their key performance indices. If there is an SPC which can streamline processes, which can improve their product quality and improve their manufacturing overhead, customers see this as a success.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi, Smartclips
---
### [Smart Manufacturing: The Evolutionary Edge](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/smart-manufacturing-the-evolutionary-edge/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Phil Walker explores the integral role of SmartFactory in the evolution of smart manufacturing. Witness the
cutting-edge advancements shaping the industry's future.
**Content:**
#### Transcript
Hi, I’m Phil Walker. I own the Maintenance and Recurring Revenue Products here at Applied Materials. I’ve been part of manufacturing for many years, and when I started in manufacturing as a young engineer, it’s a little bit hard to believe looking back at this, but we literally had stopwatches and notepads when we were doing our manufacturing.
And we would look at the manufacturing steps, and we would be measuring our steps with stopwatches and recording our notes in notebooks, and then putting those in spreadsheets and analyzing them. And that at the time, that was a pretty SmartFactory. And obviously, things have evolved from there. We now have all sorts of systems that allow us to collect our data faster, analyze the data faster, visualize things faster. So things have transformed from what they were, frankly, not that long ago. And that’s been transformative.
You know, we’re getting much faster cycles of analysis. We’re getting much faster cycles of improvement. Now, what’s gonna happen in the next wave of SmartFactory is that we’re going to get to a point where all the basics that we were talking about before are actually going to be automated.
So we have situations where, you know, we’re going to have machine learning and AI that are helping us not only put the plans together for collecting the data and analyzing the data, but actually going and acquiring that data themselves, “themselves”, the AI themselves. But what’s going to happen in manufacturing is sort of the baseline that existed before, the baseline of us being able to collect information and act on it. It’s actually going to the vast majority of that is going to be done for us by systems that are already thinking about how to better collect and analyze this information. But it’s still going to require the engineers to be able to see what that information is, take that baseline of information and insight that’s being provided by the system, and add that spark of ingenuity and creativity that’s going to make a step function improvement.
That’s what SmartFactory means. And that’s what gets me so excited about being involved with Applied Materials because all of our energy in the things that we’re developing not only is trying to figure out how we can add to that baseline of valuable information for the engineers to utilize, but we’re involved in the most cutting-edge manufacturing on the planet. So we have the best environment to push manufacturing and a SmartFactory to that next phase.
And that’s really what gets me excited about what we’re doing here at Applied Materials and the future of what we can bring to manufacturing.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi, Smartclips
---
### [Quality Quest: Insights from the Fab](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Join David Hanny as he delves into what SmartFactory customers truly desire to enhance quality in their manufacturing processes. Discover the pivotal insights that can revolutionize the fab floor.
**Content:**
#### Transcript
My name is David Hanny. I work for Applied Materials. My responsibility is the director of marketing and strategic planning, and my team gets a chance to go out and talk to our customers very frequently.
And so we have a pretty good pulse on what we think the industry is asking for. And so what I want to share with you today is some of the feedback that we get. When we talk to our customers, they really talk about four major things that they are looking for to deliver to their customers.
We recently had a chance to talk to some of the leader suppliers of different chips, people like Continental for the automotive industry and Broadcom. And we’ve had such conversations before with Apple and Qualcomm and so forth. What they are always challenged with is getting quality. As a computer semiconductor manufacturer, they strive to create chips that are reliable, that are functional, and that are to be able to do it for a long period of time.
The second thing that they are challenged with is why are things different from one tool to the next when they use the same recipe and when they run in the same kind of factory. When you get into the entire enterprise of manufacturing, they look from Fab to Fab to see why does one Fab perform in one way and another in another way, and what are the differences, and how can I characterize those things so that I can make my entire business better. That type of comparison is super important to them and the ability to take data outside of the Fab even and compare it and be able to find that best known method, that golden tool.
The third one is how do I get a new product to market on time. A new product introduction is a challenge. Depending on the step change from the previous product, they’re going to face new situations that they didn’t before. And so that new product introduction and getting through that ramp curve is so critical for their business because they make more margin on the products when they’re initially introduced than they do later on as it becomes more common usage.
And then the last thing that I wanted to mention is something that our customers are challenged with to be able to deliver on time.
And one of the statistics or one of the KPIs that they look at is found in what’s called the operational characteristic curve. And so the objective of the operational characteristic curve is to focus on on-time delivery to their customers and what are my costs. And so they want to be able to optimize their assets by making better decisions on what it is they process, when they process it, and how they move it down the line and go through the different loops and build up the mask layers and so forth.
So these are things that our customers are constantly talking about when they make their investments.
**Semiconductor Category:** Interviews, Smartclips
**Semiconductor Tag:** Semi
---
### [Supplier quality is a key contributor to enhancing Quality by Design practices](https://appliedsmartfactory.com/semiconductor-blog/quality/semiconductor-supplier-quality-management-best-practices/)
**Published:** March 31, 2025
**Author:** Yoram Barak and Vishali Ragam
**Excerpt:** Improving quality systems for semiconductor manufacturing
**Content:**
## What’s Inside
- [ Understanding Supplier Quality Management needs ](#index1)
- [ Use case: workflow and state model part ordering management ](#index2)
- [ Incoming inspection value vs. added costs ](#index3)
- [ Conclusion ](#index4)
### Understanding Supplier Quality Management needs
Maintaining high-quality standards is paramount for any manufacturer. Supplier Quality Management (SQM) plays a critical role in ensuring that the materials, components, and services procured from suppliers meet stringent quality requirements. An ideal system will:
- Provide a single source of truth for all quality related information
- Facilitate better communication and collaboration between the manufacturer and the supplier
- Offer real-time monitoring of supplier performance through key performance indicators (KPIs) to quickly identify and address quality issues and ensure continuous compliance
- Automate the audit and assessment process, making it easier to conduct regular quality audits
- Enable leveraging of data analytics to support continuous improvement initiatives and help identify trends and areas for improvement
Improving supplier quality prevents incoming quality control inspection and improves supply resiliency. Incoming quality control (IQC) in semiconductor manufacturing refers to the process of inspecting and verifying the quality of raw materials and components before they enter the production line. This is a critical step to ensure that only materials meeting the required standards are used in the manufacturing process, thereby preventing defects and ensuring high product quality. Key aspects of IQC are illustrated in Figure 1.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/03/fig1-Incoming-Quality-Control.jpg) Figure 1: Key aspects of incoming quality control. Documentation and traceability are also important for maintaining detailed records of material origins and inspection results. Sampling plans can significantly aid in identifying trends and preventing potential quality issues.
### Use case: workflow and state model part ordering management
Ordering material entails various stages, including supplier setup, material setup, and uploading of the material Certificate of Analysis (CoA). After this is uploaded, the information is benchmarked against the agreed upon specifications for the part, the results are published, and an action per results (pass/fail etc.) is triggered. If the action is a fail or additional information is requested, it is beneficial to have the ability to accept a corrected CoA against the same part, as well as strong analytics for material and supplier performance. Figure 2 outlines the workflow and state model for part ordering management. It details the process of passing and failing parts, reordering, and the various states and locations involved in the process. The model also includes checkpoints for vendors and locations to ensure quality and efficiency in part ordering.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/03/fig2-simple-material.jpg) Figure 2: An example of a simple material state model flow from ordering supplier/vendor to manufacturer’s receiving dock, inventory room, manufacturing, and end of life and the systems associated with them.
### Incoming inspection value vs. added costs
The current incoming practices of remeasuring materials when they are received provide little value and reassurance to your manufacturing quality. In fact, this process requires increased inventory stock and inhibits Just in Time (JIT) strategies. Among the costs within incoming programs that can be reduced are:
- Facility inspection floor space
- Inspection equipment and associated maintenance
- Material stored pending inspection
- Elimination of non-conformance Returned Merchandised Authorization (RMA)
- Resources required to support incoming inspection
Supplier Quality Management for your incoming program automatically verifies material quality and adds stringent controls essential to product manufacturing genealogy. Because your suppliers proactively receive nonconformance notifications, products can be held at shipment, rather than requiring your incoming department to complete the same validation process. This initial review and validation process creates the ability to address nonconformance sooner and builds supplier confidence.
### Conclusion
Effective Supplier Quality Management is essential to maintain high quality standards and ensure the reliability of their products. It allows your incoming inspection to focus on verifying the supplier’s quality controls system, improving the time from when material is received to manufacturing. It also provides greater visibility into material health. By implementing advanced supplier quality software that meets the typical requirements, companies can achieve supply chain excellence.
## About the Authors
Yoram Barak, Durables Management GPM and Strategic Marketing
Prior to joining Applied Materials Automation Products Group in 2020, Yoram was a Global Marketing Manager at BASF Human Nutrition business division and before, an Innovation Manager for the Biosciences R&D Division at BASF. Yoram earned his PhD in Animal Sciences from the Hebrew University of Jerusalem and specialized in Biotechnology throughout his career.
Vishali Ragam, Global Product Manager, SPC
Vishali has been working in the semiconductor industry for more than 15 years. Prior to joining Applied Materials, she worked at Micron Technology, first as a process engineer and then as a senior quality engineer. She has been with Applied for seven years, having joined the company as a quality solutions architect. Vishali is currently a Global Product Manager overseeing SmartFactory SPC3D, an advanced process control (APC) engine that runs statistics to determine if processes are within spec to improve product yield. Vishali has an MS in mechanical engineering from Oklahoma State University, and a bachelor’s in mechanical engineering from Osmania University, in Hyderabad, Telangana, India.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Stop the noise! Avoid alarm overload to identify the most important issues in your factory](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/avoid-alarm-overload-in-your-factory/)
**Published:** March 21, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** SmartFactory Alarm Management improves productivity by integrating and automating alarms
**Content:**
[ Part 2: Streamline alarm management ](/semiconductor-blog/manufacturing-execution/streamline-alarm-management/)
#### Transcript
Applied Materials recently announced the newest addition to its SmartFactory product portfolio, the SmartFactory Alarm Management Solution. In this two-part video, we’re going to take a look at the challenges manufacturers face managing real-time alarms and how the Applied SmartFactory Alarm Management Solution can help overcome these challenges and improve factory productivity. When an event occurs within a factory, it’s common for multiple tools or systems to trigger alarms at the same time.
When that happens, consider the impact on the technicians and operators on the factory floor. Too often they’re overwhelmed with notifications and text messages and pages and emails. It’s time-consuming and tedious to filter through the alarm information overload to determine what’s important and identify the critical problems that need to be addressed.
Manually searching through all the notifications wastes precious time and results in a delayed response, which increases the risk to product and reduces overall factory productivity. Worse still is when false alarms are triggered, alarms for which no response is necessary, but it still takes time to determine this. Or when the same alarm is sent over and over again simply because the originating tool or system continues to repeat the alarm as long as the original condition is unresolved.
It’s not hard to imagine that the technicians and operators receiving all these meaningless alarm notifications might at some point just stop paying attention to them. And can you blame them? Well, at least until someone ignores what turns out to be a really important alarm and a critical tool goes down at the worst possible moment. In the best case, manually searching through all the notifications wastes precious time and reduces factory productivity.
In the worst case, missing a critical alarm notification amidst the noise of false alarms and repeated alarms and too many alarms could result in unnecessary tool downtime, scrapped product, and reduced factory output. What if all the alarms and notifications were already filtered and prioritized before being sent and the false alarms were excluded altogether and only one notification was sent instead of a lot of duplicate alarms? Automating how alarms are handled on tools and systems across the factory could provide many advantages. Automatic filtering could allow notifications to be sent for only meaningful alarms.
Alarms could be automatically prioritized so that when several alarms occur at once, the factory staff could easily determine which to respond to first. Repeated alarms could be automatically suppressed after the very first one, and alarms could be configured to automatically trigger actions like putting a lot on hold or logging a tool down. The primary goal should be to reduce the alarm noise threshold for factory technicians and operators, allowing them to quickly home in on the most important issues and accelerate response and resolution times, freeing them for more productive activities.
Ultimately, where alarms are managed is key. Integrating the management of alarms from tools and systems throughout the factory within a common application and in a consistent manner could provide significant benefits, including accelerating problem diagnosis and resolution, reducing equipment downtime, and increasing tool utilization. And improving alarm visibility for diagnosis and root cause analysis could provide a more holistic view of alarms across the factory in how frequently they occur and how often different alarms from different systems occur at the same time.
As it turns out, Applied Materials has a solution for this, the SmartFactory Alarm Management System. By integrating alarms throughout the factory and automating alarm management within a single system, the SmartFactory Alarm Management System offers a unique alarm management solution for your factory. You can find out more about the capabilities and features of the SmartFactory Alarm Management System in our next video.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [品质追求：来自晶圆厂的真知灼见](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/quality-quest-insights-from-the-fab/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 与 David Hanny 一起深入探讨 SmartFactory 客户的真实需求，如何实现生产工艺的突破性提升，揭示晶圆厂转型升级的关键洞见。
**Content:**
#### 文稿
我是David Hanny，任职于应用材料公司，担任市场营销与战略规划总监。我的团队经常有机会与客户进行深入交流。
因此，我们对行业的需求有着深刻洞察，今天我想分享一些来自客户的反馈。当与客户沟通时，他们普遍关注四大核心需求，这是他们需要为其终端客户提供的服务。
我们最近有机会与一些不同芯片的领先供应商进行了交流，比如汽车行业的大陆集团和博通公司，我们此前也与苹果、高通等企业进行过类似的交流。他们始终面临的首要挑战是生产质量。作为计算机半导体制造商，他们致力于生产可靠、功能齐全且能长期稳定运行的芯片。
他们面临的第二个挑战是在使用相同配方并在同类工厂生产时，为什么不同设备的生产结果存在差异。在规模化制造中，客户会对比不同的晶圆厂，为什么不同晶圆厂运作的方式不同，以及差异是什么。如何量化这些差异来优化整体生产效率？这种跨工厂的数据对标能力对我们的客户至关重要。能够将数据从工厂导出来进行相互对比，找到最佳方法和黄金工具。
第三个挑战是如何按时将新产品推向市场。新产品准时上市是一个挑战，鉴于新产品的步骤发生变化，客户往往会遇到前所未有的新情况。因此，新产品准时上市，实现快速量产爬坡，对他们的业务至关重要。因为产品上市初期利润率通常比较高，随着产品的普及，利润率会随之降低。
我想说的最后一点是，我们的客户在准时交付上面临的挑战。他们关注的统计数据或关键绩效指标之一，可以在运营特征曲线中找到答案。而运营特征曲线主要关注准时交付率与成本控制，因此他们希望能够通过优化决策来提升资产配置，包括生产产品的选择，何时生产、以及生产线上的流程设计，完成不同的循环工序、构建掩膜层等。
上述这些都是我们的客户，在进行投资决策时持续探讨的核心议题。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [创新集成：把握新机遇](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/seize-new-opportunities-through-integration/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Bing Wang 讨论了 SmartFactory 解决方案如何通过无缝集成赋予客户创新的力量，把握新的发展机遇。探索使用 SmartFactory 解决方案开启通往创新之路的路径。
**Content:**
#### 文稿
我叫 Bing Wang，是应用材料公司 CIM 解决方案的产品经理。当业界谈论智能工厂时，他们通常指的是高度数字化和互联的生产环境。在这个环境下，所有系统和技术可以实时通信和协作。智能工厂的主要目标是利用物联网 (IoT) 、人工智能 (AI) 、机器学习 (ML) 和数据分析等先进技术来简化和优化生产流程，尤其是在半导体制造领域。
从行业角度来看，当我们谈论智能工厂时，我们指的是七个主要特征。所以基本上它是关于自动化、互联性、数据分析和实时监控、灵活性、定制化、能效以及网络安全。SmartFactory 解决方案体现了我们在自动化软件领域的领先地位，它能够以高度自动化的方式促进生产过程的顺利运行。
晶圆厂的洁净室里没有人员进入，所有操作都由自动化系统运行。我们是市场上唯一拥有完全集成套件的供应商或解决方案提供商，这套件覆盖了我之前提到的四个主要领域。我们为客户提供通过集成来实现创新和抓住新机遇的机会。
我认为关键价值在于，我们提供的是完全集成的CIM解决方案套件。我们可以帮助客户快速部署并快速建成一座新晶圆厂。这对我们的客户来说非常重要，因为产品的上市时间与与其盈利能力和投资回报率直接挂钩，尤其是当客户新建晶圆厂时。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [SPC 战略：实现卓越](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/spc-strategies-realizing-excellence/)
**Published:** May 31, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Vishali Ragam 揭秘 SmartFactory 的统计过程控制 (SPC) 如何推动对客户的质量改进。了解实现卓越质量管理的秘诀。
**Content:**
#### 文稿
大家好，我叫 Vishali Ragam，在应用材料公司自动化产品部工艺质量解决方案小组担任 SPC 产品经理。Applied SmartFactory SPC 提供的最具创新性的解决方案之一，是它能够轻松引入人工智能和机器学习算法。
客户在使用机器学习模型时不需要具备专业技能。该模型极大地帮助我们的客户提高整体质量，并将先进的分析技术引入他们的工厂中。我们的许多客户通过关键绩效指标来衡量价值。如果有一个 SPC 可以简化流程、提高产品质量、降低生产成本，客户会将此视为成功。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Smartclips, Semi
---
### [Streamline alarm management for a faster response and resolution](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/streamline-alarm-management/)
**Published:** March 20, 2025
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Simplify alarm management throughout the factory by integrating SmartFactory Alarm Management with key systems
**Content:**
[ Part 1: Avoid alarm overload ](/semiconductor-blog/manufacturing-execution/avoid-alarm-overload-in-your-factory/)
#### Transcript
Welcome to part two, introducing the Applied SmartFactory Alarm Management Solution. In this video, we’ll take a look at the key capabilities of the alarm management solution. The SmartFactory Alarm Management Solution manages the complete lifecycle of factory alarm events.
The solution is pre-integrated with other products in the SmartFactory software portfolio and can handle the alarms from these systems. Once an alarm is received, the alarm management solution can process it to ensure only relevant information is retained and recorded. Then, the processed information can be forwarded to the factory staff via configurable notifications.
Because the alarm management solution is pre-integrated with other SmartFactory software products, it’s possible to automate actions within those systems in response to specific alarms. And because all alarm information is consolidated within a common database, a comprehensive alarm dashboard is available, along with the ability to analyze the history of any alarm in the system. Let’s dig a bit deeper into each of these areas to see how it works.
The SmartFactory Alarm Management Solution is designed to be the common repository for all alarms from any SmartFactory system. This enables a standard process flow for managing any alarm from any SmartFactory system. Initial system configuration is simplified by the ability to bulk import alarm definitions from other alarm management solutions.
The SmartFactory Alarm Management System has a high-volume ingestion engine, allowing it to process over 500 unique alarms per second. Alarms can be automatically filtered for relevance and prioritized. Duplicate alarms can be removed, and false alarms can be blocked.
And when multiple overlapping alarms arrive from a single system, a best alarm rule can be defined to surface only the most relevant information. Notifications are a key feature of the SmartFactory Alarm Management Solution. While automating how alarms are received and filtered is useful, communicating the most important alarm information to the factory staff ensures prompt attention to serious problems and facilitates quick response and resolution.
The SmartFactory Alarm Management System can be configured to send notification emails or text messages to only the factory staff best suited to handle a given alarm. This eliminates the alarm information overload caused by bulk notifications to all factory staff for every alarm. In addition, an escalation process can be configured to forward alarm notifications to Tier 2 support staff in cases where there was no acknowledgment of the initial notification.
It’s often desirable to perform some action when a specific alarm occurs, such as putting a lot on hold or logging a tool down or preventing a new process run from starting on a tool. But this is extremely difficult to automate and typically done manually if it’s done at all. The SmartFactory Alarm Management Solution is pre-integrated with other systems within the SmartFactory software portfolio to simplify automating a variety of actions in response to any alarm.
Actions can be automatically triggered within the SmartFactory MES, equipment automation, the material control system, the run-to-run control system, and other SmartFactory systems as well. One of the most powerful capabilities enabled by the SmartFactory Alarm Management System’s centralized database is the ability to provide comprehensive alarm reporting. At the simplest level, the system provides a real-time, factory-wide alarm dashboard, allowing you to see the alarms currently active within the factory.
And because alarm information is preserved over time, alarm history can be queried to provide information that’s tailored for specific investigations. All alarm information is time-synchronized, allowing not only analysis of specific alarms over time, but also comparison of different alarms that occur in close-time proximity. The troubleshooting possibilities are endless for how alarm information can be viewed and analyzed.
To sum it all up, the SmartFactory Alarm Management Solution streamlines alarm management, providing a centralized solution that offers a consistent approach to how alarms are managed. The SmartFactory Alarm Management Solution is pre-integrated with other systems in the SmartFactory software portfolio to simplify alarm management across the factory. And the SmartFactory Alarm Management Solution automates how alarms are processed, how notifications are sent to factory staff, and how actions are triggered in response to specific alarms.
The SmartFactory Alarm Management Solution is the only solution you’ll need to streamline real-time alarm management factory-wide for faster response, quicker event resolution, and improved efficiency. It truly is smart alarm management. How can we help your factory? Contact us today for a free assessment of how you manage alarms, and how you might do it better.
Just click the button on this page to reach out. You might be surprised at the benefits smart alarm management can bring to your factory.
**Semiconductor Category:** Semiconductor Manufacturing Execution
---
### [Enhancing decision-making in real-time scheduling: leveraging data and AI technology (Part 4/4)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-4/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** Diving into digital twins: debunking misconceptions and unveiling the digital twin framework
**Content:**
[ Part 3: Challenges and opportunities with AI ](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-3/)
## What’s Inside
- [ Definition ](#index1)
- [ Example of Digital Twin technology ](#index2)
- [ Framework ](#index3)
- [ The potential to further AI ](#index4)
- [ Conclusion ](#index5)
Renowned influencer James Moyne joins Samantha Duchscherer in an engaging discussion exploring the importance of integrating additional information and advanced technologies like Artificial intelligence (AI) into the semiconductor industry’s scheduling and dispatching process. The comprehensive series consists of four parts focusing on various subjects such as the importance and advantages of data, AI, and human involvement. It also delves into the obstacles faced and offers insights into the role of digital twin technology.
In this fourth and final article of the series, they discuss two key aspects of digital twins—what they are versus common misconceptions and the concept of a digital twin framework.
#### Definition
As we started our discussion, we laughed that there’s the Hollywood impression of what a digital twin is—the human replica represented in movies like “I, Robot” — and then there’s the digital twin that is a powerful tool in the real world of semiconductor manufacturing. James provided a clear definition of the type of digital twin we’re focusing on:
James Moyne explains what a digital twin is in semiconductor manufacturing
#### Example of Digital Twin Technology
Sam: If a digital twin is not like what is commonly portrayed in Hollywood, could you provide a more realistic example?
James: Sure. Let’s consider an example on replicating the degradation of the filament of a lightbulb. If you remember, this type of bulb gets bright before it burns out. If I’m monitoring the temperature of that light bulb, or maybe the brightness of that filament, and predicting when that bulb is going to break, the model is used in a digital twin to predict its failure. In this example, we wouldn’t just model the theoretical failure of the light bulb, but we’d be synchronizing that model with an actual light bulb.
Sam: So, it seems like a key aspect of digital twins is the synchronization between them and their real counterparts?
James: Yes, digital twins are synchronized with their real counterparts in a time critical fashion. And this is important to note; it’s not necessarily in real-time, but rather is time critical. For this light bulb example, maybe I need to synchronize my model with this bulb every second because I need to predict within 60 seconds of the light bulb going out.
However, moving to the semiconductor manufacturing environment, in the case of dispatching and scheduling, I just need to synchronize every time a new wafer shows up.
Sam: What about the level of confidence in predictions? In our last blog we talked about the importance of this; how does that come into play when talking about digital twins?
James: The key outputs of the digital twin are along the lines of a prediction or detection (such as something is broken or is going to break). But, yes, just like we talked about in the last segment it also must provide information about its accuracy. If a digital twin tells you that a light bulb filament will fail, it must indicate when it will fail. If it says 60 seconds or ±5 seconds with a probability of 95%, you can use that information to order a replacement bulb.
#### Framework
Sam: Based off your definition of digital twins – it seems like they have been around for a long time in semiconductor manufacturing?
James: Right! For example, people don’t realize we’ve been using digital twins in run-to-run control in semiconductor manufacturing since the early 90s and now it’s pervasive. It takes a model of a particular piece of equipment and then tries to predict a recipe to improve the quality or throughput of that equipment. Run-to-run control is a form of model-based process control which also uses a digital twin of the process.
Predictive maintenance, which has now been around for 10 years, predicts some aspects or some failure mechanism such as in our earlier light bulb example. So, predictive maintenance also uses digital twin technology. Virtual metrology is another type of digital twin; a virtual metrology twin takes measurements from the tool, tries to predict metrology values and synchronizes with the real metrology tool to update the model.
So, as you point out, it’s important to emphasize that digital twins have been around for a very long time, and if we’re going to develop a digital twin framework for the industry, we have to have a framework to accommodate all these existing applications.
Sam: How do you build this integrated framework?
James: Essentially, we need to be able to both reuse digital twins and combine them.
First, I’ll discuss their reuse. Let’s say I’ve got a digital twin of an Applied etch tool that’s going to predict the machine’s throughput. I could develop a model that’s applicable to all etch tools that tells me what inputs are needed, but it won’t have high accuracy. If I refine that model for one Applied etch tool brand or a particular etch tool instance, the digital twin model will have more specificity. For example, it could determine what additional sensors are needed or the equation needs to be modified for the specific etch tool. This is what we call generalization hierarchy.
Combining digital twins is the other piece of the puzzle, which is particularly beneficial for scheduling and dispatch. Let’s say we have several existing digital twins: a scheduling and dispatch digital twin that is rule-based and tells us when to schedule different wafers at different tools, run-to-run control based digital twins indicating the quality of each tool that I’m sending wafers to, and a predictive maintenance digital twin that tells me when particular tools might fail in the future and with what probability. If I then had a scheduling dispatch digital twin that aggregates information from these twins on the quality of production of all my tools, when they’re going to fail and the probability of their failing, I can build a better scheduling and dispatch solution. That’s called the aggregation of digital twins.
Sam: Machine Learning and/or AI must benefit from Digital Twins – right?
James: Yes! Developing common interfaces, common ways in which these models can talk to each other, creates a playground for performing so many applications.
Digital Twins can take machine learning from different components and bring them together to create a much better system.
### Conclusion
Digital twins are purpose-driven replicas of aspects of a system, such as processes, equipment, or products, that are synchronized with their real counterparts. They have been utilized for a long time in various applications. To develop a digital twin framework, it is essential to acknowledge and accommodate these existing applications while defining clear technical definitions for digital twins and the framework itself. We can leverage the power of digital twins to drive innovation and improve various applications – even AI.
Back to [Part 1](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/), [Part 2](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-2/) and [Part 3](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-3/)
## About Dr. Moyne
Dr. James Moyne is an Associate Research Scientist at the University of Michigan. He specializes in improving decision-making by bringing more information into the scheduling and dispatching area. Dr. Moyne is experienced in prediction technologies such as predictive maintenance, model-based process control, virtual metrology, and yield prediction. He also focuses on smart manufacturing concepts like digital twin and analytics, working towards the implementation of smart manufacturing in the microelectronics industry.
Dr. Moyne actively supports advanced process control through his co-chairing efforts in industry associations and leadership roles, including the IMA-APC Council, the International Roadmap for Devices and Systems (IRDS) Factory Integration focus group, the SEMI Information and Control Standards committee, and the annual APC-SM Conference in the United States.
With his extensive experience and expertise, Dr. Moyne is highly regarded as a consultant for standards and technology. He has made significant contributions to the field of smart manufacturing, prediction, and big data technologies.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Enhancing decision-making in real-time scheduling: leveraging data and AI technology (Part 3/4)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-3/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** Realizing the challenges and opportunities AI brings to semiconductor manufacturing
**Content:**
[ Part 2: Understanding and defining AI and ML ](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-2/)
[ Part 4: Unveiling the digital twin framework ](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-4/)
## What’s Inside
- [ Walk before you run with AI ](#index1)
- [ Integrated systems ](#index2)
- [ Quantification of trust ](#index3)
- [ Discussion — Are we there yet? ](#index4)
- [ Conclusion ](#index5)
Renowned influencer James Moyne joins Samantha Duchscherer in an engaging discussion exploring the importance of integrating additional information and advanced technologies like Artificial intelligence (AI) into the semiconductor industry’s scheduling and dispatching process. The comprehensive series consists of four parts focusing on various subjects such as the importance and advantages of data, AI, and human involvement. It also delves into the obstacles faced and offers insights into the role of digital twin technology.
In this third article of the series, they discuss the challenges when implementing AI solutions, along with opportunities presented when these intelligent systems learn to ask for help.
#### Walk before you run with AI
AI and machine learning (ML) present many opportunities for semiconductor manufacturers for improving KPIs such as [quality](/semiconductor/process-quality-solutions/) and [yield](/semiconductor-blog/ai-ml/smartfactory-ai-transforming-manufacturing-productivity/). It’s important to understand, however, that integrating AI into your semiconductor manufacturing operation will at first require humans to create a system that is intelligent enough to ask the right questions from the right sources.
As James highlights, AI is prone to making mistakes due to the lack of context and its dependence on the quality of the data it operates on.
For data quality he has a saying, “One piece of bad data destroys 10 pieces of good data.” In terms of context, he notes that we can’t put data blindly into these systems; AI needs context for why it thinks a certain way. For example, it may know a light bulb is going to burn out, but the additional context of whether it’s in a residential building or an office complex, outside or inside, adds important information to help it predict when the bulb may burn out.
“Often times, when you look at data, it clusters really nicely around different context values like day versus night or outside versus inside,” he says. “A lot is dependent on how you treat these systems in terms of if you give them enough information.”
#### Integrated systems
Sam: Can you touch on why it’s important to have well-integrated systems along with high quality data?
James: To enable these systems to make accurate predictions, you want to make sure you have high quality data in terms of accuracy, precision, availability and timeliness. Not only that, but the data needs to be well integrated because, if the systems can’t talk to each other and collaborate with their data, it becomes very difficult; this is where you get issues such as time synchronization of data.
With scheduling, for example, maybe we’re thinking about an event – when the wafer arrives at a machine — and that’s how we’re making our decisions. Every time that action occurs, we make a decision. But at the fault detection level, maybe they’re not looking at actions, they’re looking at time intervals like seconds or milliseconds. How do we synchronize that kind of data?”
Sam: When you start to consider the integration of data, does sharing data become a new hurdle?
James: Yes, that’s another big challenge, especially when starting to go outside the factory’s four walls. We start to worry about things like ordering parts from suppliers in anticipation of equipment going down. While they won’t share their data with us and we wouldn’t share ours with them, we do need to share some form of information to understand each other. We also need to use that information to improve our predictions. How do you take data and secure your IP but still allow the information to pass so you can have important things like analytics, prediction and detection can take place?
Sam: Is there any other integration that needs to happen to give you a robust solution? If AI can make mistakes, how do we get to the point where it makes fewer mistakes?
James: What we’ve come to understand is that large language models are great for things like mining maintenance data coming from a human and trying to interpret what that human is saying. But that needs to go to an actual (human) subject matter expert who can take this information and fact-check it to filter out what isn’t correct. Then it can go on to something like scheduling and dispatch that will use this data to make important decisions.
A robust solution, then, would be an interface that always asks for help or for a subject matter’s input. To me, the most intelligent system is the system that knows when to ask for help, not the system that just knows things. That’s the problem with AI systems; they aren’t yet like humans where they say, “This is an area where I don’t know. Help me learn this piece.” They have to become more like students where they’re taught and they ask questions while they’re being taught.
#### Quantification of trust
Sam: While having accurate AI or ML predictions is important, how do we go about not only understanding these systems but trusting the output?
James: Yes, that’s an important question, because people can’t effectively use analytics and prediction, and even detection, without having trust in their recommendations. And this trust is not necessarily about the accuracy of these recommendations so much as about the ability to understand the accuracy level. It is called the quantification of trust. While it’s morbid, a good example is: if a doctor tells me I’m going to die, I’m going to take that seriously. But if the doctor doesn’t give me any indication of when, he’s 100 percent correct but basically telling me something I already know and not helping me. Even if the doctor says, “I am 100 percent confident you’re going to die,” that’s still not helping me. However, if he says, “I have 62 percent confidence that you’re going to die in the next two years,” I can use that information.
With predictive systems, it’s not as important that they’re great predictors. It’s that we understand completely the quality of the predictions they’re giving in terms of start time and stop time of this prediction and what that confidence level is. If I know that, I can use it with my analytics and do a lot to my scheduling and dispatch to make it work better.
#### Discussion — Are we there yet?
In our discussion, James and I explored the various ways in which AI can enhance our processes and products. However, before we could delve into the benefits, we first examined the distance we still must cover in manufacturing.
Sam and James discuss the spectrum along which AI will develop
### Conclusion
There are so many opportunities AI/ML offers semiconductor manufacturers in terms of quality, productivity and the [supply chain](/semiconductor/supply-chain-solutions/). This includes improvements in fault detection, predictive maintenance, virtual metrology, scheduling, dispatching and capacity planning, to name a few. Realizing these opportunities to their fullest potential will entail figuring out a better way to integrate the subject matter expertise of humans with AI.
In the final part of the series, James will discuss the digital twin angle and how it further empowers the AI movement
Back to [Part 1](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/) and [Part 2](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-2/)
## About Dr. Moyne
Dr. James Moyne is an Associate Research Scientist at the University of Michigan. He specializes in improving decision-making by bringing more information into the scheduling and dispatching area. Dr. Moyne is experienced in prediction technologies such as predictive maintenance, model-based process control, virtual metrology, and yield prediction. He also focuses on smart manufacturing concepts like digital twin and analytics, working towards the implementation of smart manufacturing in the microelectronics industry.
Dr. Moyne actively supports advanced process control through his co-chairing efforts in industry associations and leadership roles, including the IMA-APC Council, the International Roadmap for Devices and Systems (IRDS) Factory Integration focus group, the SEMI Information and Control Standards committee, and the annual APC-SM Conference in the United States.
With his extensive experience and expertise, Dr. Moyne is highly regarded as a consultant for standards and technology. He has made significant contributions to the field of smart manufacturing, prediction, and big data technologies.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Enhancing decision-making in real-time scheduling: leveraging data and AI technology (Part 2/4)](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-2/)
**Published:** April 16, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** Understanding and defining AI and ML
**Content:**
[ Part 1: Role of data in productivity and quality ](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/)
[ Part 3: Challenges and opportunities with AI ](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-3/)
## Table of Contents
- [ AI vs. ML ](#index1)
- [ Different levels of AI ](#index2)
- [ Discussion ](#index3)
- [ Chatbots and semiconductor examples ](#index4)
- [ Conclusion ](#index5)
Renowned influencer James Moyne joins Samantha Duchscherer in an engaging discussion exploring the importance of integrating additional information and advanced technologies like Artificial intelligence (AI) into the semiconductor industry’s scheduling and dispatching process. The comprehensive series consists of four parts focusing on various subjects such as the importance and advantages of data, AI, and human involvement. It also delves into the obstacles faced and offers insights into the role of digital twin technology.
In this second article of the series, the focus is on defining machine learning (ML) and AI. The article provides examples to illustrate their differences and similarities.
#### AI vs. ML
The distinction between AI and ML can be somewhat blurred, as there is no exact definition that universally separates the two concepts. However, in general terms, AI refers to the broader field of creating intelligent systems that can perform tasks requiring human-like intelligence. It encompasses various techniques and approaches, including machine learning. On the other hand, ML is a specific subset of AI that focuses on enabling machines to learn from data and make predictions or decisions based on that learning. ML algorithms learn patterns and relationships in data to improve their performance over time, without being explicitly programmed. While AI and ML are closely related, AI extends beyond just ML and includes other techniques such as natural language processing, computer vision, and expert systems. The boundaries between AI and ML can be fluid, with ML often being considered a crucial component of AI.
#### Different levels of AI
There are various levels of AI, each with its own scope and capabilities: - Granular AI operates within defined boundaries or parameters, using machine learning algorithms to make precise predictions or decisions within a known space. It fills in gaps between data points to provide a more granular understanding of the system’s behavior.
- Exploratory AI goes beyond known boundaries, exploring unknown territories where existing models may not apply. It incorporates external knowledge and data from various sources to gain a broader understanding of complex problems.
- General AI, or artificial general intelligence (AGI), represents the highest level of AI sophistication. It mimics human-like intelligence (i.e., reasoning, problem solving, and adaptation), possessing a comprehensive understanding of the environment and the ability to adapt to a wide range of tasks.
#### Discussion
James and I began our discussion talking about the differences between ML and AI, captured in the video below.
In this short video, Sam and James discuss the intricacies of AI and ML
#### Chatbots and semiconductor examples
After developing a deeper understanding of AI and ML, our attention shifted toward exploring practical examples:
Sam: Let’s discuss a familiar example for everyone: chatbots. Where do chatbots fit within the AI and ML spectrum?
James: You could argue that chatbots are not AI. For instance, if it’s creating my resume, it’s not creating anything new. It’s just mining data and saying, ‘Based on all this information, I’m doing probabilities and telling you what I think is true.’ Yet, it is AI in the sense that it’s mining an enormous amount of information and connecting the dots. Again, there is no clear-cut definition, but at the end of the day my perspective is that chatbots are mostly just Bayesian inference engines.
Sam: Transitioning to semiconductor examples, I’m assuming building an algorithm on two years of historical data to [predict lot cycle time](/semiconductor-blog/ai-ml/prediction-accuracy/) would be ML correct?
James: Correct! What you’re doing in that example is stay within a space that you that you’ve already had some experience with and you’re just adding more information so that the machine learning can develop a model.
Sam: What about development of a [reinforcement learning](/semiconductor-blog/productivity/advantages-of-reinforcement-learning/) model to find the optimal dispatching parameters needed for an unseen event that would happen in a fab? Where would this example fall on the spectrum?
James: I would say that still, for me, falls into machine learning, although I’m sure there are people out there who would say, ‘No, no, this is artificial intelligence.’
However, in the case of an event that has never occurred before, I might talk to experts and go read books to identify what this type of failure might look like and what the risks and rewards are. When we try to build an algorithm on this new data we bring in, whether real or simulated, this is when we start to get into the intelligence aspect.
Sam: And how do you define intelligence in this context?
James: It is a spectrum from pure artificial to pure human. What will be needed in the long term is a full integration of human and AI; even AI systems need some kind of human checks and balances. The interaction between human and artificial intelligence has to become more asynchronous. For example, a human should be able to provide intelligence to an AI system as soon as that information is obtained and verified, e.g., without being prompted. Conversely, an AI system should know when and how to ask the human for help.
I have a saying for this, ‘No knowledge left behind.’
### Conclusion
Machine learning and AI are part of a spectrum of technologies that perform similar functions. For this reason, people are often confused as to which one is at play. Ultimately, the distinction between AI and ML may vary depending on the context and perspective. Both fields continue to evolve, and the boundaries between them may become even more nuanced as new technologies and approaches emerge.
Up next, we’ll dive into the challenges and benefits associated with enabling AI and ML within the scheduling and dispatching framework.
[Back to Part 1](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology/)
## About Dr. Moyne
Dr. James Moyne is an Associate Research Scientist at the University of Michigan. He specializes in improving decision-making by bringing more information into the scheduling and dispatching area. Dr. Moyne is experienced in prediction technologies such as predictive maintenance, model-based process control, virtual metrology, and yield prediction. He also focuses on smart manufacturing concepts like digital twin and analytics, working towards the implementation of smart manufacturing in the microelectronics industry.
Dr. Moyne actively supports advanced process control through his co-chairing efforts in industry associations and leadership roles, including the IMA-APC Council, the International Roadmap for Devices and Systems (IRDS) Factory Integration focus group, the SEMI Information and Control Standards committee, and the annual APC-SM Conference in the United States.
With his extensive experience and expertise, Dr. Moyne is highly regarded as a consultant for standards and technology. He has made significant contributions to the field of smart manufacturing, prediction, and big data technologies.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Solve productivity and supply chain issues with AI/ML](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/productivity-supply-chain-using-ai-ml/)
**Published:** April 26, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Pre-built AI/ML models enable fabs to increase productivity, improve KPIs
**Content:**
SmartFactory AI™ Productivity is the only industrial AI/ML platform that can integrate with scheduling, dispatching, and full auto solutions in your current manufacturing environment. When integrated with the production environment, semiconductor manufacturers can expect to achieve improved cycle times, utilization, throughput, and yield. No other platform achieves this in as little time or effort.
### Transcript
Today, the world is rapidly moving to artificial intelligence and machine learning to service the demands of the market in every business sector. The world of manufacturing is no different. The necessity to be more intelligent, more responsive and more quality-driven is needed more than ever before.
Introducing Applied Materials SmartFactory AI. Create your own competitive advantage with the first CIM-integrated AI platform for semiconductors, helping expedite solutions for your productivity and supply chain challenges using intelligent algorithms. Optimize your multiple objectives through streaming and learning from big data, end-to-end model development and deployment.
SmartFactory AI addresses two main problems that affect fab productivity and yield. One, the shortcomings of the prediction model, including lot cycle time, dynamic bottlenecks and yield forecasting. And two, the problem of finding the best logic or parameter values to control production flow or equipment operations in an optimal way, considering real-time and future status.
SmartFactory AI is the only industrial AI platform that can integrate with scheduling, dispatching, and full-auto solutions to help you achieve improved throughput, cycle times, utilization and yield like never before. In production, SmartFactory AI collects data, trains a model, deploys it to the production environment, and monitors its performance in real-time to see how the model is performing. If there are fluctuations in the model’s accuracy, it is automatically retrained.
The solution UI shows results of the model evaluation and performance. SmartFactory AI is transforming manufacturing productivity by providing automated model building, training and deployment capabilities as well as user-friendly solution UI. This fully integrated solution is enabling manufacturers to manage deployments in as little as six months. A quarter of the time it typically takes them to develop individual models.
SmartFactory AI is integrated into the existing SmartFactory, Advanced Productivity Family and there is no need for users to learn additional environments or languages. Engineers can use pre-built ML models or configure key parameters to help focus on a fab’s particular challenges and expands the depth of problem-solving. Start amplifying your productivity and create your own competitive advantage with SmartFactory AI.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Evolutionary optimization of dispatch rule parameters](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimization-of-dispatch-rule-parameters/)
**Published:** May 24, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Dynamically optimize a dispatch rule’s parameters for better lot scheduling.
**Content:**
In the semiconductor manufacturing process, scheduling lots can have a dramatic effect on a fab’s efficiency. This type of scheduling process is called *flow shop with job re-entry* and is notoriously difficult to model and solve efficiently. The problem stems from tuning parameter values, as well as finding an optimal combination for every fab condition. The dispatch rule logic has numerous parameters, and its performance relies heavily on the ability to fine-tune parameter values according to work-in-progress and station availability.
To solve this challenge, we developed an efficient parameter tuning method based on Evolutionary Optimization combined with Simulated Annealing. Our results show that the approach outperformed other benchmarks and can be successfully used to dynamically optimize a dispatch rule’s parameter values.
For details on our methods and approach, watch the full presentation:
## Transcript
Hi, my name is Harel Yedidsion and I’m part of the AI/ML group at Applied Materials. The work I’ll present here was done jointly with my colleagues Derek Adams, David Norman, and Emrah Zarifoglu. The work is titled Evolutionary Optimization of Dispatch Rule Parameters. The agenda of this talk is as follows.
I’ll give a brief introduction to the semiconductor manufacturing process and the dispatch rule used to schedule lots in the fab. I’ll introduce our method for tuning the dispatch rules parameters, and I’ll show some empirical results comparing our method to a baseline method.
A bit of background, Applied Materials supplies equipment, services, and software for the manufacture of semiconductor chips. As you may know, there is a global shortage of chips, and FABs are struggling to supply the demand. Building new fabs is expensive and costs billions of dollars.
That is why we focus our attention on improving the efficiency of existing fabs. In the semiconductor fabrication process, wafers go through multiple steps and pass between stations. A typical route consists of 600 to 1500 steps.
A full production cycle can take up to two months. Scheduling the lots in a fab can have a dramatic effect on the fab’s efficiency. This type of scheduling process is called flow shop with job re-entry.
It is notoriously difficult to model and to solve efficiently, and in practice, heuristic dispatch rules are commonly used to schedule the lots in the FABs. The dispatch rule uses heuristic logic to rank the lots in the queue in front of each station. The rule is triggered approximately 2.5 million times in 90 days of operation.
It has about 80 parameters, both continuous, discrete, and nominal, and the parameter’s values can drastically affect the Key Performance Indicators, or KPIs. Some common KPIs which are used to measure the fab’s efficiency are on-time percentage, cycle time, lot late hours, average daily moves, Work In Progress or WIP, and number of lots completed. We’ll focus our attention on on-time percentage and average cycle time.
The problem we are addressing is how to tune the parameter’s values. Finding the optimal combination for every fab condition is computationally intractable. One possible solution is to use simulation optimization with the AutoSketch fab simulator, where in each simulation we choose a different combination of parameter values and measure the resulting KPIs.
However, simulating 90 days of operation takes about 10 hours, and we need at least 90 days to calculate meaningful KPIs. To mitigate that, we developed an efficient parameter tuning method based on Evolutionary Optimization combined with Simulated Annealing. Here I’ll show an example of how parameter values are optimized using grid search, which is a method we use to benchmark our proposed Evolutionary Optimization method.
We chose four parameters that we found to have significant impact on KPIs. The line balance parameters determine when to prioritize lots based on the work-in-progress in their next bottleneck stations. If a lot’s next bottleneck station is start, then that lot will get priority and will be processed first in its current step, so that it can quickly reach the start bottleneck station.
The idea is that bottleneck stations have to be running at full capacity to maximize throughput. In grid search, we discretize the range that each parameter value can take. Then we sample a different combination of values at each run, and each chosen combination is run for 90 days of simulation and its KPIs are measured.
This figure shows how different combinations of parameter values can generate significant differences in KPIs. We are interested in parameter values that produce a low cycle time, high on-time percentage, and a high number of lots completed, like the bunch marked and read here. To reiterate the problem and to give some more motivation, even if we discretize the parameters range, the number of combinations is infinitely large, and each run takes 10 hours.
Therefore, we cannot evaluate many combinations in a reasonable time. But can we find a better way than Grid search to optimize the parameters values? We propose a simulation optimization approach that uses Evolutionary Optimization combined with Simulated Annealing. Our approach is more efficient than grid search because it focuses on areas of the search space where good solutions were found.
Evolutionary strategy is an optimization algorithm of this form. In the first iteration, generate the initial population of individuals randomly. Then, repeat the following steps until termination.
Evaluate the fitness of each individual in the population. In our case, we’ll evaluate the KPIs at cycle time and on-time percentage. Then, select the fittest individuals for reproduction, the parents.
Bring new individuals through mutation and crossover of the parents. We combine this approach with Simulated Annealing. which is an exploration technique which gradually decreases the probability of accepting worse solutions. We use simulated annealing in the regeneration process by gradually reducing the range from which offspring are created. We basically reduce the strength of the mutation as the search goes on. Here is an example of how we implement our search algorithm on a parameter called Line Balance Threshold 1. We start from choosing a value randomly from the full range of possible values 0 to 24.
We evaluate the solutions and center the next range to pick from around the best solution found so far. We repeat the process and in each iteration the range size decreases. We stop when there is no more improvement in the solution values.
We compare our results with the best results obtained from 300 Grid search runs. The grid search samples solutions uniformly at random from all possible parameter values. The best average cycle time is 922 hours, which is approximately 40 days, and the best on-time percentage is 86.9 percent.
Here we can see the performance of Evolutionary Optimization, which found a better solution in two iterations, where each iteration is 12 runs, and it reached the solution of 902 hours of cycle time compared to 922 hours found by grid search in 300 runs.
Also for the on-time percentage KPI, Evolutionary Optimization reached a better solution than grid search in less than half the number of runs with 88.2 percent on-time percentage compared to 86.9 percent found by grid search. In addition to optimizing continuous value parameters, our approach can also optimize nominal value parameters.
In this example, we optimize which station families should be considered as bottleneck stations. We first rank the stations based on these criteria average WIP, percent of idle time, and average cycle time. And we took the top eight to be possible candidates, out of which in each run we choose only three.
The ones marked in blue were the originally the bottleneck station families. So in each run we chose three out of the top eight candidates, and in each iteration we adjusted the probability of choosing a station family based on its frequency of occurrence in the top runs of previous iterations. Then we combined the optimization of continuous parameters, a line balance parameters, and the nominal parameters, the bottleneck station parameters. And we optimized them jointly using Evolutionary Optimization and measured the on-time percentage KPI. In this figure we can see the best on-time percentage KPI for each iteration. Each iteration consists of 20 simulation runs.
In each run we vary both the line balance parameter values and the combination of bottleneck station families. By the ninth iteration, the on-time percentage reached 98.83 percent, which is a huge improvement compared to 88.2 from optimizing line balance separately, and 86.9 which grid search got. The same thing happened with cycle time.
Here again we jointly optimized the line balance parameters and the bottleneck stations using Evolutionary Optimization while measuring the average cycle time KPI. In this figure we can see that the best cycle time in each iteration goes down. Each iteration is 20 runs, and in each run we vary both the line balance parameters and the combination of bottleneck station families.
By the seventh iteration, the cycle time reached 886 hours, which is a huge improvement compared to 902 obtained from optimizing line balance separately, and much better than the 922 obtained from 300 grid search runs. So what we can see is that jointly optimizing continuous and nominal parameters using Evolutionary Strategy can reach very good KPI values. To conclude, optimizing the dispatch rules parameters requires testing an exponential number of combinations.
To mitigate that, we developed an efficient method for finding good combinations. Our method is a Simulation Optimization method, which uses Evolutionary Strategy and Simulated Annealing. Our method can handle both continuous and nominal parameter values, and we demonstrate how it outperforms Grid search on two KPIs, the average cycle time and the on-time percentage. The main advantage of our method is that it zooms-in on good solutions quickly and narrows the search space to candidate solutions in their vicinity. The main takeaway is that our approach allows finding better solutions with less simulation runs. With that, I will conclude, and I thank you very much for listening.
Ready to contact us to learn more about our dispatching, scheduling or other solutions?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [Drive yield enhancements with better visibility](https://appliedsmartfactory.com/semiconductor-blog/quality/yield-management/)
**Published:** August 2, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Improve yield learning and accelerate yield ramp using an integrated yield analysis solution
**Content:**
In your fab, what type of yield issues impact your factory performance? Defects? Parametrics? Both? Do you experience low yield, metrology, or parametric “spots” on your wafer maps? To help with such issues, an integrated, fab-wide yield management system is critical for facilitating yield learning and reducing time for quality analysis.
Built with a single storage and analysis platform for all semiconductor data, SmartFactory Yield Management offers a single source of truth for the entire organization. It loads and pre-aligns diverse data from WIP, FDC, metrology, defect, sort, assembly, final test, and other sources to reduce analysis time and help prevent costly yield excursions.
With SmartFactory Yield Management, customers have achieved **30%** reduced time to reach mature yield and **80%** reduced time to achieve quality data analysis.
For details on our solution, check out our solution brief:
\[pdf-embedder url=”/wp-content/uploads/2022/08/SmartFactory-Yield-Management-Solution-Brief.pdf” height=”1000″\]
[ Download this PDF ](/wp-content/uploads/2022/08/SmartFactory-Yield-Management-Solution-Brief.pdf)
Ready to contact us to learn more about yield management and other solutions?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Are you ready to reduce or even avoid unplanned downtime for your manufacturing software systems?](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-software-systems/)
**Published:** June 1, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** SmartFactory Monitor prevents factory-impacting problems through performance trend analysis and predictive analytics.
**Content:**
Manufacturers face many types of challenges, from process problems to equipment issues. A challenge that often flies under the radar until it’s too late is when an issue arises with the critical software and servers that support factory operations. It’s inconvenient if a process tool goes down but if your MES goes down, the entire factory goes with it.
Because your factory’s uptime is critical, you most likely have metrics in place to monitor it, as well as quality programs in place to improve it. Keeping product moving through the factory and processing correctly are keys to your company’s profitability. Your manufacturing software systems all play a key role in productivity and quality too, and this is true when they’re working –and even when they aren’t. As much as we hate to think of it, sometimes a server goes down or a network has an issue. Sometimes power is accidentally shut down to the whole server room because of a tool install happening nearby. The result is unplanned downtime, sometimes for the entire factory. This has a significant business impact.
For a modest low-volume wafer fab, just one hour of unplanned downtime can have a $10,000 impact on the company’s bottom line. For a medium-volume fab it’s more like $100,000. For a state-of-the art high-volume wafer fab, it can be as much as $1,000,000. It’s essential then, to find ways to reduce or even avoid unplanned downtime for your manufacturing software systems. SmartFactory Monitor can help you do just that.
SmartFactory Monitor is a real-time monitoring software solution that allows you to identify problems, facilitating corrective action before any of your production systems are impacted. In its most basic form, it provides a customizable, easy-to-digest dashboard showing the current state of your production systems. This makes it almost seamless to see and send a notification when a problem occurs.
One of its key features is customizability, allowing you to create custom visualizations to display performance trends over time. Its predictive analytics capabilities allow for detection of performance anomalies before they become production impacts.
SmartFactory Monitor runs on modest hardware in a small process footprint using your choice of OS. It is pre-integrated with other products in the SmartFactory software portfolio and keeps track of all your manufacturing systems—the applications, databases and both Windows and Linux servers. The system monitors, in real time, system performance logs, error logs, event logs, application logs, system logs, server logs – anything and everything that can provide a clue to system performance and health.
Everything is aggregated into Splunk, software that captures, indexes, and correlates real-time data that can then be used to generate automated notifications and create visualizations to highlight trends and spot problems. It also can be used as training data for machine learning algorithms that enable predictive analytics so issues can be identified and resolved before they become problems in the factory.
Pre-built dashboards are available to get you up and running quickly, monitoring all your system logs. Using Splunk, you can easily visualize system performance and detect trends, anomalies, and outliers using sophisticated prediction algorithms developed by Applied Materials engineers.
SmartFactory Monitor provides a comprehensive set of production-monitoring capabilities to address many of the key support-system challenges that manufacturers encounter. The primary objective is to reduce unplanned factory downtime by decreasing the time it takes to identify and resolve system problems. Ultimately, it can help prevent factory-impacting problems altogether through performance trend analysis and predictive analytics.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Smart Manufacturing Evolution](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/leaping-ahead-factory-automation/)
**Published:** October 26, 2024
**Author:** Scott D. Rothenberg, Managing Director, Deputy General Manager, Applied Materials, Automation Products Group
**Excerpt:** Key elements for leaping ahead in factory automation
(Part 3 of 3)
**Content:**
[ Part 2](/semiconductor-blog/smart-manufacturing/opportunity-to-leapfrog-manufacturing-automation/)
## This 3-part blog series was inspired by a live presentation delivered at SEMICON India on September 11, 2024
## Live Presentation
“Evolution of Smart Manufacturing: Lessons for India’s Leap Ahead to Advanced Automation.”
### Scott Rothenberg
Managing Director, Deputy General Manager
Applied Materials | Automation Products Group
## What’s Inside
- [ Four elements of Smart Manufacturing ](#index1)
- [ Roadmap to leap ahead ](#index2)
- [ Conclusion ](#index3)
In part 2 of this blog series, “leapfrogging” and the semiconductor industry’s role as technology pioneer was discussed. This blog now looks at the main elements of a smart manufacturing solution and the roadmap India can follow to take the leap.
### Key elements of smart manufacturing
The semiconductor industry led the world in creating automated factories that build the world’s most complex devices. These smart factories have systems that capture and process petabytes of data, making and executing decisions automatically, with virtually no human intervention. There are four key elements to smart factories:
**Key Element 1: Material Transport**
Material transport is a vital component of an automated factory, involving overhead transport, guided vehicles, robots, or conveyors. To ensure the quality of the final product, human handling is minimized due to the sensitivity of modern semiconductor devices. Advanced software controls the hardware, efficiently routing material to the correct location, considering numerous variables, and swiftly responding to real-time conditions on the factory floor and supply chain.
**Key Element 2: Equipment Control Software**
The software responsible for operating and controlling the equipment is another crucial element of a smart factory. It goes beyond automating basic start and end operations. Modern engineering software solutions excel at managing numerous process recipes, collecting and analyzing data from countless real-time sensors, and making dynamic adjustments to recipes to optimize product quality.
**Key Element 3: Exception Handling Capability**
Another defining feature of a smart factory is its capacity to accommodate and address exceptions while operating in full automation mode. For instance, if a machine shuts down while material is in transit for processing, intelligent software will swiftly identify an alternate path to minimize disruption and optimize the overall factory performance, adapting to the altered environment.
**Key Element 4: Learning Factory Automation Solution**
The final, and arguably most critical, element is a factory automation solution that possesses the ability to learn and continuously improve. Utilizing technologies such as artificial intelligence, machine learning, and digital twins, these smart factories have access to vast amounts of data and computational power. This enables them to autonomously tackle novel challenges and solve problems that they have never encountered before, making the factory smarter over time.
### Roadmap to leap ahead
In looking at the evolution of manufacturing and the introduction of new technologies, we saw how our own industry has had perhaps the most significant impact on developing and implementing advanced manufacturing technologies. We’ve also looked at a very high level, at the key elements required to enable smart manufacturing – whether we call it lights out manufacturing, Industry 4.0, factory of the future, or just “SmartFactory,” which we at Applied Materials use to describe our CIM offerings. The question persists: “What can India learn from 50 years of semiconductor factory automation progress, and how can it leverage these advancements to fulfill Prime Minister Modi’s vision of becoming a global semiconductor powerhouse?” Our belief is that India has a distinct opportunity to establish the world’s most advanced semiconductor factories by leapfrogging technology and adopting cutting-edge automation solutions and practices. Let’s delve into the blueprint, aptly named *“Make in India – in the Smart-est Factory.”* Here are the five key points to consider: 1. **Full Auto Manufacturing:** It is no longer a luxury, but a requirement. Meeting today’s customer requirements for quality and supply chain dependability necessitates factories running with full automation.
2. **Integrated Automation Solution:** Avoid the pitfalls of piecing together automation components from multiple suppliers. Opt for a proven, comprehensive solution to minimize costs and deployment efforts.
3. **Scalable Solutions:** Choose software that can adapt and grow with your factory for the long term. Look for solutions that support future advanced computing technologies.
4. **Gradual Automation Journey:** Start with out-of-the-box capabilities and gradually customize and enhance the system as your experience, needs, and factory evolve. Move at a pace that suits your requirements.
5. **Trusted Partner:** Select an experienced partner who understands your automation needs and has a proven track record. Let them handle software deployment, technical support, and enhancements while you focus on other aspects of building and running your factory.
Remember, your partner should have the expertise and a comprehensive suite of software solutions dedicated to automation.
### Conclusion
These are exciting times for the semiconductor industry as we embark together on India’s Semiconductor initiative. India has a tremendous advantage in being a new entrant to this market, as it can benefit from all the learnings and costly investments of its peers. But perhaps the area where it has the most advantage comes from the ability to leapfrog manufacturing productivity and quality achievements by adopting state of the art factory automation.
For more information, check out our [SmartFactory Semiconductor Blogs](https://appliedsmartfactory.com/semiconductor-blog/) and [Semiconductor LinkedIn posts](https://www.linkedin.com/showcase/applied-smartfactory/).
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [Smart Manufacturing Evolution](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/opportunity-to-leapfrog-manufacturing-automation/)
**Published:** October 27, 2024
**Author:** Scott D. Rothenberg, Managing Director, Deputy General Manager, Applied Materials, Automation Products Group
**Excerpt:** India’s opportunity to leapfrog manufacturing automation technology
(Part 2 of 3)
**Content:**
[ Part 1](/semiconductor-blog/smart-manufacturing/origins-of-manufacturing/)
[Part 3 ](/semiconductor-blog/smart-manufacturing/leaping-ahead-factory-automation/)
## This 3-part blog series was inspired by a live presentation delivered at SEMICON India on September 11, 2024
## Live Presentation
“Evolution of Smart Manufacturing: Lessons for India’s Leap Ahead to Advanced Automation.”
### Scott Rothenberg
Managing Director, Deputy General Manager
Applied Materials | Automation Products Group
## What’s Inside
- [ “Leapfrogging” ](#index1)
- [ Semiconductor pioneers ](#index2)
- [ Where we are today ](#index3)
- [ Up next ](#index4)
In the first blog of this series, we looked at the origins of manufacturing and what it means to make it “smart.” In this blog, we’ll dig deeper into “leapfrogging” and the semiconductor industry’s role in pioneering the technology that makes it possible.
### “Leapfrogging”
The concept of “leapfrogging technologies” can be defined as “bypassing the traditional evolutionary phases of research, development, investment (and failure).” Does this leapfrogging really happen? Yes, absolutely. We see this across multiple industries, including telecommunications, banking, agriculture, power generation, computers and now, semiconductor manufacturing. As new technologies are developed, those who wait to implement can skip over costly investment and infrastructure development and move directly to low cost, rapid deployment and adoption. For example, in 1990, about 5% of households in India had a phone line. Today, there are more than 1 billion smartphone users in India, representing quite a leap.
### Semiconductor pioneers
The semiconductor industry spearheaded the technologies that led to Industry 4.0 and the age of Smart Manufacturing—and make it possible for countries like India to leapfrog technology today. The early pioneers in the industry, who we’ll call innovators, took the same approach with factory automation software as they did with process equipment; they built their own. There was no ecosystem of commercial software suppliers to support the industry. Indeed, there was hardly any industry at the time, and each company solved what seemed to be its own unique manufacturing problems with its own unique software solutions. This software was rudimentary in nature and, while functional, was never architected or engineered to provide decades of mission-critical use. It was generally single-purpose, not scalable and often written and supported by a few talented individuals who were loath to allow anyone else to see the code, much less edit it.
In the 1980s and ’90s, new entrants to the industry didn’t have the technical expertise, money, or interest to develop their own software. As a result, an industry began to sprout that provided specialized products that would address one of several aspects of manufacturing automation. These included Manufacturing Execution Systems (MES) to track the flow of material; Statistical Process Control (SPC) to help improve quality; Material Control Systems (MCS) to control material handling hardware; and Real Time Scheduling to prioritize lots for processing.
Early adopters of these products needed significant expertise to turn what was essentially a set of toolkits (each of which could theoretically “do anything” but that in practice “did nothing” without a lot of expert engineering) into a solution. There were still tools and systems that weren’t available commercially, or were deemed too immature, or lacking in features. These software components still needed to be written and supported by the factory’s own engineers.
### Where we are today
Today, it’s rare to find anybody building a new factory who will follow that “Do it Yourself” approach to factory automation software. While there are still companies that created their own home-grown systems with a combination of commercial and internal software, deployed and supported by large, experienced IT teams, they too are increasingly abandoning this approach.
The smart manufacturing approach is revolutionizing – and democratizing – semiconductor manufacturing in both wafer fabrication and packaging. Smart manufacturing entails turn-key, fully integrated, fully featured software solutions that – out of the box – can run a manual pilot line, all the way to a full-auto, lights out, high volume manufacturing facility. Not only does today’s software have more functionality, but it is also more stable, supportable and scalable. It’s simply better.
### Up Next
In the next blog in the “Evolution of Smart Manufacturing” 3-part series, we’ll dig deeper into the elements of a smart manufacturing solution.
For more information, check out our [SmartFactory Semiconductor Blogs](https://appliedsmartfactory.com/semiconductor-blog/) and [Semiconductor LinkedIn posts](https://www.linkedin.com/showcase/applied-smartfactory/).
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [Smart Manufacturing Evolution](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/origins-of-manufacturing/)
**Published:** October 28, 2024
**Author:** Scott D. Rothenberg, Managing Director, Deputy General Manager, Applied Materials, Automation Products Group
**Excerpt:** Origins of manufacturing – what makes it smart?
(Part 1 of 3)
**Content:**
[Part 2 ](/semiconductor-blog/smart-manufacturing/opportunity-to-leapfrog-manufacturing-automation/)
## This 3-part blog series was inspired by a live presentation delivered at SEMICON India on September 11, 2024
## Live Presentation
“Evolution of Smart Manufacturing: Lessons for India’s Leap Ahead to Advanced Automation.”
### Scott Rothenberg
Managing Director, Deputy General Manager
Applied Materials | Automation Products Group
## What’s Inside
- [ Early manufacturing ](#index1)
- [ Stone to steam ](#index2)
- [ Buzzwords vs. blueprints ](#index3)
- [ Focus on the goal ](#index4)
- [ Up next ](#index5)
India can skip over the decades and billions of dollars that its peers invested to develop the cutting-edge smart manufacturing technologies that are best practice today. In doing so, new semiconductor factories in India, both wafer fab and packaging, can enjoy improved time to market while optimizing yield, cost, and output. In short, India’s semiconductor industry can benefit from the collective work, investment and learnings of the rest of the world to build the smartest, most productive factories, building the highest quality products at the lowest cost. They can shift the S-curve, as we say, to produce more good die at every stage of the factory lifecycle.
In this first blog, we’ll look at the origins of manufacturing and what it means to make it “smart.”
### Early manufacturing
The English word, “manufacturing” comes from the words, “hand” and “made,” and it’s not a new practice. In fact, archaeologists have determined that the first manufactured products date back more than 2.5 million years. Evidence shows that India has had manufacturing for nearly half that time. An Acheulean stone axe manufactured more than one million years ago was found in Isampur, India.
To manufacture the stone axe, someone had to first recognize a need and envision a solution to address it; create a design; specify the raw materials; build specialized process equipment; execute complex manufacturing steps flawlessly and test the final product to ensure it met requirements. These basics of manufacturing have not changed, but how all of this is carried out is vastly different.
### Stone to steam
Over the million years since the axe was made, the Stone Age gave way to the Bronze Age, which led to the Iron Age and eventually, the Industrial Age with steam-powered looms and mills. One hundred years later, after the discovery of electricity, assembly lines and powerful new machines were invented to revolutionize manufacturing. Industry 2.0 was born. It was about 100 years until the development of electronics and computers in the late 1960s ushered in Industry 3.0. Just 50 years later, the semiconductor industry pioneered the technologies that led to Industry 4.0.
### Buzzwords vs. blueprints
Engineers like to build flowcharts and schematics, and there are countless versions available on the Internet that illustrate a hypothetical Industry 4.0 solution. You’ll see elements that include components like digital twins, big data, cloud, and Internet of Things to capture data from sensors, and 5G to move it around. While these illustrations are interesting, they are not entirely helpful for someone actually ready to build their own smart factory with limited time, resources and budget.
### Focus on the goal
At this point in the discussion of how to build a smart factory, we advise customers to step back and think about what they’re really trying to achieve. Despite the numerous buzzwords and non-stop emerging technologies, the goals remain clear: produce better die faster and at a lower cost; achieve higher productivity and fewer defects. Never lose sight of these objectives.
### Up next
In part 2 of our blog series, “Smart Manufacturing Evolution,” we’ll discuss opportunities for India to leapfrog manufacturing automation technology.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [Infineon Technologies maximizes ROI real-time with SmartFactory Activity Manager®](https://appliedsmartfactory.com/semiconductor-blog/use-cases/maximize-roi-real-time/)
**Published:** July 11, 2023
**Author:** Joerg Weigang (Applied Materials) and Julius Schmidkonz (Infineon Technologies)
**Excerpt:** Activity Manager quickly tests models, puts data in easy-to-compare interface
**Content:**
SmartFactory Activity Manager increases plant utilization and efficiency by sensing changes on the factory floor, deciding on processes, and responding to factory resources—all in real‐time. This results in better management and control of resources, equipment, software applications and personnel, maximizing ROI. [Infineon Technologies](/blog/infineon-technologies-describes-how-they-optimize-productivity/) has used [Activity Manager](/semiconductor/productivity-solutions/activity-manager/) extensively in their factories, including dispatching lots, controlling the automated material handling system, and for robotics control, among many other use cases. When they wanted to find the most accurate way to determine the availability of their sequential cluster tools, they used Activity Manager to rapidly test automation solutions, choose one as standard, and share the model across the company.
### The Challenge
Like many manufacturers in the semiconductor industry, Infineon used the Semi E10 Specification to define their equipment states and accurately measure variability. Tools without chambers and parallel clusters are well defined. But it wasn’t quite suitable for cluster tools with sequential processing, which called for more complex modeling. Therefore, Infineon set out to define a best practice method for defining the state of their sequential cluster tools. To test the viability, they selected a challenging cluster tool, which requires the product to run through multiple chambers in a specific order.
There was inconsistency in how different people defined the state of this machine. Take for example, a case in which the status indicators show three of the six chambers as working and three as idle. Some would consider the machine as 50 percent idle based on the number of chambers working at the time. However, others saw this as 100 percent operational as long as the internal bottleneck kept running. It was challenging to benchmark who was right and who was wrong in deciding the tool state, essentially to answer, ‘What is my real tool availability?’. An inability to benchmark performance has a direct impact on productivity because it leaves factories vague about what to fix or when to fix it. Tools that aren’t benchmarked would miss out on playing out to their full potential.
Infineon was looking to solve for how to calculate availability on sequential cluster tools, across different sites in the company, with one simple code. They decided to implement a number of different strategies and test them using Activity Manager. They used real time equipment states and process times along with other sources to gather the live transaction data from the tools for each cell in the cluster when they went up and down. They easily modeled each strategy using the click and drag interface of Activity Manager and those jobs were automatically run with an Activity Manager job, as shown in figure 1. This data was constantly collected, calculated, and stored in the Infineon database.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/activity-manager-extracts-factory-data-runs-apf-reports-to-compute-results-for-each-scenario-and-stores-those-results-to-an-external-database.png) Figure 1: Activity Manager extracts factory data, runs APF reports to compute results for each scenario, and stores those results to an external database
The data was then displayed in APF Analytics viewer, where they could see each method, calculation, and result in one place, as shown in figure 2. It was easy to compare these outcomes with input from the equipment industrial engineers, the process engineering team, manufacturing managers, and other subject matter experts, to determine which method they deemed to be most accurate.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/result-of-modeling-solutions-as-shown-in-solution-ui.png) Figure 2: Result of modeling solutions as shown in Solution UI
Because developing Activity Manager code doesn’t require in-depth expertise in programming, it allowed the subject matter experts to code the different logics themselves without a big IT project. The Infineon team was appropriately equipped to select the best model and easily extend the method across additional company sites. The entire process of testing, implementing, and extending the preferred model to other sites took a very short time, as opposed to the months it would have taken without Activity Manager.
Now, knowing the availability of their sequential cluster tools, Infineon can benchmark against other factories in their company and against the competition. This allows them to better plan moving forward because they know their true performance (and can use it to predict future performance). This ability to benchmark will also help them with capacity modeling, better allocation of resources, and will improve productivity.
**Semiconductor Category:** Semiconductor Use Cases
**Semiconductor Tag:** Semi
---
### [Upcoming events in Japan: advancing factory automation with SmartFactory solutions](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/japan-events/)
**Published:** October 17, 2023
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Everything you need to increase quality and productivity in factories of any size
**Content:**
Join us for presentations to learn how to thrive in factories of any size by adopting best practices in smart manufacturing, process quality, AI/ML deployment, and more.
SMART FACTORY EXPO | Factory Innovation Week
Jan 24-26, 2024, Tokyo Big Sight, Japan
Visualization and Utilization of Sensor Data to Improve Yield
presented by Kohei Mizota, Applied Materials
See our recent activities in Tokyo:
SEMICON Japan 2023
Dec 13, 2023. Tokyo Big Sight, Japan
Click on the links below to see details of each events
[ An Economic Case for Digital Transformation ](#)
[ Smart Manufacturing: Creating a Path to AI ](#)
[ Improve Semiconductor Manufacturing Processes Using SmartFactory AutoSched® Simulation Solution ](#)
AEC/APC Symposium Asia 2023
Nov 2, 2023. National Center of Sciences Building,
Tokyo Japan
Unified platform for detecting faults governed by process controls
Presented by Vishali Ragam
Smart Manufacturing Webinar
Virtual | Oct 20, 2023. 10-11 am JST
Smart Manufacturing Webinar: Creating a path to AI Presented by David Hanny
Smart Manufacturing Webinar
Virtual | Oct 20, 2023. 10-11 am JST
Smart Manufacturing Webinar: Creating a path to AI Presented by David Hanny
[](https://appliedsmartfactory.com/wp-content/uploads/2023/10/semicon-japan.svg)
## Latest Trends in Manufacturing DX
December 13-15, 2023
---
Wednesday, December 13 | 12:45 pm – 1:05 pm | East Hall 7 TechSTAGE SAKURA
#### An Economic Case for Digital Transformation
Semiconductor and High-Tech manufacturing companies are in constant discovery for an edge in the market. This session will share real examples making an economic case for using Advanced Technologies (such as cloud and AI) in your digital transformation.
**Presented by David Hanny**
Sr. Director, Automation Products Group
Applied Materials Japan
[](https://appliedsmartfactory.com/wp-content/uploads/2023/10/semicon-japan.svg)
## Latest Trends in Manufacturing DX
December 13-15, 2023
---
Wednesday, December 13 | 2:30 pm – 3:20 pm | East Hall 4 Show Office
#### Smart Manufacturing: Creating a Path to AI
How can advanced technologies complement your manufacturing business? In this session you will learn steps on how to approach creating a path to implement AI to improve your operations. And how the semiconductor industry use cases can help transform your smart manufacturing initiatives.
**Presented by David Hanny**
Sr. Director, Automation Products Group
Applied Materials Japan
[](https://appliedsmartfactory.com/wp-content/uploads/2023/10/semicon-japan.svg)
## Latest Trends in Manufacturing DX
December 13-15, 2023
---
Wednesday, December 13 | 2 pm – 2:20 pm | East Hall 5 Theater
#### Improve Semiconductor Manufacturing Processes Using SmartFactory AutoSched® Simulation Solution
Semiconductor manufacturing companies are typically looking for ways to improve productivity, risk avoidance, and irregular handling such as unanticipated changes in priority lot orders or unplanned tool failures. This session will share examples on how to use simulation to increase efficiency and reduce these problems.
**Presented by Reiko Takashima**
Sr. Consultant, Automation Products Group
Applied Materials Japan
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [The significance of data and model management for deploying AI](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/model-management-for-deploying-ai/)
**Published:** November 28, 2024
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** Orchestrating scalable AI solutions
**Content:**
## What’s Inside
- [ Data Collection and Preparation ](#index1)
- [ Production Workflow ](#index2)
- [ Monitoring and Maintenance ](#index3)
- [ Conclusion ](#index4)
As the demand for artificial intelligence (AI) continues to grow, organizations are seeking ways to effectively scale their AI initiatives. One crucial element that can significantly impact the scalability of AI solutions is the data and model management approach to how they are deployed. This article highlights the significance of integrating a streamlined framework for managing and deploying AI models, while also identifying the essential components required to do so.
Learn how a robust framework can orchestrate some of the most difficult aspects of an end-to-end AI lifecycle, including standardizing coding, tracking, and maintaining AI models.
### Data Collection and Preparation
One of the most challenging aspects of building AI models is getting the necessary data in a usable format. For AI models to successfully make predictions that aid in better decision-making (or make decisions themselves), the data training a model must include dynamic scenarios that depict the complexity of a semiconductor manufacturing facility. These scenarios include fluctuations in work-in-progress (WIP) caused by downtime events, changes in certifications, bottlenecks, and more. Additionally, the data needs to be transformed into something meaningful, known as features. To do this, data scientists often start by utilizing custom code to extract data from various sources, followed by data validation to ensure its quality and completeness. This includes removing values outside acceptable tolerance and handling missing values according to their chosen methodology. Subsequently, they tailor the data transformation process to suit the specific requirements of their machine learning model.
There are also instances where data might be missing, such as when introducing a new part number or when a machine has been inactive, resulting in a data gap. In such cases, data scientists may resort to using their preferred simulation methods to generate the missing data and then do some ad-hoc feature calculations. While these custom AI deployment tasks serve their individual purposes, they lack scalability across the entire manufacturing facility or organization.
To provide the best opportunity for scaling, a standardized pre-configured feature management system is necessary to expedite data preparation. This key concept would enable any user in the fab or the organization who is attempting to develop other AI models to access a features repository. A sophisticated data management method should also go beyond simply automating feature management pipelines and allowing users to integrate their own intellectual property (IP). It should provide a variety of pre-built data validation checks, features that are ready to use, and [simulation capabilities](/semiconductor-blog/ai-ml/semiconductor-manufacturing/) to help facilitate feature generation in the cases where data is missing. Additionally, non-coding options for standardizing, executing, and automating these tasks should be available when deploying models. By offering non-coding alternatives, such as a Web-based UI, a wider range of users can actively participate and contribute their expertise to the centralized feature management repository, which leads to more effective AI models.
### Production Workflow
No one wants to work without a safety net. It is crucial to avoid situations such as an individual writing custom code on their personal machine and directly deploying their unique model to a production server without any transparency or accountability. The potential ramifications, such as inaccurate or maybe nonexistent predictions and unauthorized modifications to a production model, highlight the significance of implementing robust safeguards and maintaining accountability throughout the AI deployment process. Integrating AI into production should not be taken lightly. Therefore, a model management process that enables offline or preliminary scenario testing, model training, and model analysis is key. Necessary model validation methods could then be reviewed without impacting production.
The flexibility to choose between an on-premises (“on-prem”) or cloud option becomes essential when considering the preliminary stages of AI development. This is especially important when training a model on a large dataset, as it may require additional computational power. In an on-prem approach, tasks need to have the capability to be executed concurrently, taking advantage of parallel computing. Additionally, the versatility of a public, private, or hybrid cloud option also brings significant benefits. Providing this versatility when orchestrating AI elements ensures that end users have access to address their specific performance and data requirements effectively.
When models are deployed to production, it is essential for the system not only to automatically store previous versions in an archive location but also to provide comprehensive information about the production model. This information should then be easily available and include details such as training data, model parameters, prediction accuracy, and a clear record of the model’s deployment history, including the individual or group responsible for pushing it to production. It is also equally important to implement restrictions on user permissions. By allowing specific actions to be limited, such as restricting users to only view models without the ability to push them to production, a sense of control and accountability is maintained. This authentication, authorization, and model production workflow capability (covering preliminary stages, production, to archiving) fosters trust and, more importantly, efficiency in deploying AI by ensuring complete transparency for each model.
### Monitoring and Maintenance
While there is a lot of buzz around AI and many successful use cases, [people are still a little uncertain](/semiconductor-blog/ai-ml/leveraging-data-and-ai-technology-part-3/) about it. This is largely because it can sometimes seem like AI operates like a ‘black box.’ Change management around AI requires users to trust the output, and a critical element in gaining that trust is explainability. A robust model management implementation should allow users (domain experts) to view analytics and reports that provide insights into the performance of a model and the reasons behind it. For instance, if a machine learning model is consistently showing a trend of high lot cycle time predictions, users should be equipped with the necessary tools and analytics to investigate the underlying causes. With such tools, they may discover that the high prediction is due to a WIP bubble at a specific step and that adjusting a particular dispatching rule could help address the issue.
Another challenge when deploying AI is maintaining it in a 24/7 environment. Eventually, there will be a shift in data, maybe due to the introduction of a new part or a machine deviating from its original functionality with age. By implementing automatic retraining methodology, models can be maintained at their optimal performance level regardless of data changes. A model management interface should enable users to set up automatic training triggers without the need for coding. These triggers can be based on time intervals, such as weekly updates, or condition-based retraining, such as when a feature begins to drift or the model’s accuracy starts to decline.
Another level of maintenance is enhancing a model once it has been deployed. Consider the scenario where an industrial engineer believes a quality feature could enhance the accuracy of the model. In this situation, the adoption of a user-friendly, web-based interface for the production model management workflow would empower non-data scientists such as this to effectively enhance that AI model. This interface promotes scalability by enabling data scientists to focus on addressing the next valuable AI business use case without getting bogged down by model maintenance or enhancements.
The last pain point for maintenance is having to manage and work with many different systems. By integrating your AI data and model management workflow around proven products already utilized in your factory, and with which there is familiarity, it becomes easier to scale AI. This then eliminates the need to adopt, integrate, and learn new software. By integrating with existing infrastructures, you not only streamline the process but also facilitate quicker and more efficient AI implementation.
### Conclusion
Implementing a data and model management approach is vital for scaling AI initiatives effectively. A robust solution can orchestrate efficient management and deployment of AI models, empower engineers to interact fluently with AI, and overcome specific data and modeling challenges. This simplification and automation of the end-to-end AI operations enables organizations to achieve a significant competitive advantage.
Explore how we are revolutionizing manufacturing by orchestrating data and model management for our scalable [AI productivity solutions](/semiconductor-blog/ai-ml/smartfactory-ai-transforming-manufacturing-productivity/)!
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [采用仿真技术加速人工智能在半导体制造领域的部署](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/semiconductor-manufacturing/)
**Published:** October 9, 2023
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** 探索仿真技术如何革新半导体制造中人工智能的部署，克服数据采集的挑战，并显著提升生产效率。深入阅读本文，您将获得深刻的洞见。
**Content:**
## 概要速览
- [ 部署的各个阶段 ](#index1)
- [ 数据采集的挑战 ](#index2)
- [ 仿真解决方案 ](#index3)
- [ 合格仿真模型应达到的要求 ](#index4)
- [ 用例：仿真技术可在哪些方面为智能制造中的人工智能提供支持 ](#index5)
- [ 结论 ](#index6)
通过仿真加速人工智能为您的工厂运营带来的价值！在生产环境中部署人工智能时，仿真可以解决难以完成的数据准备任务。我们将解释仿真在部署的各个阶段是如何工作的。
### 数据的不同阶段
在生产中部署人工智能绝非易事；需要经历许多步骤才能实施成功。[人工智能生命周期](/zh-hans/semiconductor-blog/al-ml-zh-hans/improve-productivity/)由设计、开发和部署组件构成（如图1所示）。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/end-to-end-lifecycle.png) 图1: 人工智能端到端生命周期
### 数据采集的挑战
尽管每个阶段都存在一定的挑战，但在第一阶段准备建立精确模型所需的大量高质量数据，就足以让众多公司望而却步，而终止人工智能的进一步部署。
收集并整理深度学习所需的各种数据往往需要耗费大量的时间和金钱，这些往往是小型企业难以承受的。
即使制造商拥有收集大量数据所需的资源，但由于环境不断变化等原因，历史数据往往不够充分。例如，设备和工艺步骤往往根据供应链中的不确定性、劳动力限制或零件类型变化等因素不断调整。
随着技术节点的发展，半导体制造中不断变化的场景（即增加更多时间限制步骤）尤其常见。因此，这些瞬息万变的变化导致没有足够时间建立多样化的历史数据集来训练模型。
### 仿真解决方案
然而，如果有一种方法可以获得更高质量的数据呢？如果可以在不受技术进步资源限制的情况下，在业务基本用例上探索人工智能会怎样？
通过“仿真”，您就可以回答这些“如果”！您可以仿真各种场景建模并生成合成数据，用于人工智能训练。您可以在不需要清理原始数据集的情况下加速推进项目，大幅减少收集足够数量的数据所需的时间。在生产实施之前量化仿真环境中变化的影响，也是避免不必要且代价高昂的风险的关键。此外，建立在丰富数据集上的训练模型往往能够开发出更强大、更有弹性的模型。对历史数据中很少出现的边缘案例或其他不同场景进行评估，也可以增加模型的泛化能力，提高整体准确性。
### 合格仿真模型应达到的要求
仿真需要许多详细信息才能进行准确的半导体制造复制。仿真过程中不仅需要在半导体工厂环境中复制各种场景，还需要复制生产系统中的派工和排程规则行为。
### 用例：仿真可以在智能制造中为AI提供支持
在很多场景中，仿真起到了非常关键的作用。首先，[强化学习（RL）](/zh-hans/semiconductor-blog/al-ml-zh-hans/deep-reinforcement-learning/)越来越受欢迎，仿真可以在这一体系结构中发挥关键作用。强化学习涉及代理（计算机程序或智能体系），其开展目的是在环境中采取行动改变环境状态，最大限度地完善制造流程、提升生产率。为此，可以建立一个精确的、非常详细的仿真模型作为环境，在这个环境中可以观察和调整代理的行为。例如，在仿真环境中，代理可以学习何时释放队列时间约束场景中的各个批次。下文图2展示了一个包含仿真器环境的强化学习框架。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/architecture-with-simulation.jpg) 图2：带仿真功能的强化学习架构
另一个很好的例子是，在机器学习（ML）框架中利用仿真，例如预测[生产周期](/zh-hans/semiconductor-blog/al-ml-zh-hans/achieve-accurate-lot-time/)。通过仿真，可以在丰富的多年数据集上进行模型训练，提升预测精确度。计划员有机会在非生产仿真环境中对变更项目进行测试和验证，例如更新后期批次预测时所需的派工和排程参数，有效提升运营效率。与上文的强化学习示例一样，通过对机器学习或强化学习模型与现有派工规则或排程模型的评估，仿真可以发现关键性能指标（KPI）的差异。这也为各项差异的比较提供了更为强力有效的机会。
### 结论
快速、可扩展的运行时间和适应各种规划范围的灵活性也是非常必要的。从仿真短期计划情况（即，进行两天运行演示设备故障场景）到表示长期计划用例的更大的仿真模型（即，通过一年的运行演示新增设备可能造成的影响），最终用户往往都希望以合理的运行时间获得精确到分钟的运行结果。
仿真和AI相结合，可以创造出一个高效的[生产力解决方案](/zh-hans/semiconductor-blog/al-ml-zh-hans/smartfactoryai-competitive-advantage/)，从而实现真正的运营效率提升。快速、灵活、可扩展和非常精确的仿真可以为AI解决方案提供支持，有效解决当前的派工和排程难题。从预测批次生产周期、优化派工参数值和排程约束条件等环节出发，SmartFactory AI Productivity 正迅速将AI创新方案变为现实。
## FAQs
#### Why is data preparation for AI considered a challenge in semiconductor manufacturing?
Data preparation for AI can be expensive in terms of time and resources, making it a barrier, especially for smaller companies. Historical data may also be insufficient due to evolving environments.
#### How does simulation help overcome data collection challenges for AI deployment?
Simulation allows for the creation of synthetic data, eliminating the need for extensive data cleaning. It provides an efficient way to generate diverse and high-quality data for AI training.
#### What are some practical benefits of using simulation in AI deployment?
Simulation enables the exploration of AI in essential use cases without resource limitations. It accelerates projects, reduces costs, and quantifies the impact of changes before implementation, reducing risks.
#### What role does simulation play in scenarios like Reinforcement Learning (RL) and Machine Learning (ML) in semiconductor manufacturing?
Simulation plays a crucial role in RL by providing a detailed environment for agents to learn and make decisions. In ML, it allows models to be trained on rich datasets, leading to operational efficiency gains and KPI comparisons.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [What is Smart Manufacturing?](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/what-is-smart-manufacturing/)
**Published:** March 13, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** We define smart manufacturing as striving for zero defects and optimal asset utilization of trying to get the most out of what you have. This allows you to drive the highest quality in your semiconductor factory and create the most profit from your operations.
**Content:**
#### Transcript
Thanks for joining today. In a few minutes we’re going to talk about a topic that might take an hour or two, but it’s about Industry 4.0. It’s important on the top to understand Industry 4.0 is not a destination. It is something that enables you to move to the destination that you would like in your Smart Manufacturing endeavors.
What is Smart Manufacturing? We define it in two ways. The striving for zero defects and the optimal asset utilization, trying to get the most out of what you have. We believe that it’s these two things that help you to be able to drive the highest quality in your factory and create the most profit from your operations.
Let’s look at these individually for just a moment. Defects are measured in a defect in each part per million. It has the direct relationship to the process quality capability that you have.
The level of automation enables you to move forward. Today, largely, many of the analysis are done offline. To take a step forward we need to be able to do something faster than a human can do it.
And as we start to learn and be able to create trend analysis, we can understand what is going on relative to that particular operation and how we can take it to the AI to drive end-to-end quality for the striving for zero defects. Let’s take a look at the asset optimization. There are many assets in your factory that include equipment.
It includes people, your products, the things that flow in and out of your factory. The success of most of these are measured in two main ways. What is the cycle time of the product in the factory and what is the output that you can drive.
As you drive this curve to the lower and to the right, you’re getting more out of what your factory has. Let’s start with a real-world example. Many of you have probably had the chance to sit in an automated vehicle that guides itself.
I know the first time I sat in one and let go of the steering wheel, I was a little bit nervous to see what was going to happen. It’s critical that your systems operate in real time, interpret the data, make decisions, they know about the road, they know about what’s off of the road and those boundaries. And what you want to avoid is something bad happening here, right? The software system is taking control of this vehicle.
The thing that is critical for success here is the speed of decisions. When something is recognized, when an event occurs, to be able to reduce that time between that event and the decision. That requires an integrated set of data and a warehouse of knowledge that allows applications to be able to operate intelligently.
To be successful in automated driving or manufacturing, there’s two limitations that have to be overcome. The first of those is the maturity of the technology and the second one is how do I share that information? How do I integrate that data? I want to take a minute and talk about both of those. The Society of Automotive Engineering defined six levels of automation and they transition from no automation to full automation.
This is directly the same as what we see in manufacturing. That we can move from no automation, where we’re moving things with paper, we start the tools by ourselves and we start to get systems that help us, that the human is operating, to on the blue side here is system initiated operation. Well this is where we get stuck a little bit and we need some new technologies to allow us to be able to move faster.
We can’t crunch data fast enough, we can’t store enough, we can’t share it fast enough. The visualization of it is a challenge and so new technologies are required to be able to take these steps forward. In the state of level three, the initial state of what one would call full automation, this is really a proving ground.
There’s still individual techniques that are non-integrated that are proving themselves out with these new technologies. Going forward, when those start to be integrated, now we’re able to leverage the trending data, the machine learning, to be able to apply artificial intelligence, make decisions that maybe we haven’t encountered before. And this is in a controlled environment.
Level five gets us to any environment. This is where the weakest part of your entire system is going to be stressed. Let’s take a look next at what we call the intelligence maturity.
Today, most manufacturing is largely sensory. There’s signals that come along, decisions that are made. These solve a local problem.
They’re passive and prevalent. Fault detection on maybe a piece of equipment. How do I handle recipes? How do I deal with the equipment and handle bad signals as they come across? These are all sensory manufacturing techniques.
Stepping forward is peripheral intelligence. This is where sharing begins. We extend the information from one step up and one step down.
You’re solving together someone else’s problem. You start to get into more things like dispatching based on other criteria. You start to get into advanced process control.
The next move up we call interdependent intelligence. This is where multiple systems are solving a common problem together. This is where trending information starts to come.
It’s an environment of learning. As you leverage that learning and apply logic to it, you start to get to the area of probabilistic intelligence. This is where AI comes in.
You’re able to prescribe things that are going to happen at a high level of probability. The machine and the process are able to act on the learning. And then finally, as we step up to interpretive intelligence, this is when we have become so experienced and the data is so well populated that we can handle new conditions that we have never had before.
That allows you to strive towards the goal of zero defects. Hopefully this was useful for you. Our moniker is we think that intelligence is designed.
It’s not something that happens by chance. You need a strategy to be able to get there.
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [Common Data Model enables RAPID deployment for productivity solutions – Dispatching and Reporting (Part 3/3)](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-3/)
**Published:** February 6, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** Improve cycle time by 10% in less than 6 months using SmartFactory Dispatching Solution
**Content:**
[ Part 2: Solutions ](/blog/rapid-deployment-part-2/)
In semiconductor front-end fabs as well as back-end assembly, test and packaging (ATP) facilities, efficient and flexible factory-floor production dispatching is vital to high productivity. Dispatching is the process of determining the next job that should be processed—ideally in real time—then assigning it to the right tool or station and ensuring it gets there at the right time and with minimum queue time.
Although building an effective dispatching system is vitally important, it’s equally important do so quickly to achieve critical factory productivity and time-to-market goals.
A way to accomplish these goals is to automate the dispatching process. Applied SmartFactory Dispatching & Reporting is an automated decision system that executes advanced rule-based, real-time dispatching, scheduling, and reporting strategies in both front-end and ATP factories. It is deployed with EngineeredWorks®, Applied’s prebuilt, out-of-the-box automation logic that executes on Applied’s proven APF platform and enables faster deployment times for dispatching systems (figure 1)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/step-involved-in-building-the-common-data-model-schema.jpg) Figure 1. SmartFactory productivity solutions components
### Case #1: Dispatching in a 150mm Fab
In 2015, one Applied Materials customer with multiple factories in Europe and Asia began to work with Applied to increase uptime utilization of key bottleneck tools at a European site.
Initially, the customer decided to use a custom dispatching protocol. They purchased an APF license from Applied Materials and then took advantage of Applied’s services on a T&M (time and materials) basis to implement the global dispatching rule, which focused on line balancing to feed bottleneck tools better.
This initial implementation took one year. The development effort itself took about six months, and additional time was required to roll out dispatching rules in the fab as this was a big change for manufacturing personnel. Efforts were put in place to improve dispatching compliance and to gather input to improve the functionality of the dispatching rules.
However, the following year the company realized additional dispatching rules were needed for managing queue-time control and batching, while enhancements to the existing dispatching rules also were required. But with few resources dedicated to this project, and lacking the additional skilled resources needed for the deployment, the company looked for alternatives.
At this point Applied proposed the implementation of EngineeredWorks for dispatch, and the customer agreed. The project scope included developing an ETM (Extract Transform & Map) layer to map data from the factory’s MES system to a common data model, along with the development of additional dispatching rules and reports as shown in figure 2.
Using this approach, Applied and the customer were able to tailor EngineeredWorks for dispatch to meet site requirements in just three months.
During this year of roll-out and implementation, the customer also decided to use EngineeredWorks for dispatch for its site in Asia. Following its successful implementation in Europe, the same solution was deployed at the Asian site in just one week, marking a huge reduction in deployment time from the nearly two years it took for the initial full-custom implementation.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/deployment-plan-new-min.png) Figure 2. The deployment plan for an out-of-box EngineeredWorks for dispatch implementation for one customer’s 150mm front-end fab.
In addition to the reduction in deployment time for dispatching, this company also benefitted from improvements in uptime utilization for the fab overall. The impact of the EngineeredWorks for dispatch is captured in figure 3.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/equipment-uptime.jpg) Figure 3. The figure shows the improvement in equipment uptime utilization that resulted from implementing EngineeredWorks for dispatch in a 150mm front-end fab.
### Case #2: Dispatching for Assembly, Test and Packaging Sites
Today, many ATP factories are leveraging the use of automated guided vehicles (AGVs) and robots to improve production performance.Mobile applications are also being used to drive productivity improvements, and all of these may require real-time data from different factory sources for optimum performance.
These issues were relevant at one Applied Materials ATP customer with multiple sites in the U.S. and Asia. Management selected Applied’s EngineeredWorks for dispatch for deployment at all their sites as a first step towards full automation. The project was also expected to improve factory utilization by at least 8%. The first step in implementing these capabilities was to automate the dispatching decisions. EngineeredWorks for dispatch not only does this, it also provides pre-built interfaces to MES, scheduling and material control system (MCS) software (for controlling the AGV devices).
The initial project was to deploy EngineeredWorks for dispatch at 4 sites within 8 months, The project plan for this implementation is shown in figure 4.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/precursor-to-fully-automating.jpg) Figure 4. As a precursor to fully automating its four ATP plants in the U.S. and Asia, one customer needed to implement Applied’s EngineeredWorks for dispatch at all four factories. The project timeline above shows how that was accomplished within 8 months.
Applied and the customer developed a collaborative project plan in which Applied took the lead in development and customization of EngineeredWorks based on the customer’s requirements, while the customer was responsible for mapping its data into the common data model. Applied and the customer had joint responsibility for the roll-out, which enabled them to quickly address any issues that arose.
All development work and the initial deployment was done at one lead site, and after a successful implementation there, EngineeredWorks for dispatch was rolled out to 3 other sites in parallel. Although this was challenging because the 4 sites were at different geographical locations, Applied was able to provide local deployment resources at each site in addition to expert resources at the lead site for development and integration.
The initial deployment was scheduled to be completed in a couple of months, but it took longer because of data availability and accuracy issues. Nonetheless, with close collaboration between both teams, the issues were resolved and EngineeredWorks for dispatch was successfully deployed as initially planned at four sites within 8 months.
In addition, the initial results post-deployment showed that the sites also achieved tool utilization improvements of more than 8%. The customer is now looking at implementing automated guided vehicle transport solutions.
[ Part 2: Solutions ](/blog/rapid-deployment-part-2/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Common Data Models, Semi
---
### [Accelerating AI deployment in semiconductor manufacturing with simulation](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/semiconductor-manufacturing/)
**Published:** October 9, 2023
**Author:** Samantha Duchscherer, Global Product Manager
**Excerpt:** Learn how simulation revolutionizes AI deployment in semiconductor manufacturing, overcomes data collection challenges and enhances productivity. Explore valuable insights in this article.
**Content:**
## What’s Inside
- [ Stages of deployment ](#index1)
- [ Data collection challenges ](#index2)
- [ The simulation solution ](#index3)
- [ Requirements for an acceptable simulation model ](#index4)
- [ Use cases: where simulation can support AI in smart manufacturing ](#index5)
- [ Conclusion ](#index6)
Accelerate the value AI can bring to your factory’s operations with simulation! Simulation addresses insurmountable data preparation tasks when deploying AI in a production environment. We’ll explain how simulation works throughout all stages of deployment.
### Stages of deployment
Deploying AI in production is no small feat; there are many steps to a successful implementation. An [AI lifecycle](/semiconductor-blog/improve-productivity/) consists of design, development, and deployment components (as shown in figure 1).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/end-to-end-lifecycle.png) Figure 1: AI end-to-end lifecycle.
### Data collection challenges
While each phase has its own challenges, preparing the substantial, high-quality data required for an accurate model during the first stage often is enough to discourage companies from continuing the process toward deploying AI.
Collecting and formatting diverse data required for deep learning is often expensive in both time and money, which is sometimes infeasible for smaller companies.
Even if a manufacturer has the resources required to collect large amounts of data, historical data is often inadequate due to an evolving environment. For example, tools and process steps are constantly adapting to uncertainties found in supply chains, labor limitations, or change in part types.
Evolving scenarios (i.e., adding more time constraint steps) in semiconductor manufacturing are especially common as technology nodes progress. Consequently, these rapid changes do not allow time for a diverse, historical dataset to develop to train models.
### The simulation solution
However, what if there was a way to get more quality data? What if AI could be explored on business essential use cases without the resource limitations of technology advancements?
With simulation, you can answer these ‘what-ifs’! You can model various scenarios and generate synthetic data to use in AI training. Projects can be accelerated without the cost of cleaning raw datasets and in significantly less time than it takes to collect a sufficient amount of data. Quantifying the impact of changes in a simulated environment prior to production implementation is also key to avoiding unnecessary, costly risks. Furthermore, training models on rich datasets develop more robust, resilient models. Evaluating on-edge cases or other diverse scenarios that seldom occur in historical data increases generalization abilities of models, which improves accuracy overall.
### Requirements for an acceptable simulation model
Simulation requires many details for an accurate semiconductor manufacturing replication. Not only must simulations replicate various scenarios in a semiconductor factory environment, but they also need to have the ability to replicate dispatching and scheduling rule behavior found in a production system.
### Use cases: where simulation can support AI in smart manufacturing
There are multiple scenarios where simulation plays a key role. For starters, [Reinforcement Learning (RL)](/semiconductor-blog/deep-reinforcement-learning/) is growing in popularity and simulation can play a vital role in this architecture. RL involves an agent, a computer program or an intelligent system, attempting to take actions in an environment to change its state for maximum manufacturing and productivity. Here, an accurate, very detailed simulation model can act as the environment where the agent’s actions can be observed and changed. For example, a simulated environment can support an agent in learning when to release lots in a queue-time constraint scenario. Figure 2 below shows an RL framework that includes a simulator environment.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/10/architecture-with-simulation.jpg) Figure 2: RL architecture with simulation.
Another great example is utilizing simulation in a machine learning (ML) framework, such as predicting [cycle time](/semiconductor-blog/achieve-accurate-lot-time/). Simulation allows models to be trained on a rich, multi-year dataset, which aids prediction accuracy. Operational efficiency gains are then possible as planners are given the opportunity, in a non-production, simulated environment, to test and validate changes such as updating dispatching and scheduling parameters required for late lot predictions. Just as in the RL example above, simulation can find key performance indicator (KPI) differences by evaluating ML or RL models versus existing dispatching rules or scheduling models. This provides the powerful opportunity to compare those differences.
### Conclusion
Quick, scalable run times and flexibility to accommodate various planning horizons are also necessary. From simulating a short-term planning situation (i.e., two-day run to illustrate a tool down scenario) to a larger simulation model to represent a long-term planning example (i.e., one year run to demonstrate the impact of adding new equipment), end users will always want a reasonable run time with results in minutes.
Together, simulation and AI can create a [productivity solution](/semiconductor-blog/smartfactoryai-competitive-advantage/) that enables real operational efficiency gains. A fast, flexible, scalable, and very accurate simulation aspect provides the opportunity to support AI solutions for current dispatching and scheduling dilemmas. From predicting lot cycle time to optimizing dispatching parameter values and scheduling constraints, SmartFactory AI™ Productivity is rapidly accelerating AI innovations into a reality!
## FAQs
#### Why is data preparation for AI considered a challenge in semiconductor manufacturing?
Data preparation for AI can be expensive in terms of time and resources, making it a barrier, especially for smaller companies. Historical data may also be insufficient due to evolving environments.
#### How does simulation help overcome data collection challenges for AI deployment?
Simulation allows for the creation of synthetic data, eliminating the need for extensive data cleaning. It provides an efficient way to generate diverse and high-quality data for AI training.
#### What are some practical benefits of using simulation in AI deployment?
Simulation enables the exploration of AI in essential use cases without resource limitations. It accelerates projects, reduces costs, and quantifies the impact of changes before implementation, reducing risks.
#### What role does simulation play in scenarios like Reinforcement Learning (RL) and Machine Learning (ML) in semiconductor manufacturing?
Simulation plays a crucial role in RL by providing a detailed environment for agents to learn and make decisions. In ML, it allows models to be trained on rich datasets, leading to operational efficiency gains and KPI comparisons.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [创新将帮助半导体制造商实时提高效率](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/increase-efficiency-real-time/)
**Published:** June 4, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 半导体市场增长预期良好，同时市场上有许多工具可以助力其发展
**Content:**
## 概要速览
- [ 人工智能 ](#index2)
- [ 物联网 ](#index3)
- [ 模拟制造 ](#index4)
- [ 创新技术 ](#index5)
- [ 创新材料 ](#index6)
- [ 结论 ](#index7)
在过去的几年里，从耳机到汽车等产品对半导体的需求不断增长，全球半导体行业经历了诸多挑战。分析师们目前对该行业已经开始复苏并将持续到 2024 年表示乐观。世界半导体贸易统计组织 (WSTS) 预测 2024 年的增长率将达到 11.8%。在人工智能半导体收入方面，Gartner 预计将实现两位数增长，增幅超过 25% ，达到 671 亿美元。
在促进增长的众多因素中，半导体制造商需要能够充分利用以下几项关键创新：
**人工智能：** 就像人工智能对芯片制造商提出了对人工智能硬件的要求一样，半导体公司自身也已充分认识到人工智能在提升工艺质量、优化生产以及提高工厂效率方面的潜力。
**物联网：** 物联网刺激了对半导体的需求，反过来，半导体行业也利用物联网来满足这种需求。物联网设备已进入生产环境，用于实时捕获数据和监控工具、设备和工艺流程。在正确的自动化解决方案支持下，这些设备有助于持续改进工艺流程。
**模拟制造：** 开发新的配方和工艺耗时耗资。利用人工智能和机器学习模型进行模拟或虚拟建模，可使制造商模拟工艺流程。这些模型可以在几天内生成大量数据，而不需要花几个星期或几个月来生产足够的晶圆来收集这些数据。这些模型可以快速提供对瓶颈、生产周期和产量的洞察，并预测可能影响产品的问题，而所有这些都不需要中断当前的生产。
**创新技术：**越来越小的芯片需要更精确的芯片图版和布线位置。制造商已经转向先进的制造技术，如机器人晶圆处理，以及独特的制造技术，如增材制造技术。
**创新材料：** 半导体公司已将目光转向氮化镓 (GaN) 和碳化硅 (SiC) 等材料，以实现更高的工作温度、高电压抗性、更小的外形尺寸和更快的切换速度。制造商在使用创新材料方面的持续创造力将帮助他们克服芯片尺寸的限制。
### 结论
积极利用**创新半导体解决方案**来改进工艺、提高生产力和质量的半导体制造商，无论其工厂规模大小如何，都将赋予他们更大优势，帮助其更好地满足客户需求，在充满活力的市场中保持竞争力。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Common Data Model enables RAPID deployment for productivity solutions – Challenges (Part 1/3)](https://appliedsmartfactory.com/semiconductor-blog/productivity/rapid-deployment-part-1/)
**Published:** February 6, 2022
**Author:** Madhav Kidambi, Director, Technical Marketing, Automation Products Group
**Excerpt:** Data challenges for rapid deployment of factory productivity and supply chain solutions
**Content:**
[ Part 2: Solutions ](/blog/rapid-deployment-part-2/)
In today’s fabs, it has become increasingly difficult and time-consuming to integrate and harmonize the data coming from diverse CIM (computer-integrated manufacturing) applications. In fact, this is now a major stumbling block to the rapid deployment of these systems and, hence, to the ability of a fab to quickly achieve targeted productivity.
All modern fabs face this issue, but it is especially acute for (1) new companies building semiconductor factories with limited prior experience and without access to skilled resources for rapid deployment; (2) Outsourced Semiconductor Assembly and Test (OSAT) or Assembly, Test and Packaging (ATP) companies, which are becoming more wafer fab-like in their operations; and (3) companies affected by ongoing industry consolidation.
The problem stems from the fact that manufacturers use a broad array of decision-support and manufacturing execution systems (MES) to meet customer commitments. Typical CIM applications include planning, scheduling, dispatching, automation and reporting. The interactions of these systems are described in Figure 1.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/cim-planning-hierarchy-for-semiconductor-manufacturing.jpg) Figure 1: CIM (computer-integrated manufacturing) planning hierarchy for semiconductor manufacturing
These systems rely on massive amounts of data from different CIM components, and the data needs are continuing to grow as device geometries shrink and as fabs ramp new technologies.
The data included in these systems relates to orders, products, process steps, equipment and operators. For example, order-related data might include product names, due dates, customer names, quantity, bill of materials, etc. Data related to processing steps might include step names, sequencing, equipment certifications, processing times, sampling and other relevant information.
Equipment-related information, meanwhile, might include equipment names/types, location, setups, batch sizes and preventive maintenance (PM) schedules/durations. In addition, it also might include auxiliary resources such as reticles, probe cards etc. Operator-related data such as certification and shift schedules also may be required.
In general, the data described above resides in different CIM components with their own integration methods and data structure models. In some cases data does not exist, is incomplete, or is being manually maintained on someone’s laptop.
Moreover, additional data from Advanced Process Control (APC) systems (run-to-run, fault detection and classification, etc.) increasingly is being used to make dispatching and scheduling decisions on the factory floor \[1\]. Automated material-handling (AMHS) data \[2\] also needs to be included in the decision-making process because today 300mm factories and 200mm and ATP factories are leveraging the use of Automated Guided Vehicles (AGVs) and robots to improve production performance \[3\].
Also, mobile applications \[4\] are being used to drive productivity improvements, and they may require real-time data from different factory sources.
Furthermore, the ITRS roadmap \[5\] notes that holistic factory scheduling plays a key role in improving equipment utilization, cycle time and on-time delivery. Making this possible means there is a need to integrate even more data. The roadmap defines the need for a real-time predictive scheduling tool that would incorporate predictive maintenance (PdM), PM scheduling, equipment health monitoring \[EHM\] and resource scheduling data.
Typically, the cohesive integration of all these systems is one of the most time-consuming aspects of their deployment. It can take anywhere from 6- to 12 months because no standard data model is defined. A considerable amount of time also must be spent validating and cleansing the data.
In the past, fabs typically addressed these needs by copy-exact methods, and they had a lot of skilled people available to ramp these systems to optimal usage.
This may no longer be the case, and so new models must be defined to maintain and automate the data. Some efforts have been made to develop a detailed data model and framework for semiconductor fabs \[6\], and industry and academic institutions have expressed the need to standardize the data model for decision-support systems. SEMATECH’s Modeling Data Standards \[7\] is one example.
But there has been little or no progress.
To address this gap, Applied Materials is developing a common data model using the Extract, Transform and Load (ETL) capabilities modules from Applied’s APF (Advanced Productivity Platform) software environment.
In addition to a common data model, pre-engineered productivity tools are also being developed to help customers achieve rapid system deployment and achieve productivity gains faster.
**REFERENCES**
\[1\] Marcel Stehli, Daniel Zschabitz, Thomas Jaehnig, “Bridging the Gap – Integrating APC Constraints and WIP Flow Optimization to Enhance Automated Decision-Making in Semiconductor Manufacturing”, ASMC 2015
\[2\] Christian Hammel, Robert Schmaler, Thorsten Schmidt, Joerg Lubke, Matthias Schops, Ulrich Horn, Marcin Mosinski, “Empowering Existing Automated Material Handling Systems to Rising Requirements”, ASMC 2016
\[3\] Didier Chavet, Shekar Krishnaswamy, “Factory Automation is Key to Sustainable Manufacturing at Western Digital at Shanghai Assembly and Test facility”, Nanochip-Fab-Solutions/december-2016
\[4\] Didier Chavet, Shekar Krishnaswamy, “Mobile Applications to Enhance Manufacturing Productivity in Advanced Packaging”, IWLPC (Wafer-Level Packaging) 2014 conference proceedings
\[5\] International Technology Roadmap for Semiconductors 2.0, 2015 edition Factory Integration
\[6\] Heshan Li, Jose A. Ramirez-Hernandez, Emmanuel Fernandez, Charles R. McLean and Swee Leong, “A Framework for Standard Modular Simulation in Semiconductor Wafer Fabrication Facilities”, Proceedings of the 2005 winter simulation conference
\[7\] SEMATECH, “Modeling data standards, version 1.0”, Technical Report, SEMATCH Inc., Austin, TX, 1997
[ Part 2: Solutions ](/blog/rapid-deployment-part-2/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Common Data Models, Semi
---
### [Optimize MES intelligence in semiconductor advanced packaging](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/semiconductor-advanced-packaging/)
**Published:** October 16, 2024
**Author:** Seong Hoon Lee, Global Product Manager, MES 300works and FACTORYworks®
**Excerpt:** SmartFactory MES for ATP brings die tracking and traceability, material consumption history to the fan-out process
**Content:**
## What’s Inside
- [ Use Case #1 – die tracking ](#index1)
- [ Use Case #2 – die traceability ](#index2)
- [ Benefits ](#index3)
- [ Summary ](#index4)
- [ Next Steps ](#index5)
Semiconductor advanced packaging has become critical in the development of next-generation devices. As technology advances, conventional packaging approaches face limitations in terms of size, performance, and power consumption. Advanced packaging addresses these challenges by offering increased functionality, smaller packages for improved performance, lower power consumption, and enhanced reliability.
Recent innovations in advanced packaging technologies are notable – particularly in fan-out packaging, which has rapidly been gaining popularity due to its versatility and scalability. Fan-out packaging allows heterogeneous integration of multiple semiconductor devices, such as processors, sensors, and high bandwidth memory (HBM), in a single, high-performance package. And it offers increased flexibility in terms of design and form factor, enabling smaller modules with increased functionality at reduced cost.
In this blog, we’ll explore two key use cases highlighting how the MES can optimize the fan-out packaging process.
### Use case #1 – die tracking
**Problem description**
During the fan-out packaging process, when multiple die are attached to a substrate, it’s important to model which dies are attached to which location and in what order, as shown in figure 1, below. Since many different die can be attached to a single substrate location, configuring the precise die-attachment sequence is critical.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure1-substrate-1.jpg) Figure 1: Multiple die on a substrate
The SmartFactory MES for ATP provides a flexible modeling method to define the right die and the right attachment sequence in advance at each step, as shown in figure 2.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure2-setup-die-attach-spec.png) Figure 2: Setup UI for defining die attach specification
**Benefits**
The SmartFactory MES for ATP allows customers to model and track how die are attached to a substrate, improving operational efficiency by mistake-proofing run-time operation. Additionally, pre-defined automation scenarios minimize the equipment automation integration effort.
### Use case #2 – die traceability
**Problem description**
The fan-out process significantly increases the complexity of determining the number and sequence of die attached at each substrate location. Traceability is necessary to track which die are consumed on each substrate. Flexible reporting tools are also necessary to allow users to easily view and evaluate die consumption history.
The SmartFactory MES for ATP can report which die were consumed for which assembly lot. Figure 3 below shows how users can see the product IDs of die consumed by an assembly lot.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figure3-die-consume-info-1.png) Figure 3: Report showing the die on an assembly lot
Users can also see die consumption by work order (see figure 4) and determine the consumed die quantity by substrate ID.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/10/figur-4-die-lot-consume-report.png) Figure 4: Report showing die consumption by work order
### Benefits
The SmartFactory MES for ATP provides comprehensive traceability reporting for both consumed die quantity and die/substrate location. No matter the product – from AI processors to HBM modules – the solution provides thorough and accurate information that’s explicitly curated to reduce root cause discovery time and minimize the impact of issues that arise during manufacturing.
### Summary
The SmartFactory MES for ATP: - Allows modeling die attachment location and sequence in a substrate. This, in turn, enables comprehensive and accurate traceability of die, substrates, and lots throughout the fan-out process.
- Provides comprehensive traceability of consumed material, manufacturing durables usage, process genealogy, and equipment utilization and maintenance, ensuring both visibility and auditability of manufacturing operations.
- Tracks lot movements, monitors production progress, and ensures accurate data synchronization between the MES and equipment automation throughout the fan-out process.
### Next Steps
Semiconductor advanced packaging is a revolutionary and rapidly evolving technology. We invite you to join us in exploring this technology – and in learning about how the innovations in the SmartFactory MES for ATP address many advanced packaging use cases. In our next blog, we’ll discuss how the solution can enable full automation in advanced packaging factories.
Ready to learn more about the Applied SmartFactory MES for ATP? Connect with us [here](/connect).
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [以人为本的解决方案：探索 SmartFactory 的独特之道](https://appliedsmartfactory.com/semiconductor-blog/smartclips/interviews/how-to-make-people-part-of-the-solution/)
**Published:** May 8, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Selim Nahas 阐述了 SmartFactory 解决方案对于把“人”视为解决方案核心组成部分的承诺，并强调了在智能制造解决方案中融入人本理念的重要性。
**Content:**
#### 文稿
我叫 Selim Nahas，我是应用材料公司自动化产品部工艺质量解决方案的总监，我从1995年入行至今。
SmartFactory 本质上是我们投资和开发的一个生态系统，用于捕捉、学习和嵌入行为到自动化中，以管理工厂生产过程中的任务。所以我非常强调这样一个事实：人和对这个生态系统的理解是一切的基石。我认为现在的重点是：我们如何做到这一点？我们如何构建一个生态系统，帮助人们理解流程和程序的复杂性，并决定将什么放回到工厂的自动化行为中？事实上，每次我们试图逐步识别一个流程、一个过程，或者自动化一项任务时，我们就会意识到，哦，原来我们真的可以实现自动化。
我认为，这是我们与其他系统的最大区别所在，任何其他系统都无法达到。其原因与平台架构方式、我们如何连接各个环节并具象化的方式密切相关。
在我看来，这就是创新。因此，它是广泛的，不是一件单一的事情。
它适用于很多方面。行业在全球范围内并不一致。因此，对每个人来说，世界也并非相同。
我认为，客户真正意识到 SmartFactory 解决方案的价值所在是意识到它不仅仅是 单一的解决方案，而且是一套整体解决方案的路线图，当将它们综合起来时，其价值远远超过 25% 或 50%。这时候客户开始意识到它的价值，并且他们认识到这一点，因为他们知道过去，工厂生产流程极其碎片化。而现在，他们有了可以追求的统一方案的路线图。就可以整合生产流程。这是投资，是与一个供应商的共同投资。他们对路线图的内容有更大的影响力和发言权。因此，他们也能了解预期效果、发布时间及成本等信息。
我们的解决方案具有可预测性、稳定性，以及根据需求继续发展和维护的能力。因此，除非客户预见到有需要，否则他们不需要花费所有的时间——这就是客户真正获得的价值所在。
这不仅是一种技术价值，更是一种关系价值。只有那些从根本上为大量用户服务，长期进行投资和开发的行业大咖才能付诸实现。
**Semiconductor Category:** Smartclips, Interviews
**Semiconductor Tag:** Semi
---
### [SmartFactory Private Cloud – Part 1: Roadmap to Deployment](https://appliedsmartfactory.com/semiconductor-blog/productivity/private-cloud/)
**Published:** March 30, 2023
**Author:** Madhav Kidambi and Cindy McVey
**Excerpt:** Framework makes it easier to plan and implement APF solutions in the cloud
**Content:**
### Interview
Madhav Kidambi, Technology Director, discusses a new roadmap our SmartFactory Productivity team developed to make it easier for our customers to plan and implement Applied’s APF solutions in a cloud environment.
Our Insights blogger, Cindy McVey, sat down with Madhav Kidambi to find out what motivated the team to create the new cloud offerings roadmap and how it will benefit customers as they decide how to deploy applications. They also discussed the release of Real-Time Dispatching (RTD) Private Cloud, the first SmartFactory Productivity offering on the map.
Insights: How did you go about developing the roadmap for APF cloud offerings?
Madhav: We know the term cloud offering can be interpreted in different ways, so we knew we first had to define what it means in different contexts, ranging from whether an application is cloud-enabled to operating solely in a managed cloud environment.
Based on those definitions, a roadmap then was created for migrating current on-premise offerings to cloud-based offerings. The roadmap, or framework, we developed (see figure 1) defines which applications will be deployed and hosted on a cloud to achieve these objectives. It also addresses the concerns around performance and security for data and applications.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/03/roadmap-demonstrating-implementation-of-applications-on-premises-and-in-cloud-environments.jpg) Figure 1: Roadmap demonstrating implementation of applications on premises and in cloud environments
Insights: How does the roadmap help customers plan or manage their applications?
Madhav: Our customers use the roadmap to identify and plan which applications can be hosted in their own data centers, versus which they will host in a cloud service provider’s environment or that provided by SmartFactory (level 4).
Insights: Do you expect every customer to have solutions on all four levels on the roadmap?
Madhav: No, this is a very customized approach in which the customer chooses to host or deploy the solutions at different levels based on their unique performance and data requirements. Typically, the mission critical applications run in level 1 or level 2, as will those essential to protecting intellectual property. These are hosted by the client and may be as much as a particular client needs or wants to deploy at any time.
The applications which are not mission-critical or do not have real-time decision-making requirements run in level 3 or 4 depending on the data security requirements. At level 3, the company utilizes a virtual private cloud where they have a dedicated account. At level four, we provide cloud services for a set of APF solutions, as well as other products and solutions the customer chooses to run at this level. Again, the roadmap is there to help guide the decision as to which solutions they may want to deploy in which type of cloud environment.
Insights: The first SmartFactory Productivity offering released since creating the roadmap is Real-Time Dispatching (RTD) Private Cloud. Why did you start with this one?
Madhav: RTD is the mission critical application, which currently has 90% market share in 300 mm fabs and is the foundation platform key to the rest of the products and solutions in our factory productivity portfolio. It made the most sense then, for it to be the first SmartFactory Productivity offering on the cloud using container-based architecture for mission critical applications. There are also specific pain points around RTD that Private Cloud can address.
For example, on-premise systems present many infrastructure issues for customers including that it can be difficult to apply operating system level and application patches. Upgrading also can be a challenge.
Cost also can be a real pain point. There are high infrastructure costs surrounding RTD because of the number of servers needed to support these systems. It can be hard to justify the significant capital expenditure to purchase new hardware specifically for RTD. This is particularly the case because centralized IT departments want to utilize data centers with shared resources because they are easier to maintain and secure and can be more easily standardized on hardware models.
Additionally, if a RTD is sized inefficiently, there is excessive cost involved as the manufacturer pays for what they don’t use all the time just to make sure they have it available some of the time.
Insights: And how does RTD help solve or prevent these pain points?
Madhav: RTD private cloud offers many advantages. Among these, it reduces the expensive on-premise installations and capital expenditures of the servers needed for such a system. Because it is hosted and deployed in customers’ existing data centers, it provides on-demand availability of computer resources and allows for faster innovation. This allows the manufacturer to: - Optimize hardware usage
- EOL of physical hardware
- A cloud cluster can be made up of less expensive, more commodity hardware
- Using APF Cloud with a larger number of APF applications can reduce the dependency on specialized expensive hardware
- Lower the cost of ownership of maintaining the application
- Leverage large scale parallel computing to make better decisions
Insights: What are some of the more exciting application benefits of RTD private cloud, beyond resolving the pain points?
Madhav: Because it is Kubernetes based, overall management of the applications is easier. This containerized system allows users to react more flexibly to changing demands and easily move applications between Kubernetes nodes. Managed via the load balanced gateway, applications can be isolated before being transitioned to a new node. There also is an easier horizontal scaling of both dispatching capacity and the ability to provision additional capacity simply by cloning existing production node application. And, the Kubernetes system allows for rapid expansion and contraction of resources with no downtime of RTD during platform changes.
Adding or removing hardware can also be seamlessly handled by Kubernetes—deploying a new instance of a machine has never been so easy!
I think customers will also appreciate that they are still in control; they can choose whether rolling out one or more production node applications will be completely automated or managed via the cloud portal.
Some additional benefits that help manage APF installations efficiently include:
- OS patches handled via Applied container images, or can be manually managed via multi-stage container builds
- Customers will be able to track stable builds (v9.0, v9.8 or v 9.8.0) to adjust to their level of risk
- Additional 3rd party packages can be handled via multistage build and upgrade on demand
- Small incremental changes will become the norm, with the ability at any point to roll back seamlessly.
**CONCLUSION**
Our SmartFactory Productivity team’s roadmap helps you choose and implement APF applications in a cloud environment. The first offering released after development of this roadmap is a containerized and Kubernetes based RTD product running in a private cloud computing environment in which all hardware and software resources are owned and managed by the customer. This enables developers to bring software maintenance and upgrades in-house to more easily stay up to date; allows for quick deployment and replication of systems to support expansion and meet ramp needs and reduces the overall support burden.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [SmartFactory 私有云——第 1 篇：部署路线图](https://appliedsmartfactory.com/semiconductor-blog/productivity/private-cloud/)
**Published:** August 16, 2023
**Author:** Madhav Kidambi and Cindy McVey
**Excerpt:** 框架使得在云环境中规划和实施 APF 解决方案变得更加便捷和高效
**Content:**
### 访谈
技术总监 Madhav Kidambi 就我们 SmartFactory Productivity 团队开发的新路线图进行了讨论，该路线图旨在让客户更轻松地在云环境中规划和实施应用材料公司的 APF 解决方案。
我们“洞察力博客”的博主Cindy McVey与Madhav Kidambi 进行了一场对话，探讨是什么促使该团队创建了新的云产品路线图，以及在客户决定如何部署应用程序时，该路线图会给客户带来什么好处。 另外，他们还讨论了实时派工 (RTD) 私有云的发布，这是该路线图上的第一个 SmartFactory Productivity 产品。
洞察力博客：您是如何着手制定 APF 云产品路线图的？
Madhav: 我们知道“云产品”这个词可以有不同的解释，因此我们深知，首先必须定义它在不同环境中的含义，这包括应用程序是否支持云，以及是否仅在托管的云环境中运行。
根据这些定义，我们创建了一个路线图，将当前在本地部署的产品迁移到云环境中。 我们开发的这个路线图或框架（见图1），定义了哪些应用程序将被部署和托管在云环境中以实现这些目标。 同时，它还解决了与数据和应用程序的性能和安全性相关的问题。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/03/roadmap-demonstrating-implementation-of-applications-on-premises-and-in-cloud-environments.jpg) 图1：在本地和云环境中实施应用程序的路线图
洞察力博客：路线图如何帮助客户规划或管理其应用程序？
Madhav: 我们的客户使用路线图来确定和规划哪些应用程序可以托管在他们自己的数据中心，哪些应用程序将托管在云服务提供商的环境中或 SmartFactory （第4级）提供的环境中。
洞察力博客：您是否期望每个客户都拥有路线图上所有四个级别的解决方案？
Madhav: 不，这是一种定制化程度很高的方法，客户可以根据自身独特的性能和数据要求，选择不同级别的托管或部署解决方案。 通常情况下，关键任务应用程序在第1级或第2级运行，用于保护知识产权的应用程序也在这两个级别运行。 这些应用程序由客户端托管，数量可根据客户需求或随时部署的需要而定。
非关键任务或没有实时决策要求的应用程序根据数据安全要求在第3级或第4级运行。 在第3级，公司使用虚拟私有云，并拥有一个专属账户。 在第4级，我们为一套APF解决方案以及客户选择在此级别运行的其他产品和解决方案提供云服务。 另外，路线图可以帮助指导客户决定在哪种云环境中部署哪些解决方案。
洞察力博客：实时派工 (RTD) 私有云是创建路线图后发布的第一个 SmartFactory Productivity 产品。 您为什么首先发布这个产品？
Madhav: RTD 是关键任务应用程序，目前在 300mm 晶圆厂中占据 90% 的市场份额，并且是我们的工厂生产力产品组合中其他产品和解决方案的重要基础平台。 因此，RTD 成为首个在云环境中使用基于容器架构来部署关键任务程序的 SmartFactory Productivity 产品，是一个合理的决定。 此外，私有云还可以解决 RTD 的一些特定痛点。
例如，在本地部署系统会给客户带来许多基础设施问题，包括很难应用操作系统级别和应用程序补丁。 同时，系统升级也是一大挑战。
成本也会成为一个真正的痛点。 由于支持这些系统需要大量的服务器，因此 RTD 的基础设施成本很高。 很难证明专门为 RTD 购买新硬件需要的巨额资本支出是合理的。 这尤其是因为集中化的 IT 部门希望利用共享资源的数据中心，原因是这些数据中心更容易维护和保护，也更容易实现硬件型号的标准化。
此外，如果 RTD 的尺寸不适合预期用途，就会产生过高的成本，因为制造商要为他们不经常使用的服务付费，只是为了确保在某些时候可以使用它。
洞察力博客：RTD 如何解决或预防这些痛点？
Madhav: RTD 私有云有许多优势。 其中一个优势是，减少了此类系统所需的昂贵的本地安装和服务器的资本支出。 由于托管和部署均在客户现有的数据中心，因此可按需提供计算机资源，加快创新。 这样，制造商就可以： - 优化硬件使用
- 结束物理硬件的生命周期
- 云集群可以由价格较低、商品化程度较高的硬件组成
- 将 APF 云和更多 APF 应用程序结合，可减少对昂贵的专用硬件的依赖
- 降低维护应用程序的成本
- 利用大规模并行计算做出更好的决策
洞察力博客：除了解决痛点之外，RTD 私有云还有哪些更令人兴奋的应用优势？
Madhav: 由于是使用 Kubernetes 平台开发的，应用程序的整体管理要更容易。 有了这种容器化系统，用户能够更灵活地应对不断变化的需求，而且可以在 Kubernetes 节点之间轻松移动应用程序。 应用程序通过负载平衡网关予以管理，可以在过渡到新节点之前进行隔离。 通过克隆现有生产节点应用程序，可更轻松地横向扩展派工容量，以及提供额外容量的能力。 还有一点，Kubernetes 系统能够实现快速扩展和缩减资源，且在平台变更期间不会导致 RTD 停机。
Kubernetes 还能无缝处理硬件的添加或移除，部署新的机器案例从未如此简单！
我认为客户也会很高兴，因为他们仍然拥有控制权；他们可以选择，是完全自动化还是通过云门户管理从而推出一个或多个生产节点应用程序。
有助于高效管理 APF 安装的其他一些优点包括：
- 操作系统补丁通过应用材料公司容器镜像处理，或通过多阶段容器构建手动管理
- 客户能够跟踪稳定版（v9.0、v9.8或v9.8.0）以适应其风险级别
- 可通过多阶段构建和按需升级来处理额外的第三方软件包
- 小幅增量更改将成为常态，并能随时无缝回滚
**结论**
我们 SmartFactory Productivity 团队的路线图可帮助您在云环境中选择和实施APF应用程序。 该路线图后发布的第一个产品是运行在私有云计算环境中、基于Kubernetes平台的容器化RTD产品，在这种环境中所有硬件和软件资源均由客户拥有和管理。 这使得开发人员能够在内部实现软件维护和升级，从而更轻松地保持系统处于最新状态；还能够快速部署和复制系统，以支持扩展、满足爬坡量产需求，并减少总体支持负担。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [Automating the manual: Consumables management for semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/management-for-semiconductor-manufacturing/)
**Published:** September 12, 2024
**Author:** Yoram Barak, Global Product Manager
**Excerpt:** Consumables, the unsung heroes of the production floor
**Content:**
## What’s Inside
- [ Introduction to the consumables challenge ](#index1)
- [ The lifecycle of consumables ](#index2)
- [ Consumables management systems ](#index3)
- [ Challenges in consumables management ](#index4)
- [ Use cases examples ](#index5)
- [ Conclusion ](#index6)
### Introduction to the consumables challenge
In our previous [blog](/semiconductor-blog/manufacturing-execution/durables-management-for-semiconductor-manufacturing/), we delved into the challenges and opportunities of durables management within semiconductor manufacturing, highlighting the pivotal role these mobile extension elements play in the manufacturing process. In this blog we turn our focus to consumables, which present us with a new set of challenges. Unlike durables, consumables are used up during production, necessitating a robust management system to track their lifecycle from procurement to disposal. The efficient handling of consumables like chemicals, gases, targets, etc., is crucial, as any misstep can lead to production delays, increased costs, and compromised product quality. In this follow-up discussion, we’ll unravel the complexities of consumables management and explore how innovative software solutions can address them.
Examples of consumables used on the manufacturing floor include (see others in figure 1, below):
**Clean Gas:** Essential for maintaining a contaminant-free environment during manufacturing.
**Wet Chemicals:** Used for cleaning, etching, and stripping during the wafer fabrication process.
**Developer:** Used in photolithography to develop the image of the circuit onto the wafer.
**Diffusion Materials:** Include dopants that alter the electrical properties of the silicon wafer.
**Etch Gas:** Gases used for etching away unwanted materials to create the circuit patterns.
**Fluid Dispense:** Involves the distribution of various fluids used in the manufacturing process.
**Photoresist:** A light-sensitive material applied to the wafer surface to form the patterned coating.
**CMP Pads:** Critical for the chemical mechanical planarization process, ensuring wafer flatness.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/09/figure-1-examples-of-consumable-used-in-semiconductor-manufacturing.png) Figure 1: Examples of consumables used in semiconductor manufacturing
Each of these has a specific role and is integral to the semiconductor manufacturing process. The next sections will delve deeper into consumables lifecycle, management systems, and the challenges faced in handling them.
### The lifecycle of consumables
From its arrival on the manufacturer’s receiving dock, to the inventory room, the manufacturing floor and disposal/refill, each consumable’s journey needs to be carefully tracked and managed. Improperly managing consumables can be very costly and lead to a lot scrap and major delays supplying customer’s orders. Key life cycle steps of consumables are (as depicted in figure 2):
**Arrival and storage:** Upon arrival, consumables are logged into inventory systems with details such as expiration dates and storage conditions.
**Usage:** During production, consumables are used in various processes, often within tightly controlled environments to prevent contamination. For example, the consumable can be a heat sensitive chemical. This will highly impact the compatibility, quality, and shelf life of a consumable.
**Depletion and reordering:** As consumables are depleted, systems automatically flag low levels and assist in reordering to prevent production delays. Connecting these systems to suppliers allows constant replenishment of the consumables.
**Disposal:** Post-use, consumables are disposed of in accordance with environmental and safety regulations.
This cycle ensures that the right consumable is available at the right time and in the right condition, which is crucial for maintaining the high standards of semiconductor manufacturing.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/09/figure-2-example-of-a-chemical-consumable-lifecycle-.png) Figure 2: Example of a chemical consumable lifecycle
### Challenges in consumables management
Several challenges come to mind with consumables:
- **Quality:** Ensuring the quality of consumables is paramount, as subpar materials can lead to production defects and yield loss. In this case, supplier quality, ability to manage vendors and having clear audit trail capabilities are prudent. Furthermore, the ability to track consumables at the tool usage level and provide parametric context (i.e., SPC charts) could provide a major upside opportunity for process quality improvement.
- **Inventory accuracy:** Maintaining accurate inventory of ‘at spec’ consumables levels are critical.
- **Cost control:** Balancing the need for high-quality consumables with cost constraints.
A solution that can holistically address these challenges and integrate well with other systems is needed to ensure steady high-quality manufacturing.
### Ideal consumables management systems
Effective management of consumables is facilitated by specialized software systems that integrate seamlessly with the broader manufacturing execution system (MES) and other systems such as Scheduling, SPC, etc. These systems should include:
1. **Real-time tracking:** Monitoring the location and usage of consumables in real-time
2. **Inventory management:** Automated inventory control, including alerts for low stock and expiration dates
3. **Usage analytics:** Data analytics of where the consumable was, what it went through, lot and batch context, etc., are useful to optimize the use of consumables and reduce waste
4. **Compliance and reporting:** Ensuring compliance with industry standards and generating reports for audits and quality control
By leveraging these systems, manufacturers can achieve a harmonious balance between operational efficiency and cost management.
### Use cases examples
**Photoresist chemicals**
In the chip manufacturing process, the role of consumables such as photoresist, wet chemicals, and clean gases are critical. Let’s take the example of a semiconductor manufacturer facing challenges with their photoresist chemicals. These chemicals are sensitive to environmental conditions and have a limited shelf life, making their management complex.
**Problem:** The manufacturer experiences inconsistencies in their photolithography process, leading to defects in the circuit patterns.
**An ideal solution:** A software which provides the following benefits:
- **Environmental control:** The software integrates with the manufacturing floor on tool, storage, and in transit environmental systems to ensure optimal storage conditions for the photoresist chemicals.
- **Inventory monitoring:** Tracks the quantity and shelf life of photoresist chemicals in real-time, alerting the team before expiration date and/or stock reaches critical levels.
- **Usage tracking:** Monitors the usage patterns so the manufacturer can optimize their ordering schedule, reducing waste and costs.
- **Quality assurance:** The software records each consumables batch’s performance, allowing the manufacturer to trace defects back to specific chemical lots and address quality issues with suppliers.
**Physical vapor deposition (PVD) process targets**
In the PVD process, the target is a critical component, serving as the source material that gets vaporized and deposited onto a substrate to form a thin film. Targets can be made of various materials, including metals, alloys, and ceramics. Ensuring cleanliness and managing the erosion of the target can be challenging. Contaminants and uneven erosion can significantly impact the film’s quality and consistency.
**Problem:** There is no good system to track target usage, move it to refurbishment if need be and get it back. Another challenge is managing the transition based on parametric data from in-use to scrap. Additionally, there is no good system to disqualify a target based on its Certificate of Analysis (CofA) acceptance and send it back to the supplier (i.e., supplier quality).
**An ideal solution:** A software which provides the following benefits:
- **Lifecycle management:** The software integrates with the PVD tool, repair shop, storage and any other location to enable traceability and management of these state changes. The state model changes are based on counters, timers and measurements coming from various manufacturing systems and/or can be pre-configured in the system.
- **Move from in-use to scrap:** Offering maximal flexibility for tracking the usage based on vendor recommended shelf life, parametric conditions or an operator/engineer on the spot manual change decision.
- **Supplier quality:** The software can be configured to adhere to CofA metrics and disqualify with clear state transition such as send back to supplier if parametric requirements aren’t met.
With such a solution semiconductor manufacturers can improve their yield, reduce waste, and enhance their overall production efficiency.
### Conclusion
The management of consumables in semiconductor manufacturing presents a unique set of challenges to ensure best in class manufacturing quality, productivity and yield. SmartFactory Durables Management is a lifecycle management tool that can be used to manage many assets. Systems like these have become crucial in tracking and tracing the health and location of assets throughout the manufacturing process. Extending Durables Management capability to also manage consumables with their unique set of requirements is an obvious use of this solution to fulfil the semiconductor manufacturer’s asset life cycle management needs within one system. By doing so, a better manufacturing quality can be achieved.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Benefits of unifying process control in semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/quality/unifying-process-control/)
**Published:** October 16, 2023
**Author:** Christopher Reeves, Global Product Manager, E3
**Excerpt:** Achieve better detection, decision making, and costs through unified process control
**Content:**
## What’s Inside
- [ Siloed work environments ](#index1)
- [ Unifying the SPC and FDC functions ](#index2)
- [ Enabling process optimization ](#index3)
- [ Conclusion ](#index4)
- [ FAQs ](#index5)
Often in the industry, we get preoccupied with buzzwords like big data, digital twin, AI, and ML and we misinterpret these topics as goals to achieve. The real goal is to enhance factory performance. Depending on the source of the issue, there are various KPIs to focus on that help drive improved factory performance. These include how much time does it take to detect a problem, how will a decision impact production quality (Figure 1), and what is the cost of these events?
The ease of improving these metrics, as well as the ceiling to expand them, is directly linked to the way systems are implemented at a foundational level.
Figure 1: Making an impact on performance means making quality decisions quickly
### Siloed work environments
With that in mind, we need to first look at legacy practices for assessing equipment and process health in a factory. Often events are assessed in silos based on their domains, with equipment being the domain of the FDC engineer. When there is a FDC event, the FDC engineer analyzes tool data to recommend a resolution to the problem. The SPC engineer’s domain is the substrate. When there’s a SPC event, this person reviews metrology charts to prescribe action. Hopefully, they talk to each other, but that’s not typically the case. Being able to assess across domains requires a high cost which is realized through throughput, impact on product quality, and capital investment.
### Unifying the SPC and FDC functions
Integration of these domains can drastically reduce that cost, and that requires creating a unified platform. For us, unification represents integration at a core level across all process control systems and requires: - A standardized data structure, which is critical for advanced analysis and AI/ML applications
- Shared tools to help standardize our action and reaction to events
- A consistent UI which provides the same look and feel across applications
- Universal management to streamline the administration of the applications
- A standardized knowledge base that enables us to reuse expertise and lower the overall investment
- Architecture designed to scale as factories grow
### Enabling process optimization
Integrating these systems to de-silo the process changes how equipment and process health is assessed. It enables a new practice through which an event would trigger a combined action plan with the ability to assess data across domains. This results not only in resolution of the event, but in the ability to optimize the process at the same time. A better analysis across domains enables faster detection of events—helping you migrate from a reactive to proactive approach.
### Conclusion
A holistic view of the equipment and process health leads to better, first-time-right decisions, and streamlines the connectivity of systems, enabling engineers to make high-quality decisions faster. This mix of integrated systems and shared access among team members lowers the impact of events and costs associated with them. In this way, manufacturers can improve factory performance quickly without compromising quality.
Figure 2: A holistic view of equipment, process health, and team collaboration perpetuates success wide and deep.
## FAQs
#### What is the primary goal of unifying process control in a factory?
The primary goal is to enhance factory performance, but the real question is how it achieves this goal.
#### What are some key performance indicators (KPIs) that can help drive improved factory performance?
KPIs include the time it takes to detect a problem, the impact of decisions on production quality, and the cost associated with events.
#### Why is it important to look beyond buzzwords like big data, digital twin, AI, and ML in the context of factory performance enhancement?
Buzzwords can be misleading, and it’s essential to focus on practical ways to improve performance.
#### How do legacy practices in assessing equipment and process health in a factory impact performance improvement?
Legacy practices often lead to assessments in isolated domains, creating challenges in communication and a high cost for assessing issues.
#### What are the domains typically involved in process control, and why is siloed assessment problematic?
Domains include equipment (FDC engineer) and substrate (SPC engineer). Siloed assessment can hinder communication and increase costs.
#### What are the key requirements for unifying process control functions effectively?
Effective unification requires a standardized data structure, shared tools, a consistent UI, universal management, a standardized knowledge base, and scalable architecture.
#### How does the integration of process control domains reduce costs and improve performance?
Integration reduces costs by streamlining assessments and communication across domains, leading to better analysis, faster event detection, and proactive decision-making.
#### What benefits does a holistic view of equipment and process health offer in terms of decision-making and cost reduction?
A holistic view enables better, first-time-right decisions and lowers the impact and costs associated with events.
#### How can manufacturers achieve a more proactive approach to factory performance improvement?
Manufacturers can shift from a reactive to proactive approach by integrating systems, sharing access among team members, and assessing data across domains.
#### What is the overall impact of unifying process control on factory performance and quality?
Unifying process control leads to improved factory performance without compromising quality, resulting in cost savings and more efficient operations.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Pros and cons of various scheduling solutions for semiconductor factories](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solutions-for-semiconductor-factories/)
**Published:** August 9, 2023
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** Choose scheduling that will be the right fit for your factory needs
**Content:**
Schedules can be created for the production floor using a variety of methodologies and technologies. These include: manual/Excel-based methods using simple FIFO or DDO rules which consider current work in process (WIP) and/or future WIP with simple/basic cycle time assumptions; area specific rules-based heuristic scheduling; simulation-based scheduling, and optimization-based scheduling. Methodologies also can be hybrid for both predicting future WIP arrival and for sequencing the lots to generate schedules. The choice and application of a methodology has an impact on the quality of the scheduling, as well as the productivity benefits the solutions can yield. At the same time, requirements for the quality and accuracy of the factory input data also increase across different types of scheduling systems.
Explore the possibilities
Build a new ecosystem of quality powered by Intelligence
[ Let’s Connect ](/connect/)
Typically, a scheduling solution requires factory data to be extracted and converted or transformed to solution input data. Then the scheduling engine (regardless of methodology) applies the logic based on different considerations and objectives to generate scheduling output data. This then gets processed and published as schedules for end users to consume in a user friendly visual and analytical format. This is represented in figure 1, below.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/08/figure1-schedule-flow-picture.jpg) Figure 1: Scheduling solution process flow
The following looks at some of the benefits and limitations of the various methodologies and technologies.
### Heuristics based scheduling solutions
This is a rule-based approach to lot assignment and sequencing. Manual factories lose productivity by deploying a simple FIFO, DDO, or lot priority approach to scheduling. Using more sophisticated heuristics based on the area, product mix, tool configuration and factory objectives will quicky improve tool utilization, throughput and cycle time of the tool sets.
### Simulation based scheduling solutions
In simulation scheduling, models use simulation to predict future lot or WIP arrival based on their current status and position for all the tools in the factory. Simulation scheduling is considered a fab scheduler; it also can work with area schedulers by using their output as an input for downstream areas.
### Optimization based scheduling solutions
In optimization scheduling, Mixed Integer Programming (MIP) or Constrained Programming (CP) models do lot allocation and assignment based on area-specific weighted objective functions, creating optimal equipment schedules. Optimization schedulers are area schedulers that can integrate with simulation-based factory schedulers.
Table 2, below, allows you to easily see the advantages of each solution.
### Positive attributes of each solution
Heuristics Simulation Optimization Easy to develop, configure and deploy
More accurate future lot/WIP arrival prediction
Best possible feasible and optimal schedules
Simple to learn, extend and customize
Can schedule for the whole factory and implement dispatch rules in scheduling
Detailed equipment modeling
Early gains for KPI improvements
Validate dispatch rules in a non-production environment
Better bottleneck management
Moderate sensitivity to input data requirements/quality
Scales across sites and companies and achieves better line balancing
Sensitive and responsive to changing factory conditions and objectives
Table 2: Positive attributes of heuristic, simulation, and optimization-based scheduling solutions
Explore the possibilities
Build a new ecosystem of quality powered by Intelligence
[ Let’s Connect ](/connect/)
There also are limitations to each solution or technology, as shown in Table 3, below.
### Limitations of each solution
Heuristics Simulation Optimization May require constant fine tuning
Highly sensitive to factory data quality, latency, and granularity
Highly sensitive to factory data quality, latency, and granularity
Doesn’t realize all potential gains for production
Uses a simplified version of dispatch rules implementation
Difficult to explain scheduler decisions
Needs to be in production environment to assess effectiveness
Not a mathematically optimal solution
Need longer deployment time
Often provides a good but not optimal solution
Higher resource requirements for maintenance
Higher resource requirements for maintenance
Not sensitive and responsive to changing factory conditions and objectives
Model performance time nonlinear with problem size
Table 3: Limitations of heuristic, simulation, and optimization-based scheduling solutions
### Conclusion
Factories should select a scheduling software solution based on assessment of their factory requirements. Ideally, the solution should be a good fit between those requirements, your current and future maturity levels to absorb new technology and business practices, and capabilities of the software solutions available to you. The following questions can help in your decision-making process:
- Does the factory need a factory wide scheduler or an area scheduler?
- What is your bottleneck situation and the nature of your bottleneck?
- Current baseline of your factory automation
- Comprehensive account of your factory data generation, availability, gathering, storing, and processing capabilities
- Skilled resource availability to help implement and support your scheduling automation vision
Heuristics, simulation, and optimization scheduling all help improve factory KPIs, and each has its pros and cons. Factories should gain a good understanding of the suitability and capability of these varieties of scheduling to ensure successful implementation.
However, it is important to note that companies without prior experience and implementation of a sophisticated and automated scheduling solution should consider deploying heuristics-based scheduling. This will help you achieve early ROI in terms of factory improvement and, at the same time, allow you to gain experience and expertise. Implementation of more sophisticated scheduling solutions based on simulation or optimization in a company that has no existing dispatching or scheduling system could result in a shallow learning curve or an unsuccessful deployment.
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [What is an MES?
Reporting and analytics for continuous improvement (Part 5/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-5/)
**Published:** July 8, 2022
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** MES reporting and analysis | your tools to answer questions and solve problems.
**Content:**
[ Part 4: Key Data and Metrics ](/blog/mes-part-4/)
### Part 5 – Reporting & Analytics
While the MES serves a valuable role in defining, directing, and documenting factory activities, the big payoff is about the data the MES generates along the way and how that data can be used to answer the questions and solve the problems that manufacturers encounter every day. In the final part of this series, we look at how data generated by the MES can be used in reporting and analytics.
### Transcript
Welcome to the final part in this series, what is an MES? The final piece of the MES from a high-level perspective is reporting and analytics. You may remember from part one that, among the key goals of the MES, are to provide actionable insights that speed business impacting decisions and to provide advanced warning of problems that lay ahead. Reporting and analytics are intended to address both of these goals.
Management guru, Peter Drucker once said, “You can’t improve what you don’t measure”. And that’s the whole point behind reporting. We want to use the wealth of data generated by the MES to spot trends and identify areas for improvement and determine whether the improvements we’ve implemented are having the results we expected.
There are two types of reporting within the MES. Operational reporting provides a snapshot of what’s currently happening in manufacturing. It shows the state of things, right now. But operational reporting can’t show how we got here or whether the trend is positive or negative. That’s where historical reporting comes in. Historical reporting shows trends over time, making it possible to see whether conditions in the factory are getting better or worse. The explicit purpose of reports is to provide actionable insights to help the manufacturing staff proactively spot problems, identify root causes, and provide options for solutions.
Toward that end, we can view reporting from another perspective as well. Reporting within the MES can be seen as lot reporting or equipment reporting. It just depends on the nature of the problem at hand.
Where reports are terrific at creating actionable insights that can result in quicker decisions to improve manufacturing, it’d be impossible to create every report to cover every requirement in advance. Something slightly different is needed for that. What’s needed is the capability for manufacturing users to create their own reports and perform their own analysis that lead to their own insights.
Imagine a situation where a process engineer working on a problem thinks, if I only had a report that would show, “this”, I could better troubleshoot the problem and find a solution. In a typical situation, the engineer might open a request with the IT group for a new report, providing some basic specifications. It might take a couple of weeks for the request to pop up to the top of the IT’s tactical queue, at which time it gets assigned to a software engineer.
The software engineer exchanges emails with the process engineer over the course of a couple of weeks to understand the request and refine the requirements, then gets to work building the report. After a couple more weeks, the new report is released to the process engineer, who quickly concludes, there was clearly a misunderstanding because the report they received isn’t at all what they had in mind. After a couple more weeks of email exchanges between the process engineer and the software engineer, and a couple more weeks of software development time, a revised report is released.
This one captures perhaps 80% of what the process engineer needed to solve the problem. But, 10 weeks has already elapsed and the process engineer already solved the problem another way, weeks ago. So in the end, the effort was wasted. This is the type of thing that needs to be avoided.
What if, it’d be possible for the process engineer to get the report she needed in a few hours, rather than a few weeks? This should be possible by engineering MES data systems to allow direct and secure access by manufacturing customers. Manufacturers should be able to point their own analysis tools like Excel or Tableau or Power BI at the data source and slice and dice the data they need, to create insights tailored to the specific problems they’re working on. Insights in hours, not weeks.
And beyond this, the MES can never provide all the capabilities and functionality needed by every manufacturer and arguably shouldn’t even try. But if the data generated by the MES is made directly available to manufacturing customers, they could tap into it to create their own custom apps and utilities using low-code, no-code environments like Tulip or Microsoft’s Power Apps. This would allow nearly infinite customizability for customers, without the need for customer-specific modifications within the core MES product.
In the end, while the MES serves a valuable role in defining, directing, and documenting factory activities. The big payoff is really about the data the MES generates along the way and how that data can be used to answer the questions and solve the problems manufacturers encounter every day. The core features of the MES are informed by why they’re needed, the data they create, and how that can be used to solve problems for the business. And that way, what the MES is, can be thought of as the vehicle for generating the data that’s needed to drive continuous improvement in manufacturing.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [What is an MES?
Data and metrics that drive the factory (Part 4/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-4/)
**Published:** July 8, 2022
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Key MES data and metrics…and how manufacturers use them.
**Content:**
[ Part 3: Lot Tracking ](/blog/mes-part-3/)
[ Part 5: Reporting & Analytics ](/blog/mes-part-5/)
### Part 4 – Key Data and Metrics
While process definitions are important in coordinating the work being done in the factory, the data created during processing is equally important (but often overlooked). In part 4 of this five-part series, we look at some of the data generated by the MES and the factory metrics that can be derived from it. We also discuss how manufacturers use this information to improve operations and keep the factory running smoothly.
### Transcript
Welcome to part four in this series, “What is an MES?” In this part, we’ll continue our deep dive into lot tracking, looking closer at lots and equipment, the key data they generate within the MES, and the metrics that can be derived from this data. A lot’s journey through manufacturing creates a lot of data, and much of that is related to cycle time (that is, the total amount of time a lot spends in manufacturing). It includes considerations like whether a lot is on hold, slowing the lot’s progress in manufacturing, or has been designated as a high-priority lot, effectively speeding the lot up.
I’d like to point out a couple of the more interesting items. The due date is the date the lot is required to be finished and ready to ship. It’s often based on contractual terms between the manufacturer and their customer.
The estimated time remaining is the expected amount of time a lot will take to complete manufacturing. It serves as a countdown timer for the manufacturing staff for how much time they have left to finish the lot. And the estimated completion date uses the estimated time remaining to determine the expected date and time the lot will finish in manufacturing.
When comparing the estimated completion date against the due date, it’s possible to determine the amount of time the lot is ahead or behind schedule in manufacturing. This in turn, is used to prioritize lot order within equipment lot queues and keep lots moving in manufacturing with the goal of shipping on time. Some interesting metrics can be derived from lot information.
One of the most important is cycle time, which can be thought of as how fast a lot makes it through manufacturing. If we can decrease a lot’s cycle time, then that would make room for another lot to process during the time that was freed up. If we can decrease the cycle time for all lots, then potentially a lot of room can be freed up for many other lots to process, effectively increasing the overall output of the factory.
And, of course, that means increasing the potential for additional revenue, and that is a worthwhile goal. So that’s why manufacturers pay close attention to cycle time and work constantly to manage it and decrease it.
Yield is another important factory metric. It’s simply the ratio of the number of units that finish in manufacturing to the number of units that were originally started. If you need 100 units to fill a customer’s order and you start 100 units in the factory, but a few get messed up and scrapped along the way, you don’t wind up with 100 units the customer needs.
So you have to start more than 100 units in order to get the 100 units the customer needs. If you start 105 units and you finish with 100 units, your yield is, let’s see, that was number completed divided by the number started, so 100/105 or, 95% yield.
Yield is an important contributor to the cost of manufacturing. If the raw materials for the widget you’re building are expensive and you scrap a lot of them during the manufacturing process, the cost basis of the widgets that you complete are higher than they otherwise would be. If you start 100 and end up with 95, the cost of the 5 that were scrapped during manufacturing needs to be spread among the 95 you’re able to sell.
Higher cost means lower margin. Yep, that’s right. This is a business problem, not just a manufacturing problem.
And that’s why manufacturers work very hard to increase yield, because increasing yield decreases costs and lower costs mean higher margins. Each one of the lot’s key metrics has a story like this about how it affects the business of manufacturing. And the underlying data for each of these metrics is generated by the MES.
The data the equipment generates within the MES is largely related to utilization and factory throughput or how much of the time tools are available for productive processing to keep lots moving through the factory. This includes information like how long it takes to process a lot or the amount of time the equipment is unable to process lots because of, for example, scheduled maintenance. Again, I want to point out a few of the more interesting items.
The state of the equipment is typically expressed in terms of up, down, or idle. Up means it’s currently processing. Idle means it’s not processing, but is ready to process.
And down means the equipment is unable to process. The more the equipment is logged to a down state, the less it can be productive to contribute to overall factory output. So the equipment state is something that manufacturers watch very carefully.
As we’ve discussed before, an equipment’s lot queue represents the lots that have been dispatched to the equipment and are waiting to be processed. Long lot queues are often a factor in cycle time problems. The longer the queue, the longer each lot has to wait before processing.
And an equipment with a consistently long lot queue may indicate the equipment is a bottleneck in the factory. That is, the throughput of the entire factory is limited by that equipment, just like the slowest car on a windy two-lane road sets the pace for all the drivers behind. It’s important to keep bottleneck equipment up and running as much as possible, else the output of the entire factory suffers.
Processing time is the amount of time it takes an equipment to process a lot. We’d expect that time to be pretty much consistent from one lot to the next, running the same process recipe. But sometimes the processing time changes.
It could be an abrupt change because an internal component failed, or it could be a gradual change as the equipment drifts out of calibration over time. Either way, manufacturers pay close attention to processing time because changes in processing time likely point to a problem that needs to be fixed. Dividing a unit of time, say an hour, by the processing time, we get a key equipment metric called throughput.
Throughput is the number of lots that can be processed per unit of time. So if we wanted to know the number of lots that a piece of equipment can process in an hour, we’d take 60 minutes divided by the number of minutes it takes to process a lot. If it takes 10 minutes to process a lot, the throughput for that equipment would be 60 minutes divided by 10 minutes per lot, or 6 lots per hour.
For bottleneck equipment, multiply that number by the number of tools you have of the bottleneck equipment type, and you get the maximum factory throughput. So if the throughput of the bottleneck process tool is 6 lots per hour, and you have 5 of those tools, the maximum factory throughput will be 30 lots per hour. That’s a pretty important thing to understand.
Another key metric derived from equipment information is utilization. Utilization is a productivity metric. It’s the amount of time a piece of equipment is used for productive processing, that is, processing lots that can potentially be sold.
To better understand utilization, I find it helpful to look at what is not included in utilization and simply deduct that from total time. For example, scheduled maintenance can be deducted because when the equipment is being maintained, it’s not being used to process lots. And of course, so can unscheduled maintenance, when the equipment is unexpectedly broken and undergoing repairs to get it back up and running.
And when the equipment isn’t doing anything at all, it’s just idle. This can be for any reason. Maybe because there are no lots for the equipment to process.
Perhaps the equipment operator is at lunch. Maybe the operator is simply busy with something else and can’t start a new lot and idle equipment isn’t being utilized.
Manufacturers want utilization to be as high as possible, particularly on their bottleneck tools, because greater productive use increases factory output, which increases potential revenue. Yep, again, this is about the business of manufacturing. And again, the underlying data for each of the key equipment metrics is generated by the MES.
We’ll finish off this series in Part 5 by looking at how the data generated by the MES can be used for reporting and analytics.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [SmartFactory: Driving the Future of Manufacturing](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/smartfactory-driving-the-future-of-manufacturing/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Gain valuable insights as our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier explore how SmartFactory automation solutions are reshaping productivity and quality in factories of any size.
**Content:**
#### Transcript
We get a question pretty frequently, which is, what is SmartFactory and what does it mean to you? So I’m suspecting every one of you has a completely different take on this. Yeah. To me, SmartFactory means, you know, a fully integrated and fully, you know, communicative, collaborative manufacturing systems, which help you to kind of, you know, get the information in real time from your physical assets, and so that you can react to it and kind of form better strategies to improve, you know, the quality, improve throughput, and of course, you know, focus more on how you can make your factories more predictable.
There are so many different pieces of software that can go into a manufacturing facility. Software that does scheduling, software that does yield control, software that tracks lots of things like that, but how they talk with each other, how they integrate with each other to form a symbiotic system, to me, is really the key that makes the SmartFactory suite of software really unique throughout the industry. Nothing is integrated like the SmartFactory suite, and that’s what it’s all about to me, the integration. That’s the important thing.
The integration really encapsulates when you look at multiple systems that are trying to solve a common problem together, and one initiates something on the other. That means that there’s more than a pipeline. There’s a sharing of data.
In some cases, there’s a sharing of logic so that they can interoperate to solve that common problem together, and I think that as we think about that integration, it’s one of probably three key elements that really is required to be in smart manufacturing. I look at it as, what do we understand and what do we not understand? And what I mean by that is, if it’s an environment that provides the means for me to learn something about what I do and indoctrinate it into a manufacturing behavior, then it’s a SmartFactory, because it allows me to, first of all, to learn something that I didn’t previously know, and then the second part is to put it into a behavior in the facility. It’s a behavior of an automation system that allows me to learn what I don’t know, master what I do know, my disciplines and so on, and then ultimately translate it into some sort of a behavior in the automation realm itself that affects something directly in the factory in real time.
We have more data than we understand, correct. And I think that’s the first flaw. If we get to a point where we can learn what matters, we could probably throw away quite a bit of data that we today retain for the purposes of who knows what. So the question becomes, can you build an environment that helps us grow, learn the behavior of what we’re trying to do, and ultimately do new things that we previously didn’t think were possible? That, to me, is what it means to me.That’s what SmartFactory means to me.
So really, SmartFactory is about tying the capabilities of the software to actual factory metrics, things that improve the factory, things that improve process quality, things that improve productivity, for example. That’s really important.
**Semiconductor Category:** Panel, Smartclips
**Semiconductor Tag:** Smartclips
---
### [Empowering Manufacturing Excellence with SmartFactory MES Automation Solutions](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/empowering-manufacturing-excellence-with-smartfactory-mes-automation-solutions/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Learn from our technical leaders, David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier how SmartFactory MES automation solutions are at the forefront of advancing factory automation with fully integrated capabilities.
**Content:**
#### Transcript
Okay, so frequently we get asked this question, what does it bring, right? Essentially, if I captured it correctly, how do we begin to approach this? So, A, it helps you to optimize your factory assets, right, to throughput the key bottlenecks in your factory, how do you, you know, optimize the output from those, and then, you know, how much, you know, you can get more throughput from those things. Second, using this integration capabilities of SmartFactory allows us to react quickly to the events which are happening in the factory. So this is, broadly speaking, the factory productivity would enable.
And the second piece of it, which is what we call the predictability, that is where you get the benefit from the overall supply chain perspective. As the supply chains are becoming more complex, and, you know, you need the capability to quickly react to the customer demands and changing demands, and how you can better utilize the tools, there could be some opportunities where, you know, you could use this, you know, the predictability capabilities, the, you know, the way on how you are trying to optimize your tools to drive some energy efficient, cost saving, those kind of solutions as well. So I look at the issue of what does the MES bring to manufacturing, really from three very, very specific aspects.
It’s kind of like the three legs of a stool. The first is making things repeatedly. I’ve got something that I’m building, and I want to build it the same way every time.
So from an MES perspective, we’re talking about defining processes, making sure that we know the correct sequence of process steps, the correct tools that need to be processed, the correct process recipes, and we’re doing the same thing the same way every time. The second leg is, great, if I’m doing things repeatedly, I also want to be able to do them faster. So that’s a productivity piece.
How do I do things faster? So that means improving cycle time, it means improving time at step, it means identifying bottlenecks and reducing or mitigating the impact of bottlenecks. And then the third thing is, if I’m doing things repeatedly, and I’m doing things fast, I also have to do things well. So I have to improve the quality of everything that I’m doing, because if I’m cranking out very quickly, bad product, that’s a very, very bad thing.
I think those are the three fundamental stools. Many things come out of that. We have many systems that deal with each of those areas.
But again, that integration, how they’re all integrated, those are the three fundamental pillars. Yeah, I think from a more global perspective, so looking beyond the MES and looking beyond factory productivity, I think that at the end of the day, we need to be making decisions on automation to help our business. And, you know, our customers make money when something goes out the door and goes to their customer when it meets the requirements of the specification.
And every company wants to find different ways to measure that. Two of the key ways that our customers are trying to measure that is, am I getting closer and closer to zero defects? And secondly, I put a lot of money into my assets, my equipment, my people, my processes, am I getting the maximum effect out of those? And I think that we have to always remember in smart manufacturing, we’re doing it for a business purpose. It includes, we’ve already talked at some length about integration and the need for that integration and multiple systems working together
That would be one. The second would be to bring in those advanced technologies that can do more than we did before. And when something happens in the factory, any kind of an event, good or bad, to be able to make that decision faster, it’s going to allow you to do more and become, as Madhav said, more predictable in your factories.
For me, I see it as two things. First of all, you know, the SmartFactory enables you to basically build things that you otherwise couldn’t. They would be fundamentally too expensive to do and unsustainable to grow.
The second part of it, I think, is the human component, the learning component, which is without the person’s understanding of what’s going on, you don’t get anywhere. So you can capture that. So the technology component is, of course, then the integration that we’ve been talking about, the scalability of the platforms, the ability to essentially extend them for some reasonable cost, because there’s moments where you look at this and you say, we can’t solve that problem.
It’s too expensive, so it’s not worth it. So SmartFactory to me resolves the three fundamental things that I always look at when I’m looking at any system, the people component, the technological component and the economic component.
**Semiconductor Category:** Panel, Smartclips
**Semiconductor Tag:** Smartclips
---
### [What is an MES?
Lot tracking: the MES at run-time (Part 3/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-3/)
**Published:** July 8, 2022
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Keeping track of all the moving parts through lot tracking.
**Content:**
[ Part 2: Process Configurations ](/blog/mes-part-2/)
[ Part 4: Key Data and Metrics ](/blog/mes-part-4/)
### Part 3 – Lot Tracking
Lot tracking can be thought of as the MES at “run-time.” In part 3 of this five-part series, we look at how lot tracking represents the intersection of lots and factory equipment within the process flow. We also examine why the MES has a very different perspective of the role of lots and equipment within lot tracking.
### Transcript
Welcome to part three in this series, What is an MES? In this part, we’ll take a look at lot tracking. You can think of lot tracking as the MES at runtime. Lot is the generic name for the thing that’s being manufactured.
If you’re building a Tesla, you might call it a vehicle. But because in the context of an MES we really don’t know what’s going to be built, we’ll just call it generically, a lot. Lot tracking combines a lot with a workflow.
Without a lot, a workflow is just a static set of instructions, a template, as it were, for what should happen in manufacturing. But when combined with a lot, the workflow’s instructions cause the lot to be gradually transformed into a finished product. The lot starts at the very first step of the workflow, where you get all the information needed to correctly process the lot at that step.
Once you’re finished processing the step, you track the lot out of the step, recording all the pertinent processing information, and into the next step. Each step has its own resource and data requirements. Some steps require equipment, while others won’t.
Some steps require chemicals, while others require parts, and still others, nothing at all. Ultimately, you come to a step where you evaluate the work that’s been done so far to determine if it’s been done correctly. These steps are typically placed periodically throughout the workflow in order to minimize the amount of work completed before a problem is discovered.
As you can imagine, it’d be an expensive mistake to discover a problem at the last step in the workflow that actually occurred at the very first step. At those decision points, an evaluation can be made based on all the data collected during lot processing up to that point. If the lot’s historical processing looks good, the lot is tracked out and proceeds on to the next step in the workflow.
In some cases, though, problems might be found. Sometimes the lot can be reworked and the problems corrected with very little additional work. In more severe cases, however, the damage is irreparable, and the lot has to be scrapped.
In any case, the MES records everything that happens so that reporting and analysis can occur later. At any workflow step that requires equipment for lot processing, lot tracking can be thought of as an intersection between lots and equipment. When the lot is tracked into a step, it queues up in front of equipment, ready to process. Once the lot is processed by the equipment, it’s tracked out and on to the next step in its workflow. When there are many lots queued up at equipment, the order in which they process must be prioritized. This is called lot scheduling.
Scheduling the order of lot processing can be very complex and influenced by a number of factors, including the relative priority of the lot, how far the lot is ahead or behind its expected schedule, whether the lot is a production or engineering lot, and even seemingly arbitrary factors such as the customer to which the lot will ship. When multiple pieces of manufacturing equipment are available to process lots at a step, the lots must be distributed among the available equipment to avoid idle tools and to minimize the time lots spend waiting before processing. This is called dispatching.
Rules for dispatching which lot to which tool can also be complex and influenced by a large number of factors. Lots can be thought of as following a horizontal flow through the factory as they progress along their workflow, touching every process area of the factory. By contrast, equipment can be thought of in a vertical perspective, confined only to a particular process, and often with little or no integration with other processes in the factory.
This notion of horizontal and vertical perspectives bears more discussion. The MES is all about what it takes to keep lots moving through manufacturing. You can think of the workflow as representing the physical flow of a lot through the factory.
Lots touch multiple process areas and therefore many different types of equipment as lots progress horizontally through the factory from the beginning to the end of the workflow. But a lot touches each equipment only once during its lifetime in the factory since each equipment contributes a different part in the lot’s transformation into a finished product. By contrast, a piece of equipment touches all lots.
It’s like a vertical cross-section of the factory. The customer who’s buying the finished product from the factory typically doesn’t care about the equipment used during processing. They care about the result.
Deliver a perfect product on time and they’re happy. Keep them updated along the way about their order’s progress and they’re happy. Because the MES is all about what it takes to keep lots moving through manufacturing and keeping customers happy, the primary focus isn’t on equipment. It’s on lots, because lots become the results that the paying customers care about. That’s not to say that the MES doesn’t care about equipment.
When we looked at MES process definitions in part two of this series, we certainly saw that the MES needs to know a lot about the equipment in order to ensure lots are processed correctly. However, from the MES’s perspective, the assumption is that given the proper processing parameters, the equipment will do its thing and process the lot correctly. But that may not always be the case.
So, equipment needs some special attention from outside the MES. Attention that requires a direct connection to each piece of equipment. We’d want to know if the equipment had some type of error or alarm during processing. And we’d want to monitor the equipment’s critical processing parameters to determine if any of them went out of control beyond the specified limits. Perhaps we could even use this information stream to predict when the equipment will need maintenance. That could be a lot more efficient than an arbitrary maintenance schedule.
To facilitate all this, we’d want some type of system that’s listening to the stream of data coming from the equipment, monitoring it, evaluating it in real time, making decisions based on the data stream and sending notifications when anything goes wrong. But this sounds more like an industrial internet of things or IoT application. And that’s exactly what it is.
To optimize equipment performance, we need a real-time focus on equipment and its data stream. The equipment’s perspective is about the equipment, not about creating a finished product. The equipment’s perspective is about ensuring its processing is as precise as possible, not about whether a lot waits too long in its queue. The equipment’s perspective is about ensuring it has the necessary resources and maintenance to consistently process flawlessly, not about ensuring the finished product is shipped to the customer on time. That’s the job of the MES. Because the MES assumes the equipment is going to operate flawlessly, it has far more modest needs from the equipment.
The MES needs to know which specific equipment processed a lot at any step along the lot’s workflow. And it needs to know when processing started and finished on the equipment. And it needs to know the recipe the equipment used, particularly if the recipe used was different than what was specified in the workflow instructions.
And if a person is required to start equipment processing, the MES needs to know who that person is that started the equipment. But none of that information requires connecting directly to the equipment. And it certainly doesn’t depend on real-time analysis of the equipment’s data stream.
Because the MES’s perspective is all about the lot and its horizontal flow through the factory, the requirements regarding the vertical perspective of optimizing equipment performance is out of scope for the MES. It’s not that optimizing equipment performance isn’t important for the factory. It certainly is, but it’s just not a function of the MES.
In part four, we’ll continue our examination of lot tracking and look further into lots and equipment. The key data they generate within the MES, and the metrics that can be derived from this data.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [Bringing new levels of efficiency and quality to the fab](https://appliedsmartfactory.com/semiconductor-blog/quality/bringing-new-levels-of-efficiency-and-quality-to-the-fab/)
**Published:** October 18, 2021
**Author:** Selim Nahas, Global Process Quality Director
**Excerpt:** Selim Nahas shares insights on ways to reduce human variability and improve problem solving in the fab.
**Content:**
Selim Nahas shares insights on ways to reduce human variability and improve problem solving in the fab.
## Transcript
Hi, I’m Selim Nahas and I’m going to speak to you today about human factors in dispositioning SPC violations in front-end semiconductor industry facilities. One of the most important things to understand about this is it’s an extremely challenging thing that we ask people to do in any fab, primarily because it’s so dependent on so many different sources of information. The user has to make incredibly complex decisions in a very short period of time.
Adapting a workflow system is the right thing to do and it really lays the foundation of what you need to do in order to take the next steps and eventually get into some advanced analytics. The foundation is really designed to address the human factor associated with the SPC problem and the disposition problem. Simply put, people interpret information in different ways and when they do so, they respond in different ways.
So having a system that guides them through what to do, what are the potential sources or at least provides some element of guidance as to what it could be is highly beneficial. Most important of all is understanding that because people have varied understandings of problems, they tend to demonstrate a resolution of their own type, despite the fact that two experienced engineers might be addressing the same problem for the same process. Now having said that, it doesn’t negate that you do need to address the basics of SPC as a whole.
So having a system in place that helps you understand how you want to address a key elements such as your SPC practices, so converting your out-of-spec conditions to out-of-control conditions, getting good control limits is absolutely essential. This is how you’re going to primarily manage your signal-to-noise ratio so that you’re not inundating your staff with an excessive amount of problems to solve and essentially desensitizing the community. So having said that, you begin by putting in place and instituting the foundation and once the foundation is in place, you will find that the variability by user changes dramatically.
Once that has been achieved, then you can consider some of the more advanced analytics which we’re certainly investing and working on here at Applied Materials.
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Ready to optimize your packaging solutions?](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/ready-to-optimize-your-packaging-solutions/)
**Published:** October 19, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Overview on ways we can help you to leverage the latest trends in solving packaging challenges.
**Content:**
Overview on ways we can help you to leverage the latest trends in solving packaging challenges.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released, Popular, Semi
---
### [Optimize factory performance](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimize-factory-performance-2/)
**Published:** October 18, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Madhav Kidambi describes how to improve factory performance from the enterprise down to the factory floor.
**Content:**
Madhav Kidambi describes how to improve factory performance from the enterprise down to the factory floor.
## Transcript
Hi, this is Madhav Kidambi. Today, I will be talking about how to optimize factory performance. Today, all semiconductor manufacturers and OSATs are focused on optimizing production resources from enterprise-level, master planning to real-time dispatching on shop floor. Most of them use a disparate mix of software applications across the planning hierarchy. These tools may include open-source solutions, spreadsheets, commercial products, and home-grown applications. This results in inability to look at factory resources at a holistic basis, disruption, delays, and costs associated with having to analyze and validate changes to the WIP management policies such as dispatching and scheduling, and to build realistic what-if models for capacity planning scenarios.
From organization perspective, it creates silos using different applications, and this in turn results in sub-optimal decisions and increased cost of ownership to maintain the systems. By contrast, an integrated automation framework can offer user the biggest potential productivity gains. Applied APF platform provides software capabilities for developing, planning, scheduling, and dispatching reporting solutions.
It is currently deployed in more than 200 installations worldwide, both in semiconductor front-end and ATP sites. Recently, we have added new solver-based optimization capabilities integrated in APF platform, which will further enhance productivity gains possible from the enterprise level down to factory floor. As an example, let me demonstrate how we can utilize this new solver block to solve a master planning problem for an OSAT customer.
In solving the problem, basically there are four steps. In the first step, we are collecting the input data required for the master planning from different sources using the APF reporting capabilities. Once we have collected the input data, then we have set up the optimization problem for the master planning problem using linear programming approach.
And once we have solved the master planning problem, we have taken the output and then visualize it again through the APF reporting capabilities. And the whole problem, all the four steps, we were able to solve in a matter of minutes, and it was all automated from input data creation to visualization of the results.
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [Optimize system performance, detect and predict system failures.](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/optimize-system-performance-detect-and-predict-system-failures/)
**Published:** October 18, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Keep your factory healthy and running smoothly using run-time monitoring and predictive analytics algorithms
**Content:**
Keep your factory healthy and running smoothly using run-time monitoring and predictive analytics algorithms.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released, Semi
---
### [EngineeredWorks® increases speed-to-value for manufacturers and provides quicker deployment times](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
**Published:** October 18, 2021
**Author:** David Hanny
**Excerpt:** Gain continuous improvements in operations and construction of new factories.
**Content:**
Gain continuous improvements in operations and construction of new factories.
## Transcript
Thanks for learning about the Applied SmartFactory. Many of our friends have heard us talk about a new term called EngineeredWorks and ask, what is this new capability and how will it help me? Let’s start with a definition. EngineeredWorks is Pre-Built Automation Logic that executes on a proven Applied SmartFactory technology.
EngineeredWorks increases speed-to-value for customers and provides quicker deployment times. Now, what does that mean? For years, factories have been using products based on the smart manufacturing technologies. These will deliver more for your expensive manufacturing assets.
They have proven highly successful and are adopted in complex manufacturing. So why would we need EngineeredWorks? Let’s look at an example. Take Real-Time Dispatcher or RTD as a baseline product that has a powerful execution engine.
EngineeredWorks is the logic that is common to the industry best known methods and is pre-built for a much faster start to dispatching in your factory. The logic is proven, tested, and the source is available to you. You will get an immediate boost of manufacturing value.
Why do we need EngineeredWorks? Well, in your factory, requirements are growing and they continue to change. The support teams are shrinking and you are losing both capability and capacity. EngineeredWorks take action.
Capabilities available will take you to a full automated factory, perform dynamic scheduling and real-time dispatching, integrate with master planning and SNOP planning, and connect the shop floor to an integrated simulation environment. At the tool level, advanced process control and product diagnosis, leveraging SPC data is available with much more in R&D. EngineeredWorks are used in existing factories who seek continuous improvement and expansion of existing operations and even when you want to build a new factory.
Thanks for listening today to learn about SmartFactory EngineeredWorks and Innovation of Applied Materials.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released, Popular, Semi
---
### [Dr. James Moyne and Samantha Duchscherer discuss the relevance of data in real-time scheduling](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/relevance-of-data-in-real-time-scheduling/)
**Published:** April 12, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** This series focuses on how to achieve greater benefits in productivity and quality
**Content:**
#### Transcript
Sam: Doctor Moyne, thank you for your time and I’m truly excited to hear your insights and expertise.
James: Please call me James.
Sam: Thanks, James. Let’s begin by discussing the significance of Industry 4.0 in the semiconductor manufacturing industry. Overall, what is the relevance of data with regards to scheduling and dispatching?
James: OK. Well, smart manufacturing is a really large topic that covers a lot of different areas, not just scheduling and dispatching, but also advanced process control, predictive maintenance, virtual metrology, pretty much all of those high tech things that you see going on in semiconductor manufacturing today. And it’s starting even to get into the supply chain where we’re talking about managing the upstream supply chain as well as delivery to customers and maybe doing things like latent yield where we’re finding a problem, let’s say in an automotive facility where they’re shipping vehicles and they’re starting to fail and we have to trace this back to the chip production and what the problem is. So all of that really falls under the smart manufacturing and one of the big enablers is the machine learning, the artificial intelligence, the analytics, if you will.
Scheduling dispatch is just one of those areas. But scheduling dispatch is going to benefit a lot from the fact that a big part of smart manufacturing is the integration both vertically and horizontally. Vertically means from the sensors up through the machines, up through you know the station controllers, the manufacturing execution systems and even the ERP. Horizontally, we’re talking about integration from the upstream supply chain through the four walls of the fab and then downstream into the customer base.
And so, if you think about it, traditional scheduling and dispatch basically took an order from an ERP and then it would go down to the manufacturing execution system. It would figure out how to allocate the resources to deliver on that order, OK. And it would do the scheduling and dispatch. And then it would have rules like if this machine starts underperforming, then maybe switch over to this other machine. Or you know when there’s when the queue length gets greater than X at a particular machine that maybe we want to make a change there.
It’s largely rules based and it’s largely kind of looking at the factory as a set of rules within the four walls. OK. It doesn’t really look too much at how is this machine performing in terms of it’s run to run control or it’s fault detection or it doesn’t really look at what’s the upstream supply chain doing. Are we going to run low on this particular component, which if we overdrive this piece of equipment, suddenly we won’t have this equipment available? And it’s definitely not looking downstream at the customer base saying is there any push back from the customer like we’re not producing good parts?
So if you can think about smart manufacturing in the future, all of these things are going to be integrated horizontally and vertically, and that is driven by data and data interfaces. There’s a lot of issues that have to be addressed though.
First of all, the data itself, right? You have to get the data, you have to consolidate the data. Data that is normally used for things like fault detection down at the equipment level will not have to be consolidated with data that might be coming from the supply chain, because maybe you’re using that data together to solve a problem which might impact your scheduling.
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [What is an MES?
All about process configurations (Part 2/5)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/mes-part-2/)
**Published:** July 8, 2022
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Taking a deep dive into MES configurations.
**Content:**
[ Part 1: First Principles ](/blog/mes-part-1/)
[ Part 3: Lot Tracking ](/blog/mes-part-3/)
### Part 2 – Process Definitions
Figuring out the best way to build the products in our factories is hard enough, but communicating that so the instructions are clear, the results are what was intended, and the process is repeatable is an entirely different challenge! In part 2 of this five-part series, we take a conceptual look at how process flows are defined within the MES. We also take a deep-dive into MES configurations and how they’re interrelated and have the potential to be re-used within the MES.
### Transcript
Welcome to Part 2 in this series, “What is an MES?” In this part, we’ll take a deep dive into MES process definitions, where all the configurations happen, and where the work of the factory is planned in advance.
As you might expect, there are all sorts of low-level configurations that are prerequisites before you can do the meaty work of creating process definitions. But I find that jumping in here, you quickly get lost in the weeds. There are just too many seemingly unrelated pieces and parts and nuts and bolts with no context of what they’re used for or how they all fit together.
Instead, I’d like to jump in at the other end and start with what most manufacturing folks are really interested in: defining the cookbook recipe for how to build a widget or whatever it is that they’re building in their factory. I say cookbook recipe because that’s a good way to think of how manufacturers define the process of how they build what they build in their factories.
A cookbook recipe is simply an ordered list of steps for creating the perfect cookie or whatever. And within each step, it defines the necessary ingredients (like flour, eggs, butter, sugar), the required resources (like mixing bowl, large spoon, oven), and a set of specifications (like preheat the oven to 350 or bake for 10 minutes). A process definition is exactly the same thing— an ordered list of steps that defines the process for how to manufacture a specific item.
Take an example from the semiconductor industry. What you see here might be the beginning of a typical sequence of steps to build some type of computer chip. We start by allocating silicon wafers, that’s the starting raw material required to build computer chips. There are typically 25 of them that all get processed together. In the end, there may be scores or hundreds, or even thousands of individual chips that are created on each one of those wafers. But in the beginning, all 25 of them are processed together.
In step two, we scribe a unique identifier onto each of the wafers so we can keep track of how it was processed throughout manufacturing. In step three, we clean the wafers, because scratching the IDs on them is a pretty dirty process. In step four, we apply a thin film of what’s called photoresist on each wafer.
Building a computer chip is done in multiple layers, with each layer defining a part of what eventually becomes the electrical circuitry of the chip. Each layer imprints a picture of that part of the circuitry onto the wafer and, kind of like a Polaroid instant camera, that picture has to be printed on something. Here, that something is called photoresist. In step five, we transfer the pattern of that part of the circuitry onto the wafer using a machine called a stepper.
You can think of it as a very large, very expensive camera. Just as in any photo darkroom process, once you take the picture, you have to develop it, and that’s what’s done in step six. The pattern that was exposed onto the wafer is developed, leaving the image in photoresist on the wafer.
But is the image correct? Are there any smudged or smeared parts? Did a glop of something fall onto it? In step seven, the pattern that was printed onto the wafer is inspected to make sure it’s perfect, because of course if it’s not perfect, you’ll get a lot of defective computer chips in the end.
Well, there are many more steps in a computer chip manufacturing process, and this is just one example from virtually an infinite number of manufacturing processes across different industries. But you get the idea. We’re talking about an ordered sequence of steps that defines the correct manufacturing process from beginning to end.
Just as there are different opinions of what to call the MES, there’s also lots of variations as to what to call this ordered sequence of steps. We’ll call it a workflow. Some call it a process flow. Within the semiconductor industry, it’s often called a traveler. Other industries call it a route or a run card. The idea is the same, though, defining the manufacturing process as an ordered sequence of steps. To manufacture your widget correctly, you’ve got to complete all the steps in the correct order. You can’t add anything. You can’t leave anything out.
What happens at each step in the workflow is where things get really interesting.
First, we need to define the resources needed at the step. This includes the required equipment and the parts required at the step. Think screws or resistors or an LED display. Remember, this could be for any kind of manufacturing. For the semiconductor industry example we saw in the last slide, the parts were the wafers added in the very first step. But because an MES should handle pretty much any kind of manufacturing, it’s reasonable to expect parts could be added at any point in the manufacturing process.
Another resource is chemicals. In biotech, for example, this could be a liquid or powder that’s added at that part of the process. In our cookbook example, this would be flour or sugar or butter.
And finally, documents can be written procedures like how to operate the equipment or even media such as a video showing how to assemble the parts used at the step. Documents can be anything that helps make the manufacturing process more reliable.
We also need to define some data at the step; some of this is in the form of input information and some is output summarizing the processing completed at the step. First, we need to define specifications.
Specifications can be any type of information that’s known before manufacturing begins for the item being built. This might be process specifications like no more than three small defects are allowed, or other information like the customer to whom the item will be shipped. Next, we need to define the runtime data we want to collect during manufacturing.
For example, we definitely want to record the equipment on which the item was processed at each step. And we definitely want to record if some type of substitution occurred. Perhaps an alternative part was used because the specified part was out of stock. Next, we might want to automate some calculations on the data we’ve collected.
For example, imagine you’re building a machined part and you’ve got a specification that defines a target value of 5.1 centimeters for a critical dimension of that part. You also have a specification that says that the actual value after machining can’t be more than a tenth of a millimeter away from the target value. During manufacturing, once you’ve machined the part and measured the critical dimension, you’d collect the actual measured value and perform a calculation to determine how far away it is from the target value. Well, then you’d want to evaluate the calculated value against the specification (you know, the one that says the actual dimension can’t be more than a tenth of a millimeter away from the target).
The result of that evaluation might lead you to one of several possible next steps in the workflow:
- The default path if the part was machined to the correct dimension
- A rework path if the actual dimension of the part is still too big (not enough material was removed and we can still remove a little bit more to make everything fine).
- A scrap pass, if the actual dimension is too small (too much material was removed).
Together, the resources and data defined at a step clearly define what and how processing takes place at the step. But there’s still more to consider. Earlier, I suggested that jumping into low-level MES configurations only gets us lost in the weeds because there’s no context for understanding how things should work together. Well, now we have that context, so let’s look at some of those MES configurations and see how they fit.
The equipment used for processing at a step is often one of the most important process definition resources, so we’ll start by looking at equipment configurations. A piece of equipment has recipes that are low-level instructions for how to operate to achieve a specific process outcome. Some people call them programs. A recipe contains a series of specifications, in this case we’ll call them process parameters, that define the details of processing. This could be, for example, a temperature value or the length of time heating should occur. As it turns out, equipment also has specifications, typically called equipment constants, that define the equipment’s setup and calibration configurations.
So, we’ve got specifications for equipment and specifications for recipes, and we’ve already seen that we’ve got specifications for the steps in our workflow. Equipment also have consumables and durables, which, as it turns out, are a lot like the chemicals and parts resources that we’ve seen before. A consumable is anything that’s consumed or used up by the equipment during processing (i.e., your car consumes gasoline).
At the resist coat step in the workflow example, the equipment used at that step consumes photoresist. It’s used up during processing but, unlike the chemical resource, it doesn’t become part of the finished product. So, it’s similar, but a bit different.
A durable is something that’s used by the equipment during processing, but it’s not used up, at least not immediately. The tires on your car might be considered a durable. The car uses them while you’re driving, but they wear out at some point and need to be replaced.
At the first pattern step in our workflow example, the equipment used at that step, the stepper, uses a photomask as the source of the pattern that gets transferred onto the wafer. Photomasks can be used for a long time, but they do wear out eventually. It’s used during processing, but unlike the parts resource, it doesn’t become a part of the finished product.
So again, it’s similar, but a bit different. Equipment also requires maintenance, (just like your car’s scheduled maintenance). We have to define a schedule for durables as well. Durables need to be cleaned periodically, or repaired, or at least checked to see whether they’re still good enough to use.
Maintenance also has parts and chemicals required to perform the maintenance that have nothing to do with production processing. Think of the parts and chemicals for your car when you do an oil change. For manufacturing equipment, there may be filters, lubricants, or gases that are necessary for the equipment’s proper operation.
As you might expect, there can also be documents related to the maintenance. For example, there are documents explaining the procedure for performing the maintenance or the equipment manufacturer’s recommendation for the frequency of maintenance. Documents pop up in a lot of other places, too. Parts and durables often have related documents, perhaps CAD drawings or installation instructions. Chemicals and consumables have documents, too. Think of the material safety data sheets that are required by law in every manufacturing facility.
Equipment also has a location within the factory; this can be really helpful. If there’s maintenance or construction work scheduled within the factory, knowing the location where the work is going to take place can tell us the specific equipment that may be impacted. Location is also very helpful to know when coordinating emergency activities within the factory.
And location pops up elsewhere, too. It’s often specified for parts and durables. You’d likely want to know where a specific part is in the warehouse, or if a durable item schedule is flagged as needing to be cleaned, where that durable is in the factory. Location is often specified for chemicals and consumables as well, and these are usually stored in portable containers. Location is helpful so you won’t have to go all over the factory searching for the part or chemical or durable you’re looking for. Knowing the location can save lots of time.
Well, maintenance can also have a workflow because we need to know what’s happening, when, with any maintenance. We need to know how far off in the future the maintenance needs to be started, if it’s been started; we also need to know when it’s expected to be finished. If it’s due now but hasn’t been started, we need to know how much of a grace period we’ve got before we start getting some politely annoyed text messages asking why we haven’t started the maintenance yet. And if it’s really overdue, we need to know how long we’ve got before the production staff just shuts down the equipment. The maintenance workflow can manage all of that.
Durables can also have a workflow for many of the same reasons. Feeling a bit overwhelmed? Well, there’s definitely a lot to take in. For me, if I stare at this long enough, I start to go a bit cross-eyed and it begins to look like a piece of contemporary art.
The really interesting news here is that we’re not just describing the configurations of a piece of manufacturing equipment. We’re really describing the configuration of any asset. The factory’s air handlers? Sure. Electronic meters used for calibration? Absolutely. A conference room? Why not? The same characteristics apply to all these, so we should be able to apply the same behaviors and even data structures to them all while gently tailoring user interfaces based on specific use cases. Thinking of resources like this in the broadest possible sense provides possibilities to organically grow future MES functionality based on the problems they solve in manufacturing. We could go into more depth about configuring other resources, including how we might even import resource definitions for things like parts from a company’s ERP system, but I think you’ve got the picture. There are a lot of configurations in an MES and a lot of them show up in more than one place.
The MES should treat process definitions and configurations as an integrated system, making things easier for users by defining common interfaces and behaviors across the system and sharing common data throughout the system.
In part three, we’ll take a look at lot tracking, the MES at runtime.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [Beyond the MES: Fly. (Part 2/2)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-2/)
**Published:** March 15, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** Advanced capabilities and MES provide the intelligence that is key to the ‘lights out’ factory
**Content:**
[ Part 1: Crawl. Walk. Run. ](/blog/beyond-mes-part-1/)
### Part 2: Fly.
The MES ideally provides everything needed to automate steady-state manufacturing. But in the ‘lights out’ factory, all forms of non-standard processing need to be automated, as well. In Part 2 of this multi-part series, we’ll look at some of the enhanced capabilities that can be integrated with the MES to provide manufacturing intelligence that leads us closer to the ideal of the ‘lights out’ factory.
### Transcript
In part one, we used the metaphor crawl, walk, run to describe how the needs of a factory evolve over time. But that metaphor doesn’t get us quite as far as we need to go to that apex of manufacturing efficiency, the lights-out factory. So let’s extend the crawl, walk, run metaphor to include fly.
Fly is the lights-out factory, or at least something approaching that. Everything within this factory is fully configured and automated. Process definitions, tool control, optimized production scheduling, product movement throughout the factory, data collection, and specifications validation.
But that’s only what’s required for standard steady-state processing. Non-standard processing also needs to be automated. What happens when product measurements are out of spec? Can the product be reworked, or does it need to be scrapped? Is this a one-off event, or is it a systemic issue? How do we prevent this from happening to follow on product, and how do we identify and correct the root cause? And what about non-product processing? How do we automate processing for maintenance and qualifications, or engineering experiments, or R&D process development? In the lights-out factory, not only does non-product processing need to be automated, but also the response to that processing, such as what to do when a tool qualification fails.
FLY is where intelligence becomes necessary. If we can use SPC charts to detect when a process is going out of control, we should be able to use that data to intelligently and automatically tune the process recipe for relevant upstream process tools. If a process tool goes out of service unexpectedly, we should be able to intelligently reschedule product to run on other qualified tools to prevent excessive delays in late product shipments.
If a defect is detected on product in a manufacturing line where, say, only one in 10 lots is inspected, we should be able to intelligently determine the source of the defect, then identify the lots processed on either side of the initial problem lot, and automatically inspect them too. Intelligence allows us to dynamically automate the things that can’t be planned and coordinated in advance. Let’s step back for a moment and recall a rather dated term, computer integrated manufacturing, or CIM.
The notion of computer integrated manufacturing was introduced in a 1974 book of the same name by Joseph Harrington, back before computers were widely available in manufacturing, or anywhere else for that matter. In its highest form, computer integrated manufacturing envisioned what we now call the lights-out factory. The key attribute of the CIM system is that it should control every part of the production process.
That’s a much larger scope than how we’ve defined the modest capabilities of the MES. And yet, it leaves a lot of room for how additional capabilities can be layered onto the MES to create a total manufacturing solution. It also leaves a lot of flexibility for how to eventually get to the lights-out factory, even if you’re starting as a small manufacturer that does everything by hand.
Clearly, the MES is at the heart of the CIM, its foundation. A properly configured MES defines and coordinates all processing within even the most basic manufacturing. Additional capabilities can be added to and integrated with the MES over time to enable richer functionality in the CIM system as a manufacturer’s needs evolve.
However, integrating additional functionality within the MES is not a trivial task. Integration is the key word. Each piece of functionality added has its own unique integration requirements.
These glue layers are necessary to make the pieces within the CIM act as an integrated system. But these glue layers are difficult, time-consuming, and costly to implement. That is, unless you have a CIM system that provides the functionality you need pre-integrated. Ideally, you also want a path forward to add additional capabilities as your manufacturing needs grow all the way to the lights-out factory, and all pre-integrated without the need to implement custom glue layers.
The Applied SmartFactory CIM provides just such a solution. Start with the SmartFactory MES to get your factory up and running at the crawl stage. Then, when your factory is ready to walk, add tool automation, data collection, and runtime spec validation, along with SPC for process monitoring.
When your factory is ready to run, add the material control system to coordinate automated product movement throughout the factory, and production scheduling and dispatching to optimize the product flow. Finally, when your factory is ready to fly, add run-to-run control to dynamically tune process recipes based on metrology results, and build machine learning models for artificial intelligence systems to improve defect detection and product yield. Everything is pre-integrated, so no glue layers to implement, just configurations to tailor the systems for how your factory works.
In Part 3, we’ll rewind to take a look at a hypothetical factory at the crawl stage, and look at how the MES is the key system to define and control manufacturing, and at the heart of the CIM. Then we’ll fast forward a bit and look at some of the CIM capabilities that allow our hypothetical factory to walk.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [Beyond the MES: Crawl. Walk. Run. (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/beyond-mes-part-1/)
**Published:** March 16, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** The MES provides a critical foundation for the semiconductor factory as needs change over time.
**Content:**
[ Part 2: Fly. ](/blog/beyond-mes-part-2)
### Part 1: Crawl. Walk. Run.
Factories are evolving beasts. As factories evolve over time, their needs change. The MES, as the foundational factory system, must be able to grow with the factory to provide new capabilities as the factory needs them.
In Part 1 of this multi-part series, we’ll take a look at how factories commonly evolve, and at how the MES can evolve to provide an integrated manufacturing system.
#### Transcript
The Manufacturing Execution System, or MES, is the operational backbone of many factories. But if you get 10 people together in a room and ask what an MES is, you’ll get 10 different answers. Yes, typically everyone agrees that you define process flows in the MES, and you track lots in the MES.
But this is where disagreement begins. What else is in the MES? It’d be great to have a system that helps manage and maintain equipment. And we’d want to have some way to track process quality during manufacturing, perhaps a statistical process control system.
Maybe we’d want something to coordinate the physical movement of product throughout the factory, like an automated material control system. And, of course, we’d want some kind of reporting system that would allow us to see what’s happening in the factory and do some analytics on all the data the MES generates. Ultimately, the source of disagreement about what should be in an MES is about what capabilities are needed in an MES, because needs vary for each factory.
If you’re in a small factory where product is manually moved from process to process, you might reasonably think, why would I need an automated material control system in my MES? But the needs of a large, highly automated factory would be completely different. There you might think, I absolutely need an automated material control system, and I want it powered by artificial intelligence algorithms, backed by a comprehensive machine learning model based on years of real-world training data. Certainly, these are factories with very different needs, but this doesn’t help us determine the capabilities that should be in an MES.
As you might expect, each stage in a factory’s life requires more capabilities within the MES to meet the increasing demands of manufacturing. There’s a familiar way to think about a factory’s evolving needs. Crawl, walk, run.
Crawl is the new factory. Perhaps it’s a small factory that’s just starting up, or perhaps it’s a brand new, multi-billion dollar high-tech greenfield factory. In the crawl stage, things are just beginning to come together.
The building is largely complete, the support systems and utilities are mostly turned on, the equipment is generally installed, the staff is beginning to come on board, but production hasn’t started yet. This is a factory that has modest needs. MES? Yes, please.
AI-powered systems to optimize production? Thanks, but no, not just yet. We need to get a basic process up and running first. Walk is the factory that’s been around for a while.
The building and support systems are in place, processes are well-defined in the MES, tools are qualified and running production, the staff is working as a team, and the factory is shipping finished product to its customers. This is a factory that has the basics down and is looking for new capabilities to improve yield, cycle time, and other factory performance metrics. MES? Yeah, been there, done that.
SPC system to monitor process quality? Of course. Tool automation to ensure proper processing? Certainly. Reporting systems to help keep production moving? Definitely.
Run is the factory that’s working to squeeze out every last bit of efficiency possible and looking for advanced capabilities in their MES to support this. These factories have mature operations and high capital equipment costs and commonly have 24 by 7 production to maximize utilization of their expensive assets. Their goal is to maximize efficiency to drive high volume at high yields and reduce the unit cost of their products.
MES? Yes. And? Augmented by lots of reporting, analytics, and real-time notifications. Tool automation? Absolutely. Controlling every tool and automating process recipe download and tool data collection as well. Automated product transport? Yes, of course. Throughout the entire process flow to ensure product is ready to go when tools are ready to process.
So what’s left? What other capabilities are needed to reach the holy grail of the lights-out factory? In a word, intelligence. In part two, we’ll extend our crawl, walk, run metaphor to include one more item. Fly.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi
---
### [AI: Revolutionizing Factory Automation and Shaping Our Experiences](https://appliedsmartfactory.com/semiconductor-blog/smartclips/panel/ai-revolutionizing-factory-automation-and-shaping-our-experiences/)
**Published:** June 6, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Join our technical leaders David Hanny, Selim Nahas, Madhav Kidambi, and Dan Meier as they explore how AI is accelerating the next generation of factory automation and transforming our daily lives.
**Content:**
#### Transcript
So, I want to turn the focus a little bit to AI. You touched on it there for a moment and talked about the complexity of the environment that just keeps growing. I met with a customer recently and we were talking very, very briefly about AI and the customer quipped, I don’t need AI.
I need a ‘why’. I need something that tells me ‘why’ something is happening. I need something that helps me to solve those business problems in manufacturing.
How many of you were surprised by how fast ChatGPT came on the market? Yeah, right. I mean, we all knew something was coming, but did you expect it to be that far along? It was the fastest product launch and ramp of any technology product ever. Yes, yes.
So, a little prediction here. If something comparable to that was to happen in the manufacturing world, that would be a vast departure from anything on the market today. There’s nothing like it today.
The question is, who’s poised to do it? Is there anybody on the field that is actually positioned to do it? Personally, biased? I think we are. Because if you want to, so there are companies in the past that had this idea that you could do this, right? Like they had this notion that we can do anything. We can look at data, mine it and use AI sort of principles to mine it.
The problem was they skipped the fundamentals, which is what is in that data? What’s the clarity of the data? What’s the resolution of the data? What is the meaning of the data? But if we wanted to go to some place where we’re really going to depart the performance of a current facility, that’s not going to happen unless the foundation is really solid. And in order to do that, you have to be capable of providing a total CIM.
So those capabilities are there. Now, what SmartFactory is enabling is also connecting. So it helps, for example, you know, we can enable the robots to drive or take those actions. So that’s the unique thing what SmartFactory does, is it can enable the AI devices, AI-based devices to take actions in the factory.
And that we are seeing today, right? And then there’s a second set of machine learning-based capabilities where, you know, where there are various applications you know, related to how you kind of, you know, detect some pattern or predict some pattern. So again, there have been a lot of, you know, progress that has been made. And where SmartFactory again brings the kind of a unique value is earlier what we talked about is this integration capability where we can take the data from factory productivity systems, from MES, from our, you know, E3 platform, and use that to make, you know, better machine learning model.
So we’re really talking about AI in many ways in a very specific model, right? An AI to manage wafer yield, for example, an AI to manage productivity or cycle time or throughput or tool loading, for example, right? And I think what we’re, within the SmartFactory software suite, what we’re doing today is building a foundation for the AI of the future in many ways. Yes, we have to build AI into our different components. But at some point when we get to the next step, artificial general intelligence, we can make an AI that really controls the whole factory.
And to me, that’s what’s really exciting as I look forward to the next five to 10 years in our trajectory of where we’re going with things. It’s really heightening productivity to the maximum level. And I think that we get to that point, we’re doing that at point levels within the factory today with our different systems, but to be able to take all of that and integrate that with a factory level AI to be able to distribute and control all of those individual factory components, that’s where we can do much with very, very little.
It’s exciting to think about.
**Semiconductor Category:** Panel, Smartclips
**Semiconductor Tag:** Smartclips
---
### [The Point of Truth for Runtime Recipe Control](https://appliedsmartfactory.com/semiconductor-blog/quality/runtime-recipe-control/)
**Published:** April 29, 2022
**Author:** Eric Warren
**Excerpt:** The latest release of SmartFactory Recipe Management offers better data synchronization options for runtime recipe control.
**Content:**
Managing thousands of recipes is a fundamental requirement of recipe management (RM). To provide a foundation of recipe control in a facility, manufacturers must synchronize information between their MES and equipment. Today RM systems must accommodate individual user organization preferences and provide flexible configuration options. Some tool owners, may store recipes in a single folder on their equipment. Others may create unique folders and sub-folders based on technology, products, or unique conventions, which change over time. Regardless of the method, synchronization of recipe name and location, as defined on equipment, must occur at runtime.
To better manage the synchronization of data between the MES and equipment, Applied SmartFactory® Recipe Management System (RMS), version 2.1.0, powered by the Applied E3® framework, is tailored for equipment recipe body and recipe parameter control. This new release continues to build upon high volume manufacturing proven methodologies, including recipe resolution modes for fully qualified recipe mapping.
### Mitigating Cross-application Changes
With SmartFactory RMS, version 2.1.0 released in April 2022, our vision is to use recipe management as the “point of truth” for runtime recipe control and mitigate cross-application changes. Now, a short form recipe name (e.g., Recipe\_Product\_A) is the common identifier, yet at a system level, the *recipe name **and** directory* (as defined on the equipment) dictate the fully qualified recipe:
**Recipe Directory + Recipe Name (short form) = Fully Qualified Recipe**
In MES-centric environments, qualified recipes are included in MES route definitions. While effective, this method may require changes in both the RM system and MES if either the recipe directory or recipe names are modified on the equipment. The challenge is that organizationally, people responsible for creating and modifying recipes on equipment and those responsible for MES routes are often on different teams with different execution timelines.
In such cases, our RMS provides better synchronization between the MES and equipment by enhancing and expanding its runtime resolution modes and providing external short form conversion modeling and external context resolution.
- **External Short Form Mode.** External short form mode inherits the short form recipe name from the MES definition and provides a recipe directory conversion modeling interface in RM to generate the fully qualified name. Decoupling the recipe directory from the MES definition enables organizational responsiveness, such as adding or modifying folder names on the equipment based on product changes or when introducing new technology.
- **External Context Resolution.** This feature enhances flexibility by using MES contextual information to resolve the fully qualified name at runtime. For example, a key combination of Operation + Equipment + Product could be modeled to obtain the appropriate recipe (e.g., Recipe Directory + Recipe\_Product\_A). Decoupling both the recipe directory and recipe name from the MES route definition enables flexibility for individual organizational preferences.
In either mode, SmartFactory RM defines and resolves mapping fully qualified names to minimize MES route modifications. This, in turn, enables RM teams to operate independently, while maintaining synchronization for runtime recipe control.
To learn more about SmartFactory Recipe Management 2.1.0
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Newly Released, Semi
---
### [设备回线自动化提高设备效率](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
**Published:** October 23, 2023
**Author:** Seong Hoon Lee and Boon Guan Lim
**Excerpt:** SmartFactory 300works™ 可帮助减少设备停机维护期间经常被忽视的因素
**Content:**
制造商总是希望最大限度地提高工艺设备的可用性，并尽量减少停机时间， 这在资本设备成本极高的半导体行业尤其如此。
设备在进行停机维护期间，一个经常被忽视的因素是维护后重新鉴定工艺设备所需的时间。 加快维护后的鉴定过程可以减少整体设备维护所需的停机时间，并提高工艺设备的可用性。 SmartFactory 300works 为这一过程的自动化提供系统化的方法。
举一个简单的例子，设备工程师在预防性维护后需要运行监控晶圆来重新鉴定设备。 这通常是一个手动过程，工程师在这一过程中需要：
- 确定所需的鉴定流程
- 确保所需的晶圆可供使用
- 从存储区提取所需的晶圆
- 处理监控晶圆
- 评估结果并决定如何配置工艺设备
这在概念上很简单，却是一个耗时的手动过程，特别是在出现意外情况时，例如发现没有所需的晶圆或晶圆尚未做好使用准备。 这大大降低了工厂的效率。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/factory-efficiency.jpg)
300works 通过设备回线自动化软件包实现了这一过程的自动化。 根据现场部署的工厂自动化程度，制造商可以将后期维护成本和重新鉴定时间减少一半或更多。
图 1 显示了如何在设备回线自动化软件包中实施与预防性维护相关的监控晶圆工艺流程。
以下说明了 300works 设备回线自动化软件包如何通过以下方式改进这一过程： - 找到合适的监控晶圆，并确保它们已做好使用准备
- 将工艺配方下载到工艺设备并启动工艺
- 上传加工结果
- 自动做出处置决定，并将监控晶圆放回存储区，以备再次使用
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/automated-tool-recovery-workflow-2.jpg) 图1：设备回线自动化软件包工作流程
自动化维护后重新鉴定的总体影响可能是巨大的，尤其是对于瓶颈设备而言。
我们的 300works 设备回线自动化软件包工作流程可确保使用正确的重新鉴定工艺流程并监控晶圆，并以一致的方式进行重新鉴定处理。 它还加快了重新鉴定过程，减少了设备停机时间，使设备迅速恢复生产运行。
有兴趣了解更多信息？ 点击[此处](https://appliedsmartfactory.com/zh-hans/connect/)获取更多信息！
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, Newly Released
---
### [通过更好的数据可视化，提高运营效率](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/data-visualization/)
**Published:** November 21, 2022
**Author:** John Robinson
**Excerpt:** 利用 SmartFactory Material Control 和 APF Reporter，为数据驱动型决策制作简单、一致且具有视觉吸引力的图表。
**Content:**
在我之前担任自动化物料搬运系统 (AMHS) 经理和自动化技术开发负责人期间，我参加过晶圆厂的“运营总结”会议，每位模块负责人需提出影响晶圆厂运营的相关问题。 在那些会议中，当处理三家不同的半导体公司的工作时，我发现这些不同的晶圆厂之间的一个共同之处——数据 *可视化的一致性问题。* 他们的数据存在一些共性，其中包括晶圆厂 30 天报告，显示每小时搬送 (MPH)、总搬送时间、随时间推移的 Paretos 警报以及按 bay 排序的存储利用率。
本文着重介绍 30 天的 AMHS 报告。 目的是在一张 30 天趋势价值图表上，一目了然地看出共性和异常情况。 图 1 是我在大多数晶圆厂看到的典型的图表报告。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure1-30-day-dashboard.jpg) 图1： 典型的30天趋势的图表报告，显示每天的搬送时间和搬送计数
图 1 中的图表报告由 x 轴、右轴和左轴构成，具体定义如下。
- 底部的 **x 轴**表示回顾的时间，在本例中为 24 小时搬送统计数据的 30 天趋势。
- **右轴**显示通过消除异常值（顶部 5% 的时间）得到的平均搬送时间和第 95 百分位数搬送时间。 这在图中用两条折线表示，是 AMHS 优化中最基本的 KPI 指标。 它是工厂中存储优化效率和搬送的派工产能的滞后指标。 当然，关注的重点放在搬送时间趋长的异常值上。 这些趋势通常需要在运营总结会议中向管理层解释说明。 异常值有时与即将上线的新设备或 AMHS bay 相关，通常表明需要更好地组织上游存储地点或改进排程逻辑，以确保物料存储在更靠近设备的地方，从而缩短搬送时间。
- **左轴**显示每 24 小时总搬送量 (MP24)，用一个叠加图显示三种搬送类型：储料机-储料机、储料机-设备以及设备-设备。 叠加的总数表示在 24 小时内的总搬送数。 叠加图是有趣的可视化数据，因为我们可以从中获取随时间推移的搬送类型趋势的线索。 例如，有些日期送入存储的量明显增多，而另一些日期向设备的搬送量更大。 这些趋势通常与工厂特定的里程碑相一致，可以根据需要突出显示。
解释这些图表元素——MP24、日均搬送时间以及 30 天趋势——十分重要，因为这样我们就能意识到它的价值。 例如，某位晶圆厂经理可能想知道，为什 **19-Sep** 么与其他日子相比 ，9 月 19 日的平均搬送时间飙升，这里您可以向运营团队回答具体原因，比如新产品导入 (NPI)、初制晶圆运行新测试或新 bay 上线。 通常，第 95 百分位数搬送时间与平均搬送时间之间的差距还可能表明，在特定日期可能出现了瓶颈，或某些偶发干扰导致了此事件，这可以在每日趋势中查看。
如果我们同意此图表具有价值，并普遍用在大多数运营总结中，那么接下来我将展示我们如何在 CLASS MCS 5™ 中创建此图表，然后用 APF Reporter 将其可视化。
### 第1步 – 搬送分析
我们需要首先定义什么是搬送，并从 AMHS 的角度清楚理解构成一个搬送的所有要素。 图 2 显示了在一座 300mm 半导体工厂中进行搬送的详细拆解——从最初申请到搬送完成。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure-2-move-anatomy.png) 图 2： 搬送的拆解和事件触发要素
在图 2 中，**总搬送时间**是发生的几个事件的合并，尤其是等待分配、检索和搬送时间的总和。 另一个关键点是搬送的定义。 搬送从**请求**制造执行系统 (MES) 搬送开始，以天车 (OHT) 的**搬送完成**事件为结束。 这里要特别指出的是，从储料机到设备的搬送是一次整体层面的**完成搬送**（从 MES 的角度来看），同时意味着我们会有两次微设备搬送（一次从储料机，一次从天车）。 区分 MES 搬送和设备搬送是我们如何在物料控制系统 (MCS) 统计数据表中存储此信息的关键所在。
### 第2步 – 数据组织
接下来便是这一切的秘密武器——数据组织。 CLASS MCS 5 数据存储结构（如图 2 中的搬送拆解示意图所示）将全部包含在一个名为 **SCARMOVE\_SUMMARY** 的表格中。 此表列出了我们客户用户组给出的意见和反馈，其中我们达成统一的存储组织策略。 该表格类似于如图 3 所示的表格。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure3-scarmove.png) 图3： SCARMOVE SUMMARY 表示例
此表会列出搬送的所有相关元素：MES 请求时间、载具分配时间、到达时间、搬送时间、命令 ID 等等。 需要构建这类图表的工厂数据分析师很快就会意识到其价值。 一份表格即可集中列出搬送拆解步骤中的所有数据，是 SmartFactory Material Control (CLASS MCS 5) 的独特成果。
### 第3步 – 数据可视化
现在是精彩亮相的时刻——完成数据的可视化。 有了所有经过适当定义、归类并存储在一份数据库表格中的搬送要素，我们现在能够利用 CLASS MCS 5.14 版本的 MCS 搬送时间报告模板，使用 APF Reporter 工具。 APD Reporter 模板在设计时已经考虑了我们的用户，考虑到他们需要参加的运营总结会议。 图 4 显示了使用 APF 创建的示例图表。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/09/figure-4-delivery-time-report.png) 图4： 使用 APF Reporter 工具创建的 MCS 搬送时间报告
近年来，我们的客户一直在寻求这项报告功能，现在，用于创建此图表的 APF 模板将于 2023 年 3 月随 MCS 5.14 版本一起提供。
准备好联系我们，了解更多有关此图表或其他图表的信息以提高生产效率吗？
[ 联系我们 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Newly Released
---
### [利用经行业验证的交钥匙 CIM 解决方案实现关键的工厂 KPI](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/cim-solution/)
**Published:** July 21, 2022
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** 使用我们的 SmartFactory CIM 解决方案在您的整个工厂生产领域中集成自动化功能。
**Content:**
### 访谈
Bing Wang，CIM 解决方案经理，讨论如何利用经行业验证的交钥匙解决方案“应用材料 Smartfactory™ CIM 解决方案”实现关键的工厂 KPI。
我们的“洞察力”博主 Todd Snarr 与应用材料自动化产品部的 CIM 解决方案经理 Bing Wang 进行了一场座谈，探讨交钥匙 的CIM 解决方案如何能够加速提升半导体晶圆厂的良率和产品产出，同时缩短生产周期和降低成本。 成功部署这种交钥匙解决方案的秘诀是什么？
洞察力：首先，在半导体的背景下，您如何定义“计算机集成制造”？
Bing: 这只是一种利用计算机软件应用程序来控制、 自动化和记录从前道晶圆制造到后道封装、测试和包装的整 个半导体制造过程的方法。
洞察力：CIM 解决方案提供什么价值？或者说，能够提供什么价值？
Bing: 如果实施得当，CIM 交钥匙系统可以帮助制造商实现快速系统部署，更快提高生产效率，这不仅对那些旗下现有工厂在成本、质量和生产周期面临更激烈竞争的公司来说尤为重要，对新建工厂经验有限的新公司来说也尤为重要。 对于新晶圆厂来说，时间非常宝贵；部署完全集成的 CIM 是帮助这些晶圆厂更早实现生产第一块硅和量产目标以满足技术和商业需求的途径（参考[ 拉近和实际生产的距离](/zh-hans/blog/bringing-production-reality-closer-to-target/?hilite=driving+curve)）。
洞察力：在您看来，除了部署和速度之外，半导体晶圆厂在采用 CIM 时还经常需要应对哪些其他挑战？
Bing: 对于今天的半导体晶圆厂，我们通常看到制造自动化分布在四个主要领域：制造执行、工艺质量控制、生产效率和供应链集成。 跨晶圆厂的许多区域并以一种有凝聚力的方式连接和集成所有这些制造领域，是部署中最耗时的方面之一。 这可能需要 6 到 12 个月的时间，因为每个晶圆厂及其产品都不同，这需要从一个工厂到另一个工厂进行大量的定制。 此外，还必须花费相当多的时间来验证晶圆厂产品所需的极其复杂的制造过程。 半导体晶圆厂在实施和运行 CIM 时面临的另一大挑战与数据消费有关。 半导体自动化系统依赖于从不同CIM组件集成的大量数据——与订单、产品、过程步骤、设备传感器和操作人员相关的数据，以驱动业务决策过程。 这些数据通常驻留在具有各自集成方法的不同 CIM 应用程序中。 在某些情况下，数据不存在、不完整，或者是在操作员的笔记本电脑上进行手动维护。
洞察力：应用材料公司采取哪些措施来填补此缺口？
Bing: 我们开发了 SmartFactory CIM 解决方案——一站式、交钥匙、完全自动化的解决方案，它集成了应用材料公司跨四个关键工厂领域的自动化产品，包括[制造执行](/zh-hans/semiconductor/manufacturing-execution-solutions/300works-full-auto/)、[工艺质量](/zh-hans/semiconductor/process-quality-solutions/)、[工厂生产效率](/zh-hans/semiconductor/productivity-solutions/scheduling/)和[供应链](/zh-hans/semiconductor/supply-chain-solutions/)。 每个领域的底层系统通过消息总线连接（参见图 1）。 这种开箱即用的集成支持同步实时通信，实现无缝决策逻辑流，从而控制晶圆厂的复杂制造操作。 其现成的功能让制造商在不到 6 个月的时间内建成一座新半导体工厂成为可能。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/06/fig-1-cim-diagram.jpg) 图 1. 应用材料 SmartFactory CIM 解决方案将自动化产品集成到四个工厂领域：制造执行、工艺质量、工厂生产效率和供应链管理
洞察力：在您看来，CIM 解决方案处理的关键性能指标是什么？ 或者说解决方案中值得称道的关键领域是什么？
Bing:我认为是加快上市时间、缩短生产周期和更好的工厂监控。 更具体地说，我认为有五个关键领域值得注意：
**制造操作的全自动化**
[SmartFactory MES 300Works™ Full-Auto](/zh-hans/semiconductor/manufacturing-execution-solutions/300works-full-auto/) 提供集成工厂操作的 MES 框架和解决方案，例如[物料控制](/zh-hans/semiconductor/manufacturing-execution-solutions/material-control/)、[工厂事件](/zh-hans/semiconductor/productivity-solutions/activity-manager/)、[规划](/zh-hans/semiconductor/productivity-solutions/simulation-autosched/)和[排程](/zh-hans/semiconductor/productivity-solutions/scheduling/)以及[设备维护管理](/zh-hans/semiconductor/manufacturing-execution-solutions/maintenance-management/)并且全部采用全自动化模式。
**工艺质量和良率**
我们的 Applied E3™ 过程控制框架提供行业领先的应用，支持[故障检测](/zh-hans/semiconductor/process-quality-solutions/fault-detection/)、[run-to-run control](/zh-hans/semiconductor/process-quality-solutions/run-to-run-control/)、[SPC](/zh-hans/semiconductor/process-quality-solutions/spc3d/)、[设备自动化](/zh-hans/semiconductor/process-quality-solutions/equipment-automation/)、[配方管理](/zh-hans/semiconductor/process-quality-solutions/recipe-management/)、良率管理和缺陷管理，所有这些都应用于跨多个晶圆厂的各种制造过程，以产生工艺质量成果和实现良率最大化。
**工厂生产效率**
我们的 SmartFactory APF 生产效率框架包括[排程](/zh-hans/semiconductor/productivity-solutions/scheduling/)、[派工和报表](/zh-hans/semiconductor/productivity-solutions/dispatching-and-reporting/)、[模拟](/zh-hans/semiconductor/productivity-solutions/simulation-autosched/)和预测，并且集成[企业规划、](/zh-hans/semiconductor/supply-chain-solutions/enterprise-planning/)[设备自动化](/zh-hans/semiconductor/process-quality-solutions/equipment-automation/)、[维护管理](/zh-hans/semiconductor/process-quality-solutions/equipment-automation/)和先进过程控制 以使得设备正常运行时间实现最大化，从而提高生产效率。 生产效率领域的完全自动化能力可减少空窗时间和设备闲置时间，最大限度地提高工厂产出。
**上市时间和生产周期**
我们的 SmartFactory 工作流引擎，由生产模拟技术驱动，提供智能的工作负载预测，减少材料等待时间，从而缩短生产周期和整体上市时间。
**工厂监控**
值得一提的是，我们的 SmartFactory [监控](/zh-hans/semiconductor/manufacturing-execution-solutions/monitor/)解决方案可巡查所有 CIM 解决方案组件，同时也加强和保护工厂运营。 其自动化安装程序和易于使用的特性让客户能够以更低的成本享有支持服务和降低拥有成本。
洞察力：最后，您认为应用材料的 CIM 产品有什么独特之处？
Bing: 肯定是经验了。 我的意思是，我们的 SmartFactory CIM 解决方案由业内出色的行业专长和知识打造。 作为全球半导体行业中部署规模最大的 CIM 解决方案，随着每一次连续的工厂安装（或随着时间的推移不断发展），它都得到了“强化”。 我认为我们解决方案的关键竞争优势包括：
**部署规模最大的 CIM 解决方案**
应用材料是领先的半导体行业自动化解决方案提供商，拥有近 1000 名专家和三十年的半导体晶圆厂自动化经验。
**对集成的定制要求很低，甚至无需定制**
大多数制造运营管理供应商只拥有半导体工厂全自动化需求中一部分的功能，这需要大量定制来集成各种供应商产品以满足全工厂需求。 相比而言，我们的 SmartFactory CIM 解决方案包括一套全面的 SmartFactory 解决方案，这些解决方案已经预先集成，可满足定制要求较低或无需定制的半导体工厂全自动需求。
**现成的功能**
应用材料SmartFactory EngineeredWorks™提供预组合派工规则、MES 自动化规则和 R2R 控制器，支持 90% 以上的工厂全自动化运行场景。 这些现成的功能让新晶圆厂初创企业能够快速部署并加快上市速度。
**强大的自助服务平台**
APF 平台允许工厂的工业工程师或规划人员在不消耗 IT 资源的情况下，针对特定的派工情况制定定制的派工规则。 同样，我们的 Applied E3 平台让工厂的工艺工程师能够打造 run-to-run 过程控制器，以调整特定的过程参数。 这些平台让用户能够掌控晶圆厂的运行状况。
**结论**
应用材料完全集成的 SmartFactory CIM 解决方案包括广泛的成熟能力，涵盖制造执行、工艺质量、工厂生产效率和供应链管理领域。 半导体行业正在使用这种自动化套件来实现可预测的良率和产出结果。
准备好联系我们，了解更多有关 SmartFactory CIM 或其他解决方案的信息吗？
[ 联系我们 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi, Popular
---
### [提高 AI 和 ML 解决方案的开发和部署效率](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/improve-productivity/)
**Published:** May 26, 2022
**Author:** Jeong Cheol Seo
**Excerpt:** 借助我们的 SmartFactory 高效人工智能/机器学习（AI/ML）平台，体验通过集成化的方式对人工智能/机器学习（AI/ML）模块进行开发。
**Content:**
对于正在考虑使用人工智能 (AI) 和机器学习 (ML) 技术的半导体晶圆厂管理者来说，有一些需要考虑的问题：针对您的特定问题开发 AI/ML 模块的生命周期是什么？ 使用 AutoSched™、Activity Manager™ 和 APF Formatter 等 SmartFactory 高效产品在您当前使用的系统和生产环境中实施 AI/ML 模块的有效方式是什么？ 您是否了解涵盖 AI/ML 模块开发的全生命周期的集成化解决方案？ 制造商依赖于我们的 SmartFactory高效人工智能/机器学习（AI/ML）平台，支持整个 AI/ML 模型的开发生命周期，能够将开发前置时间缩短 30% 以上。
### AI/ML 模块开发生命周期的标准步骤
AI/ML 模块开发生命周期包含四个标准步骤：准备和获取数据、定义和计算特征、训练和评估 ML 模型，以及部署和监控模型（见图 1）。
- **步骤 1： 数据准备和获取。** 如果晶圆厂的历史数据或设备数据已准备好，那么首先将进行数据采集和清洗。 如果历史数据不足以表征未来的变化，则需要扩充数据。
- **步骤 2： 特征定义/计算。** 在晶圆厂或设备数据准备完成之后，晶圆厂运营团队应定义要解决的关键问题特征，包括设备统计信息和工作属性。 在团队对特征进行定义之后，将进行自动计算。
- **步骤 3： ML 模型训练和评估。** 解决问题的最佳 ML 算法是哪种？ 套索回归？ Xgboost？ 团队会根据问题类型确定适当的算法。 在此步骤中，团队会根据需要进行重复训练和评估，然后根据结果调整特征和参数/超参数。
- **步骤 4： 部署和监控。** 在这一最后的步骤中，模型得以部署到生产中，但请注意，这种部署不会影响当前生产系统的性能。 部署简单高效。 在团队实施模型之后，通过实时监控可以得知模型的性能和对生产的影响。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-lifecycle.jpg) 图 1。
### 晶圆厂借助 SmartFactory 高效 Al/ML 平台提高效率
晶圆厂在使用 AutoSched、APF Formatter、Activity Manager 和 Solution UI 等 SmartFactory 高效 AI/ML 平台组件之后，能够直接将这些模块集成到生产环境中，无需像通常那样在 AI/ML 开发生命周期的每一步开发单独的 python 程序。 集成这些模块，帮助晶圆厂降低成本，避免对额外开发资源的需求（见图 2）。
- **步骤 1： 在准备和获取数据时：** 如果晶圆厂管理者需要为新的晶圆厂或设备数据进行数据扩充，**AutoSched** 是一款出色的模拟产品，能够针对新的晶圆厂行为和设备统计信息扩充数据。
- **步骤 2： 在定义和计算特征时：** 在定义了一整套特征之后，应自动化进行特征计算。 如果需要新的特征，那么在当前环境中添加新特征并修改现有特征应该很容易。**Activity Manager** 可进行自动化流程，而使用 **APF Formatter** 能够轻松实施特征计算。
- **步骤 3： 在进行 ML 模型训练和评估时：** 在此步骤中，初始模型训练和评估将会在一般的 python 开发环境中进行。 平台将使用即用型 ML 模型，从而解决常见的工厂生产效率和供应链问题。 这些模型是“基线”模型，晶圆厂也可以根据需要自由修改和重用。 此外，**Solution UI** 能够提供多种多样的评估界面，从而加速模型训练和评估。
- **步骤 4： 在开发和监控 ML 模型时：** 在生产中部署 ML 模型不应给当前生产系统造成负担，并且最好在当前规则开发人员熟悉的环境中进行。 如果这些开发人员能够将 **APF Formatter** 作为其规则开发工具以及部署工具（见图 3），那么效果将更为理想。 规则开发人员可以简单地使用 Python 代码块将 ML 模型部署到生产中，这与当前方式别无二致。 **Solution UI** 能够提供仪表盘，能实时监控模型性能以及对晶圆厂的影响。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-resources.jpg) 图 2。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-resources-fig.png) 图 3。
### 使用我们的 Solution UI 集成 AI/ML 开发生命周期
图 4 显示了我们的 Solution UI 如何与整个 AI/ML 模块开发生命周期相集成。 晶圆厂可以使用我们的 Solution UI 来配置参数、查看评估分析，并在部署之后进行实时监控。 此外，晶圆厂还能够了解下一步要执行的特定任务，并检查多个分析信息数据来识别潜在的问题。生命 周期中的每一步骤都能高效集成，并为每一步骤提供宝贵的信息，从而加速整个开发流程。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/development-lifecycle-solution-ui.jpg) 图 4。
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [EngineeredWorks™助力制造商加快实现价值创造，并缩短部署时间](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/engineeredworks-increases-speed-to-value-for-manufacturers-and-provides-quicker-deployment-times/)
**Published:** November 25, 2021
**Author:** David Hanny
**Excerpt:** 助力持续改进运营和新建工厂
**Content:**
助力持续改进运营和新建工厂
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, Newly Released, Popular
---
### [Walking on the Edge – SEMICON Europa 2021](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/walking-on-the-edge-semicon-europa-2021/)
**Published:** January 11, 2022
**Author:** Amnon Shenfeld and Yoram Barak
**Excerpt:** The path to seamless, hybrid-cloud environments
**Content:**
A common misconception is that implementing cloud-native applications is about asking the question, *Where*… “Where is our code and data being transferred-to and executed?” Cloud-nativity is more about the *How*… “How will our software and data architecture support quality, performance, security and scale?”
As seen in Figure 1, the Cloud is more about the architecture than its geography.
 Figure 1: The cloud is not about the geography, it’s about the architecture.
To enable cloud-native applications there are pre-requisite steps, including containerization, streamlined security, encryption, authentication, virtualization, decoupling hardware\\software dependencies (elasticity), compute & storage elasticity (cloud bursting), etc.
We anticipate great benefits from cloud-native architectures. Manufacturers who have a need to bridge the gap between factory capacity and customer delivery commitments are relying on our advanced productivity suite, focusing on SmartFactory Planning and Scheduling solutions.
One example is with our SmartFactory Production Planning and Scheduling in our Advanced Productivity Suite, where the objective is bridging the gap between factory capacity and customer delivery commitments.
Currently, this is achieved by applying simulation models to explore “what-if” scenarios to identify opportunities for improving throughput and capacity utilization. The challenge is that simulations are CPU/Memory/Storage intensive and potentially, depending on the use case and scenario complexity TAKE FOREVER TO COMPLETE!
To shorten time to action, we compared single-server simulation modeling + ML, to a cloud-native enabled architecture to achieve accurate cycle time prediction based on parallelizing thousands of simulations run with different product and recipe mixes + ML.
As seen in Figure 2, The outcome is an outstanding **24X run-time reduction from 5 days to 5 hours** by achieving seamless, hybrid-cloud implementation, elastically scaling and parallelizing CPU workloads to worker pools.
 Figure 2: Decoupling software and hardware dependencies accelerates time to results by an order of magnitude.
For more info, check out Walking on the Edge presented at SEMICON Europa 2021 PDF below:
[pdf-embedder url=”/wp-content/uploads/2022/01/Walking-on-the-Edge-SEMICON-Europa-2021-Presentation.pdf”]
[ Download this PDF ](/wp-content/uploads/2022/01/Walking-on-the-Edge-SEMICON-Europa-2021-Presentation.pdf)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Enhancing your digital experience](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/enhancing-your-digital-experience/)
**Published:** December 1, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Transforming UX, image, and functionality with improved dashboards, reports, operations, and workflows
**Content:**
User experience (UX) is the process developers use to create the most functional and effective products for customers. It’s about shaping digital experiences for users to provide the best way to interact with them. This blog briefly overviews the usability efforts within the Automation Products Group (APG)—highlighting where we’ve been, what we see, and where we’re going with UX.
### The Case for Better Usability
An oft-quoted UX design statistic illustrates how McAfee, the global computer security software company, cut their support calls by **90%** because of a simple **user interface redesign,** giving their customers a better overall user experience.1
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/mcaffee-stat-.png)
Unfortunately, user experience is an aspect of design that often gets overlooked. In the semiconductor industry, reliability is paramount—and for good reason. Any interruption in an automation system caused by software **reliability** concerns can cost **millions of dollars in lost revenue.** As such, it used to be “ok” to have a bad user experience for an enterprise application—if the application was reliable and functionable.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/ux.png)
### Where We’ve Been
The software developed within Automation Products Group at Applied Materials is proven and deeply mature in high volume factories worldwide. Our strength and differentiation over the last **30 years** has been designing and deploying reliable, feature-rich software that delivers superior results—but admittedly with less emphasis on usability, interface design, or user experience.
But the times are changing. Today’s new generation of fab managers and operators have **loftier expectations** for usability and ease-of-use.
### What We See
Today we see accelerated **digital transformation** of companies and the economy at large. And we’ve seen expectations of software usability increase considerably—with greater emphasis on smartphone mobility, 3D-rendered equipment, simplified KPI statistics, and better drill downs.
### Where We’re Going
We understand these realities and over the past few years have made significant investments in innovative technologies, from cloud, mobile, and advanced analytics solutions to next generation UX/UI technology and capabilities in direct response to customer needs. With this investment, we have done the following: - Formed a **UX Design team** to create new design process and workflows. This ensures user-centered design is applied consistently to software development.
- Deployed a **UI Kit** with ready-made interface libraries and components, enabling functionality to be built in a quarter of the normal development time.
- Initiated a process for better **partnership** and **collaboration** with customers. This allows customers to engage in the design process, increasing sense of ownership.
With its UI Kit project, we’re transforming user experience, image, and functionality with improved dashboards, reports, operations, and workflows. Our UX designers are engaged through the entire product life cycle, from the first contact a customer has, through user research and information architecture, and through every screen interaction in the software.
In addition, we recently entered a new market, introducing [SmartFactory Rx](https://appliedsmartfactory.com/pharmaceutical/) in the pharmaceutical industry. Using Applied’s new UX design processes and workflows, our software development teams have rapidly prototyped product features while working to first define the product with customers, and then building the product with constant feedback from customers and end users.
And because the product was built using the UI Kit, software engineers had ready-made interface libraries and components they could rapidly bolt together to build powerful new functionality in a quarter of the normal development time.
In summary, we continue to be fully committed to maintaining our long-standing reputation for reliable, stable software solutions. But, in addition, with a new framework for building best of breed UX solutions, we’re now better positioned to shape digital experiences for users—providing an enhanced way to interact with them for a better overall user experience.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Bringing production reality closer to target](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/bringing-production-reality-closer-to-target/)
**Published:** November 18, 2021
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Driving the “S curve” to enable performance throughout your fab’s life cycle
**Content:**
From development through production, as device quality and performance specifications become more stringent, factory automation solutions, such as those developed by Applied’s Automation Products Group (APG), enable customers to achieve important yield, output, and cost improvement targets.
In this blog, I highlight the critical aspects of maximizing profitability for a new fab using a framework called the “S curve.” It makes the case for using advanced automation software solutions to add value during the development and transfer-to-volume-manufacturing phases of the fab life cycle.
### What’s the S Curve?
Figure 1, referred to as the S curve, illustrates the life cycle of a fab ramping to full manufacturing potential—from first silicon through continuous improvement. Elements of this life cycle, illustrated by the chart, include: - **Time** (x axis).
- **Yield** and **output** (y axis).
- **Production goal** (heavy green line), or the ideal ramp of output and yield through the phases of development.
- **Production reality** (orange jagged line) of the ramp that a customer must manage.
- **Example issues** (grey ovals) that prevent a fab from reaching targeted capacity and yield (note that these are just examples; for some fabs, depending on volume and product, other issues may be more critical).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/11/s-curve-figure1.png) Figure 1. The “S curve” showing production goal (green line) vs. production reality (orange line), as well as various barriers to achieving capacity and yield targets (gray ovals)
### Driving the S Curve
Not evident in Figure 1 are the critical aspects or factors that a fab must optimize to ensure that production reality meets or exceeds the production goal. These factors are:
- Yield
- Cost
- On Time Delivery
- Output
The effort of optimization—ensuring that production reality meets production goals—is referred to as **“driving the S curve.”** In your fab, how well do you drive the S curve? What’s required for successfully driving the curve?
### The Earlier the Better
The main point of the S curve is that both yield learning and volume production have more value **early in the life cycle of a new product,** than they do later in the life cycle of that same product. This is because a “new” semiconductor device typically achieves a higher selling price earlier in its life cycle. For a fab costing $20B or more, the area between the green curve and orange line is worth **hundreds of millions (if not billions) of dollars.** This represents unrealized potential, and time is incredibly valuable throughout this process; a delayed ramp means longer time for returns.
### Our Recipe for a Successful Drive
To help fabs realize this hidden potential and successfully drive the S curve, our Applied SmartFactory® computer integrated manufacturing (CIM) control and productivity suite offers a proven, successful deployment approach for managing fab production—an approach implemented in two stages to help new fabs achieve: - **First silicon.** During this phase, customers can begin trial production, shorten their production schedule and learning curve, and increase their production capacity.
- **Volume production.** During this phase, customers can reduce process variation and wafer scrapping, stabilize yield, increase unit interest rate, and optimize their capacity profitability curve.
The key to this approach is deploying software solutions when required to bring production reality closer to target (see Figure 2). By deploying software capabilities when required, fab managers can address and resolve challenges throughout production, providing faster time to market, higher quality, and lower scrap.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/11/s-curve-with-solutions-figure2.png) Figure 2. The “S curve” showing our approach of deploying proven software automation capabilities when required to bring production reality closer to target
Built on over 30 years of software and fab manufacturing experience, SmartFactory solutions are proven in the world’s most advanced fabs and differentiated as follows: - **Fully integrated** components to eliminate inefficient and disjointed systems, reducing deployment time and IT support costs
- **Pre-built automation logic** using Applied EngineeredWorks® to increase speed-to-value, enabling quicker deployment times
- **Open box** approach to eliminate extensive customization costs and enable full user control over fab behavior
### Summary
No matter what node or product, today’s semiconductor manufacturing challenges are tough. Fab managers must meet business and production targets—and be able to evolve quickly—to meet changing business and technology requirements.
Whether you need to quickly ramp a new process, run new technologies, or get more out of your installed base, our extensive software capabilities can help you “drive the S curve” to ensure that production reality meets or exceeds your production goal. In this environment, CIM automation, such as that offered with the Applied SmartFactory suite, is critical for achieving important yield, output, and cost improvements at every step of the fab life cycle.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular, Semi
---
### [Achieve faster resolution of SPC and FDC violations](https://appliedsmartfactory.com/semiconductor-blog/quality/spc-and-fdc-violations/)
**Published:** May 17, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Extend automation intelligence capabilities in your factory with cohesive OCAP solution using SmartFactory Knowledge Advisor.
**Content:**
Did you know that human error is responsible for nearly **50%** of the scrap in a factory (see Figure 1)? Automating out-of-control action plans (OCAPs) represents a significant opportunity for return on investment.
An *OCAP* is the plan engineers follow to understand and correct defects on a process or production tool. For example, if a statistical process goes out of control, the processing on the associated tool stops, allowing engineers to perform a series of tasks to bring the tool back online as quickly as possible.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig1-min.png) Figure 1. While other causes are often believed to be the biggest cause of downtime, human error is the largest contributor to downtime
### Data Availability, Accessibility and Completeness
But not all tasks are readily available or distributed to engineers equally, and no single parametric dataset from a process provides a complete picture of sources of variation. Data used for control plans often resides in different components, such as SPC or FDC, with their own integration methods and data structure models. In some cases, data does not exist, is incomplete or is being manually maintained on someone’s laptop. Also, correctly performing recovery tasks requires an engineer to have an appropriate plan, read and understand the steps, and then execute those steps properly.
### The Value of a Cohesive Approach
Today’s fabs need a more cohesive approach—one that governs information sets and extends the automation intelligence of facilities. Figure 2 outlines the requirements of such an approach and highlights the value of implementing an OCAP solution with the proper capabilities.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig2-min.png) Figure 2. With the proper ingredients, an OCAP solution offers the opportunity to achieve 40% faster resolution of SPC and FDC violations
### An Integrated Workflow for Reducing Variability
To implement these ingredients for a successful OCAP and extend the automation intelligence in your factory, SmartFactory Knowledge Advisor provides an integrated workflow engine that—
- Embeds AI functions, such as context pattern matching (CPM) and data patterns, within the workflow to help guide users
- Enables users to build action plans for resolving anomalies
- Guides users to error resolution by providing workflow details with an intuitive user interface experience (see Figure 3 as an example)
- Reduces human variability related to incorrect interpretation of cause and effect
- Manages action trails to identify previous troubleshooting activities
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig3-min.png) Figure 3. This example action plan illustrates the availability of the user interface in Web Analytics on the browser and shows how you can easily view the details for a selected step on the left in the main panel on the right
### How Is Knowledge Advisor Different?
Many third party or inhouse OCAP solutions lack the “automation hooks” required for a multiple discipline approach. For example, they may only work with SPC and lack the capabilities for collecting data from other systems to help with troubleshooting anomalies.
However, Knowledge Advisor accommodates data from any of the Applied E3® solutions, including advanced process control (APC), SPC, FDC and recipe management (RM). As shown in Figure 4, the solution harnesses the full functionality of Applied E3, facilitating data collection from various sources and AI functions.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/05/ka-fig4-min.png) Figure 4. Knowledge Advisor is the only solution for building anomaly resolution action plans that is fully integrated to the SmartFactory E3 family
By using a common platform, engineers can better manage recipes, equipment, SPC and FDC violations. If you’re using E3 for FDC or SPC, having a common platform provides you with one less point to manage across your CIM.
### Conclusion
In today’s fabs, human error accounts for the largest source of scrap and downtime. The cost of automation must be considered against the cost of recovery and scrap. Therefore, the key is gauging what level of automation is appropriate to maintain competitive margins and investment for future growth. Knowledge Advisor is designed to provide cost effective flexibility to customers. With its integration and accurate decision-making capabilities, Knowledge Advisor enables users to be more effective resolving equipment and process failures. Key results include reduced repeat violations and false resolutions, improved audit compliance, standardized error handling activities and AI capabilities to reduce signal to noise management.
Our SmartFactory automation solutions have served the semiconductor industry for over 30 years and have been hardened with best-in-class know-how in all aspects of a semiconductor factory.
Ready to contact with us to learn more about SmartFactory Knowledge Advisor or other solutions?
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [Deep reinforcement learning (RL) for Queue-time management in semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/deep-reinforcement-learning/)
**Published:** August 18, 2022
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Use deep RL to minimize yield loss with automatic control of Queue-time management
**Content:**
Queue-time constraints (QTC) define a limit on the time that a lot can wait between two process steps in its flow. In semiconductor manufacturing, lots that exceed that time limit experience yield loss, need rework, or get scraped. QTCs are difficult to schedule, since a lot needs to wait to be released to the first process step until there is available capacity to process the final step. However, exactly calculating if there is enough capacity is computationally expensive.
In this work we propose a deep Reinforcement Learning (RL) method to manage releasing lots into the Queue-time constraint. We analyze the performance of our RL method and compare it to seven baseline solutions. Our empirical evaluation shows that the RL method outperforms the baselines in five performance metrics including the number of Queue-time violations and makespan, while requiring negligible online compute time.
For additional details, please view or download this PDF:
[pdf-embedder url=”/wp-content/uploads/2022/08/DEEP-REINFORCEMENT-LEARNING-FOR-QUEUE-TIME-MANAGEMENT-IN-SEMICONDUCTOR-MANUFACTURING-rev2.pdf” height=”1000″]
[ Download this PDF ](/wp-content/uploads/2022/08/DEEP-REINFORCEMENT-LEARNING-FOR-QUEUE-TIME-MANAGEMENT-IN-SEMICONDUCTOR-MANUFACTURING-rev2.pdf)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [Automating the manual: Durables management for semiconductor manufacturing](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/durables-management-for-semiconductor-manufacturing/)
**Published:** April 22, 2024
**Author:** Selim Nahas, Yoram Barak
**Excerpt:** Assembly Test and Packaging burn-in use case scenario using SmartFactory Durables Management
**Content:**
## What’s Inside
- [ Introduction to durables management (DM) ](#index1)
- [ Assembly Test and Packaging burn-in use case example ](#index2)
- [ Optimizing remeasurement use case ](#index3)
- [ Asset performance use case ](#index4)
- [ Integration ](#index5)
- [ User experience/user interface elements of success ](#index6)
- [ Conclusion ](#index7)
### Introduction to durables management (DM)
In semiconductor manufacturing, durables are critical assets such as a reticle, carrier, probe card, pump or valve, chambers, fixtures, robots, and other equipment used in the manufacturing process. Durables can be considered mobile extensions of the manufacturing tool. Durables management, then, is the comprehensive management of these assets. It involves tracking, monitoring, and optimizing their usage, maintenance, and lifecycle to ensure smooth operations and maximize productivity.
Durables management is extremely important to semiconductor manufacturing for the following reasons:
**Cost efficiency:** Semiconductor manufacturing involves high-value equipment and efficient management of these assets helps reduce costs associated with maintenance, repairs, and replacements. By tracking the usage and condition of durables, companies can identify and address issues promptly, preventing costly breakdowns or unnecessary inventory.
**Operational efficiency:** Optimal utilization of durables is crucial for maintaining consistent production schedules. Effective durables management ensures that equipment is available when needed, minimizing production delays and maximizing throughput.
**Process optimization:** By monitoring the performance and health of durables, semiconductor manufacturers can gather valuable data and insights. This data can be used to identify patterns, optimize equipment settings, and improve overall process efficiency. Durables management software can provide real-time analytics and actionable insights to drive continuous improvement initiatives.
**Maintenance planning:** Durables management enables proactive maintenance planning by tracking asset usage and predicting maintenance needs. Predictive maintenance strategies can utilize the lifecycle data from the durables management system.
**Quality control:** Durables management helps ensure consistent product quality by monitoring and controlling the performance of critical assets. By tracking equipment performance metrics, semiconductor manufacturers can identify deviations and take corrective actions to maintain product quality and yield.
SmartFactory Durables Management offers several benefits that directly address the challenges faced in semiconductor manufacturing through the triad of traceability, state model, and integration, as shown in Figure 1. It is an automated durables management system that properly manages the state and location of durables throughout their life cycle, which is essential for achieving optimal product quality, cycle times, and tool utilization rates. Combining these with SmartFactory Real Time Dispatching (RTD) creates an unparalleled powerhouse for running assets at peak efficiency.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/04/figure-1-The-benefits-of-SmartFactory-Durables-Management.jpg) Figure 1: The benefits of SmartFactory Durables Management
### Assembly Test and Packing (ATP) burn-In use case example
Over the course of the last three years, Automation Products Group worked to develop, update, and modify durables management capabilities that can be universally used irrespective of a customer’s MES. The fundamental difference in the back end is that many activities are often manual. The first project of interest was a back-end burn-in facility. This facility is responsible for testing devices that have been packaged for delivery to customers. The devices are loaded on burn-in boards, sometimes referred to as BIBs (see Figure 2). These boards will circulate between loading equipment known as Burn-in Loading Units (BLUs) and then sent to burn-in ovens where the BIBs and devices are heated while parametric tests are run on them.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/04/figure-2-1.jpg) Figure 2: BIB (a) and Socket (b) examples. These can be going into physical ovens or ovenless (i.e., where the heat is generated directly in the socket via high voltage and current)
The industry has been looking for a way to manage these assets to gain reliable testing of devices as well as manage the expense of maintaining these durables in the facility. Manual handling of such activities would be extremely challenging. It is fair to say that, from the human perspective, it can be a daunting task to track that many durables. For example, it is estimated that a facility could contain as many as >20,000 or more durables of one type alone. The BIBs are populated with sockets and a single BIB can contain as many as 150 sockets. If sockets are defined as a durable as well, we now could be looking at a much greater number of durables to manage. It’s not simply a question of health management, but also of logistics. A burn-in facility has the fiduciary responsibility to test devices and isolate those that fail for one reason or another, as well as assure that the failure is coming from the device and not the BIBs and/or sockets. A prerequisite in such a facility is to be able to manage a remeasurement scenario in the event of a failed device. These activities are greatly facilitated by having the ability to track and trace the location and performance of the boards and the sockets upon them.
### Optimizing remeasurement use case
In the ATP market, an example of an optimization opportunity is the remeasurement activities of devices that initially failed, ensuring their validity by transferring them to appropriate alternate boards. Because we understand sockets and board performance, the dispatcher can select the optimal board and socket for devices that failed.
### Asset performance use case
Judging an asset performance is significantly better with a Durables Management system. Tracking usage, movement, cycle, etc., allows us to draw statistics around a population of assets. Ensuring an understanding of the utilization of assets and its resulting performance can strengthen the understanding of how to best utilize the asset. This would be true from a maintenance and usage perspective.
### Integration
More automation is needed to make durables management less daunting for the humans responsible for it. This automation can only be made possible if the durables have an application in which equipment integration can be connected. There must also be a provision for manual interfaces, as many of these facilities still rely on operators to load and unload equipment. This means that the ability to define relationships between boards and equipment and people is an essential part of a durables management system. It is also important to be able to define criteria that are tracked for the purposes of evaluating the health of durables. Last but not least, it is essential to establish a relationship between one durable and another in instances where they may contain each other or affect each other in some way. An example might be a container that is considered a durable which contains another durable, such as a cassette and reticle in a front end fab, or a BIB and a socket in a back end fab. These durables are expected to move throughout the day, often into equipment or out for repair and, in many cases, even outside the facility. To that end, a modern durable management system needs to have the ability to define and manage relationships both inside and outside the facility.
All durables must be able to maintain a state model that defines a business process of interest for the given durable. This business process will include simple elements such as counters and custom fields as well as parametric results from inspection tools or other calibration equipment. All these elements must be able to affect the behavior of the state model.
### User experience/user interface elements of success
A well-thought-out product will make provisions for automated data entry generally supported by an application programming interface (API). Equally important is the human interface which may allow entry via a keyboard, mouse, barcode gun, tablet, or phone. The key component to a successful deployment of durables management is making it as unobtrusive as possible to the end user while allowing a growth path toward increased automation. This means that, as tasks are automated, updates to the automation behavior are easily accommodated. Equally important is that there is a visualization element for the user community.
SmartFactory Durables Management adopted several guiding principles to that end:
- Navigation and intuitive design are an essential part of a successful adoption of a durables management system.
- All the interfaces supporting this application will need to make use of lean efficiency principles.
- It is essential that such an interface be well designed to facilitate a natural progression of thought from the user and an ability to handle single or batch actions in a simple and concise manner.
- It is best if the interface supports these actions as if they were an extension of the human being’s behavior.
- All these various elements must allow inputs to drive the behavior of the state model.
- The equipment interface or RFID tags may also play a role in traceability of durables in the facility.
- A well-thought-out user interface allows the user to visualize at a macro level the durable of interest such as a bib. From that visualization, the ability to drill down to an individual socket is also a requirement. (See figure 3.)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2024/04/figure-3-scaled.jpg) Figure 3: SmartFactory Durables Management has a modern UI with superb UX.
### Conclusion
The implementation of SmartFactory Durables Management has become crucial in tracking assets throughout the manufacturing process, starting from their source to their arrival at the facility. This enables semiconductor manufacturers to effectively manage the health, cost, and performance of their assets, as well as easily locate them. More optimized operating processes are made possible using Durables Management. By tracking and tracing the health and location of assets, more complex activities like scheduling and staging can be performed, ensuring efficient utilization of durables for specific tasks. Additionally, the ability to trace back to suppliers enhances suppliers’ quality, enabling management to make informed decisions about altering business processes based on durable performance and availability to support manufacturing needs.
## About the Authors
Selim Nahas, Global Process Quality Director
Selim Nahas is responsible for the Process Quality Group. Selim has 29 years of experience in semiconductor factory automation systems. He is a technical marketing specialist developing new solutions and methods of improving quality in semiconductor manufacturing. With a portfolio of technologies and developers with diverse specialties, the Process Quality Group develops and deploys Statistical Process Control systems for both Inline and Electrical Test as well as Fault Detection, Run to Run control and Recipe Management. This entire portfolio of capabilities is tightly coupled with one of the most advanced Knowledge Management Systems currently available in industry.
Yoram Barak, Strategic Marketing
Prior to joining Applied Materials Automation Products Group in 2020, Yoram was a Global Marketing Manager at BASF Human Nutrition business division and before, an Innovation Manager for the Biosciences R&D Division at BASF. Yoram earned his PhD in Animal Sciences from the Hebrew University of Jerusalem and specialized in Biotechnology throughout his career.
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [Moving to a new level of intelligent manufacturing.](https://appliedsmartfactory.com/semiconductor-blog/smart-manufacturing/moving-to-a-new-level-of-intelligent-manufacturing/)
**Published:** October 18, 2021
**Author:** David Hanny
**Excerpt:** Semiconductor manufacturing has moved through several levels of technology. Now the industry is entering another change cycle.
**Content:**
Semiconductor manufacturing has moved through several levels of technology. Now the industry is entering another change cycle.
\[pdf-embedder url=”/wp-content/uploads/2024/04/Moving-to-a-New-Level-of-Intelligent-Manufacturing-1.pdf” height=”1000″\]
[ Download this PDF ](/wp-content/uploads/2024/04/Moving-to-a-New-Level-of-Intelligent-Manufacturing-1.pdf)
**Semiconductor Category:** Semiconductor Smart Manufacturing
**Semiconductor Tag:** Semi
---
### [Automated tool recovery increases equipment efficiency](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/automated-tool/)
**Published:** July 20, 2023
**Author:** Seong Hoon Lee and Boon Guan Lim
**Excerpt:** SmartFactory 300works® can help reduce an often-overlooked component of maintenance downtime
**Content:**
Manufacturers are always interested in maximizing process tool availability and minimizing down-time. This is particularly the case in the semiconductor industry, where capital equipment costs are exceedingly high.
An often-overlooked component in maintenance downtime is the time it takes to re-qualify process tools following maintenance. Accelerating this post-maintenance qualification process can reduce overall maintenance downtime and improve process tool availability. SmartFactory 300works provides a systematic approach to automating the process.
Consider a simple example where an equipment engineer needs to run a monitor wafer to re-qualify a tool after preventive maintenance. This would ordinarily be a manual process during which the engineer looks to:
- Determine which qualification process flow is required
- Ensure the required wafers are available and ready for use
- Retrieve the required wafers from storage
- Process the monitor wafer(s)
- Evaluate the results and decide the disposition of the process tool
This is conceptually simple, but it’s a time-consuming, manual process – particularly when something unexpected occurs, such as discovering that the required wafers aren’t available or aren’t ready to use. It becomes a big drain on factory efficiency.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/factory-efficiency.jpg)
300works automates this process with its automated tool recovery package. Depending on the degree of factory automation deployed onsite, manufacturers can reduce post-maintenance costs and re-qualification time by half or more.
Figure 1 shows how a monitor wafer process flow associated with preventive maintenance might be implemented within the automated tool recovery package.
This is how 300works automated tool recovery package improves the process by: - Locating the proper monitor wafers and ensuring they’re properly prepared for use
- Downloading the process recipe to the process tool and initiating processing
- Uploading processing results
- Automating the disposition decision and returning the monitor wafers to storage ready to be used again
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/07/automated-tool-recovery-workflow-2.jpg) Figure 1: Automated Tool Recovery Workflow
The overall impact of automating post-maintenance re-qualifications can be significant – particularly for bottleneck tools.
Our 300works automated tool recovery workflow ensures the proper re-qualification process flow and monitor wafers are used, and that re-qualification disposition occurs in a consistent manner. It also accelerates the re-qualification process, reducing tool down-time and gets tools back up and running in production quickly.
Interested in learning more? Reach out [here](/connect/) for more information!
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Newly Released, Semi
---
### [Using a framework to validate factory scheduling solution systems (Part 1/2)](https://appliedsmartfactory.com/semiconductor-blog/scheduling/scheduling-solution-systems-part-1/)
**Published:** November 14, 2023
**Author:** Ravi Jaikumar, Global Product Manager, Real Time and Advanced Scheduling
**Excerpt:** A quality factory scheduling solution can improve equipment productivity, product quality, and on-time delivery of products
**Content:**
A semiconductor factory’s manufacturing schedule has a direct impact on critical business objectives such as equipment productivity, product quality, and delivering products to customers on time. A schedule that isn’t performing as it should, then, can be costly. Fortunately, it’s possible to validate the schedule to make sure it was created using the right data and is creating the right outcome in the factory.
[Factory scheduling solution systems](/semiconductor/productivity-solutions/scheduling/) help semiconductor manufacturers make the best use of their equipment and personnel resources. To be effective, solutions will produce a schedule that is accurate and complete. A validation framework lets manufacturers determine the validity of the schedule by looking at both its output and the quality of the input data used to create it.
Manufacturers use factory scheduling solution systems to create a 12 to 24 hour factory schedule for lots, tools, and durables. The schedule is typically refreshed and updated in near time every 5-10 minutes to an hour, depending on the factory use case and their cycle times, product mix, and operating philosophy. When a scheduling solution is deployed in a factory, the validation framework must also be deployed to determine the validity of the schedule it generated. It’s important that the framework has the granularity to be able to drill down to the tool level and lot level from the table-level summary for deeper analysis.
### Creating the Factory Schedule
A typical scheduling workflow is shown in figure 1, below. Factory data sources including the [MES](/semiconductor/productivity-solutions/scheduling/) are accessed to generate the solution input data needed for the scheduling solution. The scheduling engine then applies logic to generate lot-to-tool assignments to fulfil the defined objectives of the local area or the factory globally. Any and every discrepancy, inaccuracy, invalidity, and infeasibility of a schedule can be traced back to the solution input data and/or the scheduling engine.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure1-scheduling-workflow.jpg) Figure 1: Typical scheduling workflow
Evaluation and validation of the schedule entails a base level validation and validation of the input data quality and completeness, as shown in figure 2.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure2-three-levels.jpg) Figure 2: Three levels of validation of a schedule
### Base level validation of a factory schedule
The schedule is produced in the form of a Gantt chart. A set of specific questions is used to validate the schedule. If the user can answer ‘Yes’ to any of the following questions, then the schedule is invalid and more investigation is needed to trace the root cause and apply fixes.
Tools-related questions:
- Are up tools not assigned any lots by the scheduler?
- Was there any WIP qualified and available to run on those tools?
- Are down tools assigned lots by the scheduler?
- Are scheduled down tools assigned lots by the scheduler overlapping with the maintenance event time horizon?
- Are unscheduled down tools assigned lots by the scheduler?
- Are tools assigned lots for steps where they are not qualified to run?
- Are tools assigned lots for a part that does not have that step in its route?
- Does lot assignment consider the configuration of the tools including load ports and chambers?
Lot specific questions: - Are active WIP lots not assigned to any tools for their current and future steps?
- Are inactive WIP lots assigned to any tool for their current and future steps?
- Does the scheduler assign lots that would violate Q-time windows or show zero wait time lots waiting in queue for processing behind lower priority lots at a step?
A production schedule typically refreshes in a cadence from every five minutes to up to an hour. Therefore, the validation framework needs to have summary report and analytics (as shown in figure 2) to track the trend of the schedule validity run over run.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure2-table-analytic.jpg) Figure 2: Example of a summary table analytic
### Secondary validation of factory schedule
#### Input data quality and completeness
When there is an incomplete or invalid schedule, validation of the extract transform load/extract transform map (ETL/ETM) layer of the solution is often the reason. For example, tools, lots, and routing steps might be missing due to the incompleteness and incorrectness of the data extraction and transformation process. Data validation reports are needed to make sure the scheduling solution was fed accurate and correct input data. The following are examples of outputs generated when input data is incomplete:
- **WIP:** WIP in the factory, not in the scheduling system, are accounted for.
- **Tools:** Scheduling solution input data reflects all installed and operational tools in the factory.
- **Step:** number of steps without routes mapped to it or tool groups defined to run it.
- **Part number of parts:** with no valid route assigned to them.
- **Part number of lots:** running on routes not matching those defined in the scheduling solution input data.
- **Generic resource of steps:** that claim a generic resource like probe card or reticle for usage.
- **Setup of stations:** with no current setups defined.
#### Input Data Tracking for Factory Scheduling
Schedule adherence and accuracy is impacted by the relative accuracy of model inputs like process time. To measure the drift and delta of process time, you must be able to compare process time for a part-step-tool group combination versus statistically generated and computed process time based on historical data, as shown in figure 3. This can help the user identify entries which need correction or updating out of cycle (if they have a regular cadence to update those model inputs). There also need to be alerts in the workflow to notify the user about drifts in process time
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure3-example.jpg) Figure 3: Example of a table tracking process time.
Once these validations have been completed, manufacturers can move on to advanced validations and fine tuning of the schedule. This includes understanding the decision making that went into creating the schedule and consideration of specific KPIs. These are discussed in **“Using a framework to validate factory scheduling solution systems,** [(Part 2/2)](/blog/scheduling-solution-systems-part-2/)”
## What’s Inside
- [ Need for a validation framework ](#index1)
- [ Creating the schedule ](#index2)
- [ Base level validation ](#index3)
- [ Secondary validation: input data quality and completeness ](#index4)
- [ Input Data Tracking ](#index5)
- [ What’s next ](#index6)
A semiconductor factory’s manufacturing schedule has a direct impact on critical business objectives such as equipment productivity, product quality, and delivering products to customers on time. A schedule that isn’t performing as it should, then, can be costly. Fortunately, it’s possible to validate the schedule to make sure it was created using the right data and is creating the right outcome in the factory.
### Need for a validation framework
[Factory scheduling solution systems](/semiconductor/productivity-solutions/scheduling/) help semiconductor manufacturers make the best use of their equipment and personnel resources. To be effective, solutions will produce a schedule that is accurate and complete. A validation framework lets manufacturers determine the validity of the schedule by looking at both its output and the quality of the input data used to create it. Manufacturers use factory scheduling solution systems to create a short interval, 12–24 hour, factory schedule for lots, tools, and durables. The schedule is typically refreshed and updated in near time every 5-10 minutes to an hour, depending on the factory use case and their cycle times, product mix, and operating philosophy. When a scheduling solution is deployed in a factory, the validation framework must also be deployed to determine the validity of the schedule it generated. It’s important that the framework has the granularity to be able to drill down to the tool level and lot level from the table-level summary for deeper analysis.
### Creating the Schedule
A typical scheduling workflow is shown in figure 1, below. Factory data sources including the [MES](/semiconductor/manufacturing-execution-solutions/) are accessed to generate the solution input data needed for the scheduling solution. The scheduling engine then applies logic to generate lot-to-tool assignments to fulfil the defined objectives of the local area or the factory globally. Any and every discrepancy, inaccuracy, invalidity, and infeasibility of a schedule can be traced back to the solution input data and/or the scheduling engine.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure1-scheduling-workflow.jpg) Figure 1: Typical scheduling workflow
Evaluation and validation of the schedule entails a base level validation and validation of the input data quality and completeness, as shown in figure 2.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure2-three-levels.jpg) Figure 2: Three levels of validation of a schedule
### Base level validation
The schedule is produced in the form of a Gantt chart. A set of specific questions is used to validate the schedule. If the user can answer ‘Yes’ to any of the following questions, then the schedule is invalid and more investigation is needed to trace the root cause and apply fixes.
Tools-related questions:
- Are up tools not assigned any lots by the scheduler?
- Was there any WIP qualified and available to run on those tools?
- Are down tools assigned lots by the scheduler?
- Are scheduled down tools assigned lots by the scheduler overlapping with the maintenance event time horizon?
- Are unscheduled down tools assigned lots by the scheduler?
- Are tools assigned lots for steps where they are not qualified to run?
- Are tools assigned lots for a part that does not have that step in its route?
- Does lot assignment consider the configuration of the tools including load ports and chambers?
Lot specific questions:
- Are active WIP lots not assigned to any tools for their current and future steps?
- Are inactive WIP lots assigned to any tool for their current and future steps?
- Does the scheduler assign lots that would violate Q-time windows or show zero wait time lots waiting in queue for processing behind lower priority lots at a step?
A production schedule typically refreshes in a cadence from every five minutes to up to an hour. Therefore, the validation framework needs to have summary report and analytics (as shown in figure 3) to track the trend of the schedule validity run over run.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure2-table-analytic.jpg) Figure 3: Example of a summary table analytic
### Secondary validation: input data quality and completeness
When there is an incomplete or invalid schedule, validation of the extract transform load/extract transform map (ETL/ETM) layer of the solution is often the reason. For example, tools, lots, and routing steps might be missing due to the incompleteness and incorrectness of the data extraction and transformation process. Data validation reports are needed to make sure the scheduling solution was fed accurate and correct input data. The following are examples of outputs generated when input data is incomplete: - WIP: WIP in the factory are accounted for versus WIP in the scheduling system.
- Tools:All installed and operational tools in the factory are reflected in the scheduling solution input data
- Step: number of steps with no routes mapped to it and no tool groups defined to run it.
- Part: number of parts with no valid route assigned to them.
- Part: number of lots running in the factory on routes not matching the defined routes in the scheduling solution input data.
- Generic resource: of steps that claim a generic resource like probe card or reticle for usage.
- Setup: of stations with no current setups defined.
### Input Data Tracking
Schedule adherence and accuracy is impacted by the relative accuracy of model inputs like process time. To measure the drift and delta of process time, you must be able to compare process time for a part-step-tool group combination versus statistically generated and computed process time based on historical data, as shown in figure 4. This can help the user identify entries which need correction or updating out of cycle (if they have a regular cadence to update those model inputs). There also need to be alerts in the workflow to notify the user about drifts in process time
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/11/figure3-example.jpg) Figure 4: Example of a table tracking process time.
### What’s next
Once these validations have been completed, manufacturers can move on to advanced validations and fine tuning of the schedule. This includes understanding the decision making that went into creating the schedule and consideration of specific KPIs. These are discussed in “Using a framework to validate factory scheduling solution systems, [part 2/2](/semiconductor-blog/scheduling-solution-systems-part-2/).”
**Semiconductor Category:** Semiconductor Scheduling
**Semiconductor Tag:** Semi
---
### [Zero-defect strategy: steering the automotive manufacturing electronic revolution](https://appliedsmartfactory.com/semiconductor-blog/quality/automotive-manufacturing/)
**Published:** April 19, 2023
**Author:** Selim Nahas and Manan Dedhia
**Excerpt:** Increase yield and reduce costs of non-quality in automotive manufacturing
**Content:**
Automotive manufacturers are heavily reliant on getting access to the long list of electronic parts required to keep up with the demands of high performing automobiles. In fact, as this list of parts continues to grow, the need to reduce failures and increase quality control is complex and expensive. Manufacturers who are serious about building a zero-defect strategy need to take people, technology, and economics into the equation as they navigate their journey. Find out how and why automotive manufacturers should be bold and prepared to uncover new ways to build a zero-defect strategy.
[ Read More ](/semiconductor-blog/automotive-quality/)
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [创建蓝图：借助先进的工厂自动化技术来优化生产力](https://appliedsmartfactory.com/semiconductor-blog/productivity/factory-automation/)
**Published:** February 28, 2024
**Author:** Michael Frenna, Global Product Manager, Workflow Automation and Factory Analytics
**Excerpt:** 了解自身现状，探究如何简化部署，保障智能制造有效实施。
**Content:**
半导体在不断发展的技术领域中发挥着举足轻重的作用，决定了现代电子产品在使用方式和应用领域上的发展。 从智能手机到先进的医疗设备，半导体技术驱动着消费者和企业创新的进程。 随着对更高性能和更高能效的需求不断增长，智能制造流程变得越来越复杂。为了提高生产力，芯片制造商们正在向工厂中引入先进的自动化技术。
### 引领实现良率提高、质量改进，并加快产品迭代速度
这种模式转变也带来了生产流程的改变。 优化生产效率、增加零缺陷制造需求的迫切性，促使创新型工厂提高良率、显著提升产品质量，并加快产品迭代时间。
应用材料公司的SmartFactory自动化技术专家团队持续与世界各地领先的半导体制造商合作，助力实现智能、可靠的工厂自动化。 客户信赖我们的团队，来帮助他们探索实现业务目标、迈向全自动化的最佳途径。
### SmartFactory解决方案引领实现全厂自动化
- **决策制定：**晶圆厂复杂决策的自动化。 这包括运营决策，如跑何种货以及何时运行。 半导体晶圆厂的复杂程度很高，每个工艺步骤都有庞大的运行要求。
- **运输：**自动化管理制造工厂内物料的运输。 这包括在多个加工步骤之间传输晶圆，将其储存在洁净环境中，并确保将晶圆及时运送至各工作站。
- **异常处理：**自动响应并解决工厂中的突发事件。 这取代了工厂车间以往发生异常情况时的大量人工干预，并大幅缩短处理问题的时间。
- **学习：**半导体行业的自动化并不局限于实质任务。 量化分析和人工智能被用于实时监控设备性能、预测维护需求和优化生产流程，最大限度地减少停机时间并提高效率。
实现全自动化有诸多优势。 其一是制造商可以通过尽可能地减少人为失误、缩短生产周期和提高产出等方式来提高效率。 自动化可以在保障质量的同时实现全天候生产。 其二在于一致性和质量。 自动化流程可以提供稳定一致的结果，减少缺陷并改善产品质量。 在追求精益求精的芯片行业中，这一点至关重要。 随着半导体产品需求的不断增长，借助自动化流程，制造商能够在不对基础设施进行重大调整情况下轻松扩大生产规模。 另一个重要的优势是长期成本。 虽然最初的建设成本可能较高，但实现自动化后可以降低人工成本、提高良率、有效利用资源，从而实现长期成本节约。
### 克服部署方面的挑战
尽管自动化在半导体行业中拥有诸多优势，但也面临着挑战。 各类技术方案整合、自动化工厂前期准备、人才储备、硬件/软件采购和安装部署都可能是需要克服的重大障碍。 克服这些挑战可能是一项艰巨的任务，甚至使一些工厂不愿采用更高水平的自动化。 然而，智能制造所面临的挑战并非无法克服，只要制造商有明确的愿景和路径，就能克服挑战达成预期的计划和目标。
在与客户的合作中，我们发现，如果制造商能够定义实现目标所需的每个环节，他们就能更容易地执行全自动化计划。 首先，企业需要明确自身所处的自动化阶段，进而理解他们期望达到的自动化程度，最终规划实现目标所需的步骤。
为帮助客户明确自身所处的自动化阶段，我们将制造工厂划分为三种不同的类别：手动、半自动和全自动工厂。 每个类别代表了标准部署的工业自动化水平。 如图1所示，三种不同的工厂自动化水平。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-1.png) 图1：识别工厂自动化水平
如图2所示，一旦企业理解了其自身的自动化水平，他们就可以规划后续步骤。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-2.png)
[  ](https://appliedsmartfactory.com/wp-content/uploads/2023/09/picture-3.png) 图2：自我识别自动化阶段的步骤
### 展望未来
工厂自动化正在重塑半导体行业，使制造商能够满足实施先进电子产品的日益增长的需求。 借助机器人、人工智能和量化分析，将自动化技术的效率、质量和可扩展性提升到前所未有的水平。 随着技术的不断发展，自动化与半导体生产改进的结合将推动创新，塑造智能制造的未来。
了解更多有关全自动化的信息，请浏览： [https://appliedsmartfactory.com/zh-hans/semiconductor-blog/move-to-full-automation/](/zh-hans/semiconductor-blog/move-to-full-automation/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [派工规则参数的渐进优化](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimization-of-dispatch-rule-parameters/)
**Published:** September 15, 2022
**Author:** Jeong Cheol Seo
**Excerpt:** 对派工规则的参数进行动态优化，从而实现更高效的批次排程。
**Content:**
在半导体制造过程中，对批次进行排程会对整个晶圆厂的效率产生显著影响。 这种排程过程称作 *“作业重入的流水车间 ”*，因其难以建模和有效解决而被人们所熟知。 问题的根源来自于对参数值的调整，以及找到基于每个晶圆厂情况的优化组合。 派工规则逻辑包含众多参数，其性能在很大程度上依赖于根据在制品和站点可用性对参数值进行微调的能力。
为了解决这一难题，我们基于渐进优化法并结合模拟退火法开发了一种高效的参数调整方法。 结果表明，这一方法胜过了其他基准，可成功地对派工规则的参数值进行动态优化。
如需详细了解我们开发的这一方法，请观看下方的完整演示：
### 准备好联系我们，了解关于派工、排程或其他解决方案的更多信息？
[ 联系我们 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [降低生产杂讯，提高运营效率](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/boost-operation-efficiency/)
**Published:** September 21, 2023
**Author:** Bing Wang, Director of CIM Solution
**Excerpt:** SmartFactory 团队推出全新警报处理解决方案
**Content:**
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/10/section.png)
您知道吗？在产量较高的制造工厂中，各种系统或设备每秒钟可发出多达 1000 个警报。 事实上，管理如此繁多的并发警报或警告成为使操作人员分心的主要因素，这意味着他们可能会错过导致晶圆报废或异常的关键警报。 操作员遇到这些问题时，周围充斥着大量误报警报，从而对警报变得不再敏感。 因此对警报的响应被延误，设备长时间处于问题状态，也可能造成错误处理的晶圆继续运行而未被发现。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/10/alarm-management-works.jpg) 图 0：警报管理工作原理概述
每天处理成百上千个警报仍然是众多高产量制造工厂面临的常见运营挑战。 事实上，为了应对这种工作负载，制造商需要时刻保持实时的警报管理和响应能力。 借助一种有效管理工厂警报以实现优化运营的解决方案，意味着操作员能够集中精力处理那些需要立即解决的关键警报，并过滤掉那些不太重要的警报。
我们推出全新 SmartFactory Alarm Management 警报管理解决方案，旨在实时应对上述警报管理挑战。 图 1 显示了过滤警报如何提高生产率。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/10/fig1-alarm-validity.png) 图 1：基于规则过滤警报使操作员能够专注于有效的警报
### 优势亮点
**预防异常，提高良率**
由于警报已经过滤，操作员可以快速识别出关键警报，从而更容易快速解决优先问题，避免误处理晶圆误。
**减少设备停机时间，提高设备利用率**
对目标警报的更快响应使技术人员和工程师能够更迅速地采取适当的行动，延长设备正常运行时间。
**缩短生产周期，提高产量**
降低生产杂讯、整合警报数据，使用户能够快速解决生产问题， 进而提高劳动生产力和运营效率。
Manufacturers using SmartFactory Alarm Management see improvements in operations efficiency, throughput, and yield
### 产品亮点
- 在一个单一位置集中对警报进行实时处理
- 通过一致的程序，简化来自各种系统的警报管理
- 分级过滤警报，选择最佳警报规则
- 对警报重要性进行分级，采取最佳警报措施
- 通过重复警报消除算法，减少生产杂讯
- 整合警报数据，快速排除故障和解决问题
您是否需要了解更多有关 SmartFactory Alarm Management 解决方案的信息？
[ 联系我们 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Bingeworthy, Semi, Newly Released
---
### [提升您的数字体验](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/enhancing-your-digital-experience/)
**Published:** January 31, 2022
**Author:** Todd Snarr
**Excerpt:** 通过改进仪表板、报告、操作和工作流转变用户体验、图像和功能。
**Content:**
用户体验（UX）是开发人员用来为客户创建最具功能性和最有效产品的过程。其关乎为用户塑造数字体验，提供与他们互动的最佳方式。 本篇博客简要概述了自动化产品部（APG）在可用性方面所做的努力，重点介绍了我们的一路历程和所见，以及在用户体验方面的发展方向。
### 可用性更好的案例
一项广为引用的用户体验设计统计数据表明，全球计算机安全软件公司 **McAfee 因为对用户界面进行了简单的**重新设计，减少了 **90%** 的支持呼叫，为客户带来了更好的整体用户体验。1
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/mcaffee-stat-.png)
可悲的是，用户体验是设计中经常被忽视的一个方面。 在半导体行业，可靠性最为重要，而且这有充分的理由。 任何由软件**可靠性**问题而引起的自动化系统的中断都可能造成**数百万美元的收入损失**。因此在过去，如果应用程序可靠并可以运转，那么对于企业应用程序来说，糟糕的用户体验在是“可以接受的”。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2021/12/ux.png)
### 我们的历程
应用材料公司自动化产品部开发的软件在全球高产量工厂中得到广泛验证，并且技术运作非常成熟。 在过去 **30** 年里，我们的优势和不同之处在于设计和部署运行可靠、功能丰富的软件以提供卓越的结果；诚然，我们对适用性、界面设计或用户体验的重视程度仍有不足。
然而时代在变迁, 如今新一代的晶圆厂管理者和运营商对可用性和易用性有**更高的期望.**
### 我们所见到的
今天，我们看到各家公司和多数经济体都在加速推进**数字化转型**。 我们已经看到人们对软件可用性的期望大幅增加，越来越重视智能手机的便携性、3D 渲染设备、简化的 KPI 统计数据和更好的深入挖掘。
### 我们的前进方向
我们了解这些实际情况，并于过去几年在创新技术上进行了大量投资，包括从云计算、移动端和高级分析解决方案到下一代用户体验（UX）/用户界面（UI）技术和直接响应客户需求的能力。 通过此项投资，我们完成了以下工作：
- 成立**用户体验设计团队**来创建新的设计流程和工作流程, 确保在软件开发中一致地应用以用户为中心的设计。
- 部署带有现成接口库和组件的 **UI 套件**，只需正常开发时间的四分之一即可完成功能的构建。
- 启动改善与客户**合作**和**协作**的流程, 让客户参与到设计过程中，提升了其主人翁意识。
凭借 UI 套件项目，我们正在通过改进的仪表板、报告、操作和工作流程来改变用户体验、图像和功能。 从客户的第一次接触，到用户研究和信息架构，直至软件的每一个屏幕交互，我们的用户体验设计师参与了整个产品生命周期。
此外，我们最近还进军新市场，在制药行业推出 [SmartFactory Rx](https://appliedsmartfactory.com/zh-hans/pharmaceutical/)解决方案。 我们的软件开发团队使用应用材料公司新用户体验设计流程和工作流程，在开始与客户一起定义产品的同时迅速建立产品特性原型，然后根据客户和终端用户的持续反馈构建产品。
由于产品使用 UI 套件构建，软件工程师拥有现成的接口库和组件，它们可以快速组合在一起，只需用正常开发四分之一的时间，即可构建强大的新功能。
总而言之，我们将继续全力维护自己在可靠、稳定的软件解决方案方面的长期声誉。 不过，除此之外，凭借用于构建同类最佳用户体验解决方案的新框架，我们现在可以更好地为用户塑造数字体验，提供一种与用户加强交互的方式，以实现更好的整体用户体验。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [您是否希望减少或避免制造软件系统意外停机的情况？](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/manufacturing-software-systems/)
**Published:** August 17, 2023
**Author:** Dan Meier, Director of MES Product Management
**Excerpt:** SmartFactory Monitor 可以通过性能趋势分析和预测分析，防止出现影响工厂运行的问题。
**Content:**
制造商面临从工艺问题到设备故障在内的诸多挑战。 然而，一个通常被忽视的挑战是，当支持工厂运行的关键软件和服务器出现问题时，人们往往不会注意到， 直到出现无法挽回的后果。当一个工艺设备发生故障时，会造成不便，但如果制造执行系统 (MES系统) 出现故障，整个工厂将陷入瘫痪。
鉴于工厂的正常运行时间至关重要，您很可能已经制定了监控指标来监测工厂运行情况，并且有质量计划来进行改进。 确保产品在工厂的各个工序之间连续流动，并得到正确处理，是保证您公司盈利的关键。 制造软件系统在提高生产效率和质量方面也发挥着重要作用，无论它们是否正常运行。 然而，虽然我们不愿意去面对这一点，但有时服务器会宕机，网络也时而会出现问题。 有时，由于附近正在进行设备安装， 整个服务器机房的电源会意外关闭，这将导致计划外的停机，甚至可能导致整个工厂停工。 这对业务的影响是巨大的。
对于一个规模适中的产量较低的晶圆厂来说，一小时的意外停机就会给公司造成 1 万美元的损失。 对于一个中等产量的晶圆厂来说，损失可能是 10 万美元。 而对于一个先进的、产量较高的晶圆厂来说，损失可能高达 100 万美元。 因此，找到减少甚至避免制造软件系统意外停机的方法至关重要。 SmartFactory Monitor 可以帮助您实现这一目标。
SmartFactory Monitor 是一个实时监控软件解决方案，让您能够及时发现生产系统中的问题，并立即采取纠正措施，以确保生产系统不受影响。 在其最基本的形式中，它提供了一个可定制、易于理解的仪表盘，显示您生产系统的当前状态。 这样，当出现问题时，几乎可以无缝地查看和发送通知。
其关键特征之一是可定制性，您可以创建自定义视图，以显示随时间变化的性能趋势。 其预测分析能力可在性能异常影响生产之前检测出这些异常。
SmartFactory Monitor 可在普通硬件设备上运行，进程占用内存空间小，操作系统可任意选择。 另外，它与 SmartFactory 智能工厂解决方案软件产品组合中的其他产品预集成，能够追踪您的所有制造系统——应用程序、数据库以及 Windows 和 Linux 服务器。 该系统可实时监控系统性能日志、错误日志、事件日志、应用程序日志、系统日志、服务器日志等一切可以反映系统性能和健康状态的信息。
各种来源的数据都被汇总到 Splunk 软件中，该软件能够捕获、索引和关联实时数据。然后这些数据可以生成自动通知并实现可视化效果，以突出数据的趋势并发现问题。 此外，汇总到 Splunk 的数据还可用作机器学习算法的训练数据，从而实现预测分析，以避免问题在上升为工厂级别的问题之前被识别和解决。
预构建的仪表盘可以让您快速启动和运行，监测所有系统日志。 使用 Splunk 软件，您可以轻松地实现系统性能可视化，并利用应用材料公司工程师开发的复杂预测算法检测出趋势、异常和异常值。
SmartFactory Monitor 提供一套全面的生产监控功能，可应对制造商面临的众多关键支持系统挑战。 其主要目标是通过缩短发现和解决系统问题的时间，减少工厂意外停机时间。 最终，通过性能趋势分析和预测分析，帮助预防对工厂运行产生影响的问题。
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Semi
---
### [实现工厂自动化是应对生产效率挑战的关键](https://appliedsmartfactory.com/semiconductor-blog/productivity/factory-automation-is-key-to-overcoming-productivity-challenges/)
**Published:** November 25, 2021
**Author:** Shekar Krishnaswamy
**Excerpt:** Shekar Krishnaswamy 分享关于计划、排程、设备控制及工厂整体运营如何改善生产周期、工厂产出、成本和客户交付的见解。
**Content:**
Shekar Krishnaswamy 分享关于计划、排程、设备控制及工厂整体运营如何改善生产周期、工厂产出、成本和客户交付的见解。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [如何借助机器学习和专家系统来推动工艺质量的提高](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/quality-using-machine-learning/)
**Published:** September 14, 2022
**Author:** Vishali Ragam, Global Product Manager, SPC
**Excerpt:** 了解这项技术如何成为在制造业中打造“会思考的机器”的基石
**Content:**
您是否曾想过，杂货店会如何理货？ 比如，杂货店是如何知道要把黄油放在面包旁边的？ Netflix 是如何根据观看历史推荐电影的？
这些就是基于数据提取技术的“购物篮分析”示例，这项技术也叫做频繁模式挖掘。 这种技术会寻找重复出现的关系，从而在不同数据项之间找到关联。 当我们将这项技术运用到半导体制造时，它帮助我们深入了解工艺以实现快速的质量提升。 此类算法完全能够在尽可能减少人为干预的情况下处理海量数据，从而获得最优的解决方案。 应用材料公司的团队采用了机器学习的研究，这些研究成果帮助我们识别生产设备和工艺流程的行为，从而进行产线的定制化、持续和自动化的调整。
如需了解更多详情，请查看全文：
\[pdf-embedder url=”/wp-content/uploads/2022/09/Datasheet\_Thinking-Machines-Inside-Factories\_CN-1.pdf” height=”1000″\]
[ 下载 PDF 文件 ](/wp-content/uploads/2022/09/Datasheet_Thinking-Machines-Inside-Factories_CN-1.pdf)
### 如需了解更多信息
[ 联系我们 ](https://appliedsmartfactory.com/zh-hans/connect/)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [优化工厂绩效](https://appliedsmartfactory.com/semiconductor-blog/productivity/optimize-factory-performance-2/)
**Published:** November 25, 2021
**Author:** Productivity Solutions Team
**Excerpt:** Madhav Kidambi介绍如何提高从企业级别到工厂车间的收益。
**Content:**
Madhav Kidambi介绍如何提高从企业级别到工厂车间的收益。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [Automotive quality: striving for zero defects](https://appliedsmartfactory.com/semiconductor-blog/quality/automotive-quality/)
**Published:** February 23, 2022
**Author:** Selim Nahas and Manan Dedhia
**Excerpt:** Learn how to steer the automotive electronic revolution by doubling down on a zero-defect mindset to reduce the cost of non-quality.
**Content:**
The last 10 years have experienced an explosive demand for electronic parts(v). In 2016, for example, a top-of-the-line Bentley required 110 pounds of wiring with 90 computers to connect. In 2020, similar wiring and connectivity requirements are prevalent in most cars that people buy. The automotive industry is among the least dependent on leading-edge supply chain technologies, instead choosing to use parts made on legacy nodes with proven reliability. Most of these legacy node fabs are semiautomated to manual and have been in production for 15 to 30 years. The economics that drive the decision to use 150mm and 200mm facilities is also changing—although not for the foreseeable next five years. Within the Automotive Electronics Council (AEC) and International Standards Organization (ISO), recent announcements on increased safety, design for test (DFT), and design for manufacturability (DFM) reflect the inevitable rise of Level 4 and Level 5 autonomous vehicles and automotive original equipment manufacturers (OEMs) and Tier 1s. These announcements have rightfully doubled down on a zero-defect mindset to reduce the cost of non-quality.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/automotive-electronic-scaled.jpg) Figure 1: The automotive electronic revolution.
### Anatomy of field returns
The International Automotive Task Force (IATF) standards essentially require us to strive for zero defects. If we look at where the industry performs today, data suggests that the automotive supply chain resides at approximately one defective parts per million (PPM) or above. When reviewing field returns that constitute either warranty returns or zero-kilometer failures (Figure 2), the field estimates suggest that roughly 25% of the failures come from the front end fab. Within this data set, 50% of failures that leave the facility essentially have a parametric test, but somehow elude our ability to detect the problem. Another 30% have no test coverage and therefore, no detection. Another 15% are undefined, meaning we can’t assign the failure to any specific cause. This third category is essentially the unknown. In these cases, no real corrective action is deployed and the gap in detection persists. And finally, approximately 5% of the failures reflect disagreements within the supply chain as to the origin of the failure.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/packaging-contributions-scaled.jpg) Figure 2: Fab and packaging contributions to field returns.
### What eludes the supply chain
The constituents of the current supply chain – fab, packaging, and electrical test – can be evaluated as detection gates, with an increasing granularity of detection, but also in the order of increasing cost.
From a wafer fab perspective, automotive components can be broken out into the following buckets: safety/advanced driver assistance systems (ADAS), propulsion, and infotainment. First, the safety/ADAS bucket includes sensors (microelectromechanical systems \[MEMS\], optical, temperature) that are made on larger nodes, or radio- frequency (RF) components in specialty fabs (GaAs, GaN, SiGe, and so forth) with a lower than average level of automation and detectability. Second, propulsion is an increasingly large group with the advent of electric vehicles (EV) and can be anywhere from 180nm to 32nm. This bucket includes power components and engine control units (ECUs). These items would be considered mission-critical components in a way, requiring a higher level of reliability. Finally, infotainment does not warrant the same level of reliability and has some flexibility in terms of sampling the latest and greatest fab nodes.
Given the wide range of fab nodes that are sampled in the automotive supply chain, we are subject to a variety of available quality levels. Reducing cost per component to maximize profit also means reducing the acceptable quality level to an acceptable bare minimum. Every detection step is a non-value-added step, and hence the cost is passed off further downstream. This means that even with the best fabs in the business, PPM-level detection is neither offered, nor discussed for parts that are in volume production. This situation deteriorates further as older nodes or specialty technologies are used.
The best chance for detecting defects on a part is with electrical testing, which entails wafer probe or final automated test equipment (ATE) in packaged form. Conceptually, if the part has been characterized thoroughly and built on a known technology with a low defect rate, then any remaining PPM-level failures can be captured at the electrical test step. Characterization depends on: 1) the design failure mode and effects analysis (DFMEA) being able to simulate all failure modes; 2) product engineers being able to test the parts to cover all customer mission profiles; and 3) with increasing software components in the parts, ensuring that data fidelity is maintained throughout.
Most parts do not have wafer-level traceability, which further degrades the ability to tie back failures to fab processing as warranted. In the face of meeting ultra-aggressive customer timelines and cost pressures, we again see the acceptable quality level of this stage reduced to the bare minimum, which ensures that the outgoing product does not receive the full benefit of detection at electrical test. This translates to most customer failures being test-related issues and increased costs of non-quality and further results in the motivation to move towards a holistic approach as a matter of progress and safety.
### Framing the issue
If we are to consider a strategy to move the needle closer to a zero-defect concept, then several things must change from the way facilities operate today. Most of these legacy facilities are semi-automated or manual. This means that they fundamentally have a multitude of point solutions and disciplines to govern their quality standards. Simply put, they neither capture all the data needed to govern their processes effectively, nor analyze
this data in a manner that allows for speedy and effective feedback. Based on field returns and internal failures, we have seen how far this strategy can take us. It is unlikely that we will be able to breach the 1PPM barrier consistently without rethinking the process entirely.
To paraphrase the problem, we have an inability to scale our detection, coupled with the inability to assure our test coverage compounded by an inability to assign root cause with total certainty in too many of our cases. All these problems result from a patchwork approach to quality and a siloed perspective on quality data management. A holistic approach would streamline information sharing and facilitate first-timeright decision-making (Figure 3). So why haven’t systems evolved to be holistic?
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/holistic-intelligent-scaled.jpg) Figure 3: Moving to holistic and intelligent systems.
### Adopting the needed changes
The fundamental flaw with point solutions is that they don’t address the challenging issues observed at the fab level, with packaging and surface mount lines. The solution to this problem originates from a holistic approach. Holistic in this case refers to the ability to look at the entire manufacturing line. Beyond the single facility, holistic means the entire supply chain as a single entity. Moreover, we must adopt new principles of signal detection to successfully manage chart scaling. Most systems today are predicated on the idea that if a measurement chart is set up properly for a known parameter, it will detect anomalies accordingly. While in principle this is true, it becomes a daunting problem to manage 100,000 charts in a single facility with a skeleton crew. Each measurement value irrespective of control and specification limit is given a meaning that relates to the overall quality of the device. To put it another way, it’s the ability to review the effect the sum of variation has on the performance and reliability of a part. This approach is not currently practiced in the industry.
### Cost of implementation and training
The rate that semiconductor fabs accommodate new automation solutions poses a barrier to being able to quickly change the quality capabilities of the fab. Most automation systems today are still fundamentally built around the same paradigm seen over the last 20 years—charts driven by Western Electric rules and out-of-control action plans (OCAPs) that are based around the errant chart. By the time the industry accessed streamlined automation solutions, legacy manufacturing facilities had long since amortized their building costs and depreciation regimes, running the business with just the operational essentials. This situation left minimal resources for new development because the revenue capacity of these facilities does not easily support the required investment to resolve any singular problem.
Holistic automation solutions address systemic problems rather than single gaps. Half a million dollars can easily represent half a percent in profits depending on the facility, which is a significant erosion to margins. Furthermore, the return on investment is either too small to justify the risk or takes too long to achieve. Point solutions can easily range from $150K to $750K, which is a difficult barrier to breach. Understanding them requirements and the intricacies of the domain and the information technology (IT) infrastructure required to support it takes a substantial investment. There is a significant cost to define and test disruptive systems that can replace the multitude of current automation practices. Unless a solution can provide a systemic resolution to quality – meaning resolve several high-value targets – these facilities will not be able to invest. These paradigms need to straddle the entire supply chain.
Most personnel in these facilities are not focused on developing new automation solutions, but rather on manufacturing reliable parts cost effectively. So, accessing the technology to build a holistic and streamlined quality system is not a realistic expectation for these facilities. It would require a financial and manufacturing mindset change. A strong holistic quality program requires both automation and learning systems for those responsible for operating it. While numerous opportunities exist to automate tasks and decisions that historically were manual, the expectation will remain high on understanding the meaning of signals and quality metrics.
### Moving to zero defects
There is certainly a hierarchy of automation need in legacy facilities. Automated data acquisition is a good starting point, followed by a centralized alarm management system to connect signal’s and prevent moving materials into process tools that should not run product. A significant need also exists to reduce human error as part of the processing. Recipe management systems play a key role as does centralized configuration management. After the automation layer is in place, the ability to expand the capabilities increases. For instance, once the statistical process control (SPC) practices of the fab access the raw data of a wafer measurement, the engineering community can make use of it to isolate within-wafer variation problems. Qualifying new products is time consuming and preparing for production can be slow and prone to missing opportunities to define needed tests. The more understood the variation sources of a facility, the more opportunity to quickly qualify new products. This knowledge will directly impact the gap of test coverage that allows 30% of field failures to persist.
Moving these traditional good practices to a holistic approach requires some integrated infrastructure. The first step is to define what holistic means in this context. Holistic is the ability to understand the interdependent behavior of the process steps. The control plan illustrates the known measurements associated with any product. The automation system will need to provide users with the ability to define interdependency relations of different process steps, as outlined in the control plan and process failure modes and effects analysis (FMEA). At runtime, the system will consume the data coming from multiple process steps, as defined in the control plan, and outline which data does not fit the population that we
expect for the specific processes. This will need to be done using real-time data tools because a single decision will require users to assess 15 parameters with 12 to 20 sites for each. Each site will need to have a statistic and be broken down to divulge within-wafer variance profiles, wafer-to-wafer variation within the same process step, and finally, variation inherited from upstream steps. This approach will reduce the variation arriving at final test and therefore, reduce the chance of failing parts leaving the facility. More important is the change that this approach will impose on final test validity. A more stringent variation verification will become more effective to capture a greater degree of nonconformance.
Another key difference is that holistic systems are not only error driven, but also sensitive to variation within the specification limits. Data shows that this is happening in facilities that have yields ranging from 88% to 92%. The frontend fabs combined with the packaging operations account for an approximately 0.76PPM failure rate. Devices within the specification limits will ultimately be functional, but not necessarily the same from a performance or longevity perspective. Process problems such as whiskers and bridging will elude many of these tests, causing shorts in the field. So, the automation system provides users the ability to define qualitative stack-up of step attributes, which is a measure of acceptable variation for a
given problem.
It is true that other factors play a role in the overall failure rate including electrostatic damage and other forms of mishandling that can occur in several places throughout the supply chain. This highlights the need to have rapid genealogy of quality attributes that include design. Design is the concept of parts that have been made for a long time but are now used in a new way that is not suitable for their reliability. This constitutes an approximately 0.15PPM contribution to failures in the field. The cases that are “unknown” represent an approximately 0.21PPM contribution to the failures and are a major liability to the vendor. In the case where no cause can be assigned, the small vendors will be held accountable for the failure and will have the cost deducted from their agreement with the big car manufacturers. If this ability could be automated to straddle the front end and back end and ultimately include the surface mount technology (SMT) line, then rapid identification would become possible for any given device and cause. The speed of resolution in this case will impact cost of liability and more importantly, safety. Unless the design of new automation systems adopts these guiding principles, it will be difficult to expect any supply chain to converge effectively towards zero defects (Figure 4).
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/02/zero-defects-scaled.jpg) Figure 4: Striving for zero defects.
**REFERENCES**
Original Equipment Suppliers Association
Automotive defect recall report2019
**Semiconductor Category:** Semiconductor Quality
**Semiconductor Tag:** Semi
---
### [How to drive process quality using machine learning and expert systems](https://appliedsmartfactory.com/semiconductor-blog/ai-ml/quality-using-machine-learning/)
**Published:** June 20, 2022
**Author:** Vishali Ragam, Global Product Manager, SPC
**Excerpt:** Learn how this technique has become a cornerstone to build thinking machines into the world of manufacturing.
**Content:**
Have you ever wondered how grocery stores arrange their products? For example, how do they figure out how to display butter so close to the bread? How does Netflix recommend a movie based on our watch history?
These are examples of “shopping basket analyses” based on a data extraction technique commonly referred to as frequent pattern mining. This type of technique looks for recurring relationships to find correlations between different data items. When we apply this technique to semiconductor manufacturing, it helps derive an in-depth understanding of the process to attain rapid quality enhancements. Such algorithms are fully capable of handling high volumes of data with minimal human intervention to push the best-in-class material. Our team at Applied, has adopted machine learning studies, which explicitly expose the behavior of manufacturing tools and processes for customized, continuous, and automated adjustments.
For more additional details, check out the full article:
[pdf-embedder url=”/wp-content/uploads/2022/06/Thinking-Machines-Inside-Factories.pdf” height=”1000″]
[ Download this PDF ](/wp-content/uploads/2022/06/Thinking-Machines-Inside-Factories.pdf)
### To learn more
[ Connect With Us ](/connect)
**Semiconductor Category:** Semiconductor AI/ML technologies
**Semiconductor Tag:** Semi
---
### [准备好紧跟市场对生产效率的要求了吗？](https://appliedsmartfactory.com/semiconductor-blog/productivity/ready-to-keep-pace-with-productivity-demands-in-the-market/)
**Published:** November 25, 2021
**Author:** Productivity Solutions Team
**Excerpt:** 了解如何使用集成的生产效率解决方案缩短生产周期、管理瓶颈问题并实时响应事件。
**Content:**
了解如何使用集成的生产效率解决方案缩短生产周期、管理瓶颈问题并实时响应事件。
**Semiconductor Category:** Semiconductor Productivity
**Semiconductor Tag:** Semi
---
### [使用具有维护管理功能的即插即用型Spares和 ERP 模块可降低集成成本，减少复杂性，提高设备综合效率 (OEE)](https://appliedsmartfactory.com/semiconductor-blog/manufacturing-execution/using-plug-play-spares-and-erp-modules/)
**Published:** April 21, 2022
**Author:** John Robinson
**Excerpt:** 合适的时间，合适的设备，合适的部件
**Content:**
如今，一家传统的 300mm 半导体前道晶圆厂可能需要数千种工艺和计量设备，才能将晶圆裸片加工成令人印象深刻且灵活的器件组件。 每种设备都非常复杂，且功能固定，因此必须仔细协调所有设备以确保设备综合效率 (OEE)。
### 数以百万计的部件
维护和备件的复杂程度，可以光刻工艺为参照。 在光掩模设置步骤中，用于 Litho 曝光胶片的掩模必须在类似扫描仪下仔细检查是否存在缺陷。 Zeiss AIMS 检测设备就是一个例子。 这套具有特定功能的设备中包含来自 134 个不同供应商的 4,500 多个子系统和 64,000 件单独部件。 这是令人难以置信的部件阵列和巨大的管理挑战——不仅涉及供应链，还涉及关联部件和部件编号 (P/N) 所涉及的维护和工作。
### 在合适的时间使用合适的部件
为管理此复杂流程，晶圆厂必须保证部件供应。 对于所有成千上万的设备和数以百万计的备件，许多最必要的或需更换的部件都由工厂内部提供，可能存放在晶圆厂内，也可能存放在位于工厂附近的某个仓库，以便随时可用。 其他较长交货时间的部件，则根据需要从原始设备制造商 (OEM) 和第三方供应商处发货和订购。
所有这些部件的复杂性都会影响单个设备的设备综合效率 (OEE)，因为部件和 P/N 必须与设备维护工作相关联。 当为晶圆厂中的设备计划或触发维护工单时，所需的备件必须可用并与该工单相关联。 考虑到可能无法在合适的时间对合适的零件进行维护，需要有效地管理 P/N 与维护工单的关联，以降低复杂性并确保合适的部件安装在合适的设备上。
### 部件信息交换
图 1 所述为此部件关联过程，显示了分段和维护阶段的部件流程，分为物理系统和逻辑系统。 通过底部显示的物理系统，将零件从实际供应商转移至仓库，然后转至设备。 为了促进备件到维护工单的自动化管理，我们还展示了必要的逻辑流程，其中通常由 ERP 系统维护的大量备件库存必须与维护管理系统交换 P/N 信息。 两个系统之间重叠和数据交换需要仔细协调和系统集成，以确保使用合适的设备维护合适的备件。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/the-flow-of-parts-through-various-lifecycle-phases.png) 图 1：部件在各个生命周期阶段流动，分为逻辑和物理系统 （从供应商和设备到 ERP 和维护管理应用程序）
应用材料公司拥有众所周知的基于 Xsite™ 技术的维护管理能力，该技术可有效用于自动化维护计划，以及根据 SEMI E10 状态追踪设备维护性能。 这种跟踪能力可根据 MTBF 和 MTTR 指标对设备综合效率（OEE）进行测量，这些指标可在使用 Xsite 技术进行维护期间自动捕获。
### 客户的心声
为了增强此类维护管理功能，我们与客户密切合作，确认从备件集成到维护中出现的关键挑战。
1. 自动化和管理与维护工单**关联的备件**
2. 通过允许 P/N 在这两个系统之间移动，降低系统复杂性
3. 可与 ERP 系统实现**开箱即用的集成**
考虑到这三个客户优先事项，我们发布了两个可选模块 Spares 和 ERP，这两个模块现在都可用于维护管理。 图 2 突出显示了 Xsite 技术框架中的这两个模块。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2022/03/the-new-spares-and-erp-modules.png) 图 2：图中以橙色显示的新 Spares 和 ERP 模块可与其他模块选项共用， 通过 Xsite 技术内核实现这些模块的即插即用
### 这些模块有何作用？
Spares 模块基于大家熟知的 INV 模块，并有以下作用： 1. 将工单与 P/N（序列化部件和耗材部件）相关联
2. 在 PM 期间消耗备件
ERP 模块： 1. 标准化数据字典和服务器端规则 (SSR)，以实现与 ERP 的快速开箱即用集成
2. 允许 P/N 追踪历史记录和查询
3. 确保 P/N 消耗并返回 ERP
### 这为半导体晶圆厂带来哪些好处？
这些模块对制造商的基本好处包括：
1. **数据可追溯性**（P/N 关联和使用计数）
2. **通过 P/N 与工单关联，在合适的时间提供合适的部件，提高平均修复时间（MTTR），从而减少维护停机时间。**
3. 通过提供标准接触点和简单的 SSR 配置**降低ERP 集成成本**
4. **降低复杂性：**P/N 在系统之间移动，不需要在两个位置都存在
5. **提高设备综合效率 (OEE)：可以识别备件异常值，原因是可以查询 P/N 并将其与越界 MTBF 指标相关联**
**Semiconductor Category:** Semiconductor Manufacturing Execution
**Semiconductor Tag:** Popular
---
## Events
### [Semicon west 2026](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2026/)
**Published:** August 31, 2026
**Author:** Sushmita Kumari
**Content:**
# Applied SmartFactory® Speaking Session
### A New Design Mindset to Enable
### AI-Driven Factory Automation
Thursday, October 15, 2026 | 10:55 AM – 11:15 AM
Selim S. Nahas
Director of Strategic Marketing
Automation Products Group | Applied Materials
October 13–15, 2026 | Moscone Center, San Francisco
**When**
**Thursday, October 15, 2026**
10:55 AM – 11:15 AM
**Where**
**Moscone Center, North Hall**
Expo Floor | Smart
Manufacturing Pavilion
**Session Track**
**Automation & Equipment**
Toward Fully Autonomous
Factories & Facilities
### **Discussion**
**Factory automation is at an inflection point. The vision: a new generation of fully autonomous process tools, deeply integrated with the CIM system.**
The success of autonomous tools depends on establishing a data and context relationship with broader fab operations. Making process tools autonomous in concert with the fab is not entirely new, but the design paradigm, and the performance gains AI makes possible, are well beyond today’s factory system capability.
The industry has largely operated at the lot level for Advanced Process Control. Autonomous tools require the ability to operate at the **wafer level**, and that demands an entirely new set of capabilities.
This session explores the design changes required to reach these new levels of factory performance — including the distributed architectures needed to scale factory-wide, and how machine learning and agentic solutions are enabling a new level of learning. These capabilities have proven themselves in point solutions and applications; factory-wide rollout remains the challenge.
#### **What you'll take away**
- Why wafer-level control — not lot-level — is the prerequisite for autonomous process tools
- The distributed design patterns required to scale automation across an entire fab
- Where machine learning and agentic solutions are already delivering, and why factory-wide rollout stalls
- Projections for capacity and yield gains as these new design concepts are adopted
Selim S. Nahas
Director of Strategic Marketing
Applied Materials | Automation Products Group
**For questions, contact:**
Selim S. Nahas
[Selim\_Nahas@amat.com](mailto:Selim_Nahas@amat.com)
**Event Category:** Semiconductor
---
### [Semicon India - 2026](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2026/)
**Published:** August 7, 2026
**Author:** Sushmita Kumari
**Content:**
SmartFactory Symposium India
Advancing India’s Semiconductor Manufacturing Ecosystem
Fri Sep 18 at 12:00 PM – 4:00 PM
Conference Room 405, Convention Centre, IICC
#### Don’t miss out!
Join us at SEMICON India to learn how semiconductor manufacturers are leveraging our Applied SmartFactory® fully integrated automation solutions to enhance quality and productivity in factories of any size.
Featured highlights include:
- Exclusive keynote insights from a semiconductor industry leader
- The launch of a new Applied Materials and TCS joint thought leadership paper outlining the journey from automation to autonomous semiconductor manufacturing
#### Topics Include
- Digital infrastructure for factory scale-up
- Practical use cases for productivity, quality, and decision-making
- Strategies to accelerate time-to-market and volume ramp
- Lessons learned from leading semiconductor manufacturers
#### Agenda Highlights
Friday, Sep 18 at 12:00 PM – 4:00 PM
Conference Room 405, 4th Floor, Convention Centre,
Yashobhoomi / IICC, Dwarka, New Delhi
*(Conveniently held during SEMICON India 2026)*- Check-in & Networking Lunch
- Welcome & Keynote
- Technical Sessions
- Expert Panel Discussion
- Closing Remarks
*\*Final agenda details to follow.*
Register Now
All fields marked * are mandatory.
First Name: \*
Last Name: \*
Business Email: \*
Country: \*
Please select countryAfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Job Title: \*
Department: \*
Company Name: \*
No. of Employees: \*
Please select1-2021-200201-10,00010,000+
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
#### For questions, contact:
**Applied Materials**
[Joy\_Thomas@amat.com]()
**Tata Consultancy Services**
[Preeti.Choudhary@tcs.com]()
**Event Category:** Semiconductor
---
### [SmartFactory Symposium Penang](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-symposium-penang/)
**Published:** May 19, 2026
**Author:** Sushmita Kumari
**Content:**
### SmartFactory Symposium Penang
### Smart Manufacturing Reimagined with AI
### Smarter Decisions. Faster Outcomes.
8:45 AM – 4:20 PM | July 16, 2026 | Amari SPICE Penang
[ Register ](#register-now)
#### Don’t miss out!
Explore how AI is advancing smart manufacturing, from intelligent equipment to faster decision-making, while connecting with industry peers.
#### Agenda Highlights
- **08:45 AM – 09:10 AM:** Check-in reception
- **09:10 AM – 12:10 PM:** Morning Sessions
- **12:10 PM – 01:30 PM:** Lunch & Demos
- **01:30 PM – 04:20 PM:** Afternoon Sessions
#### Applied Materials Presentations
- **Reimagining the Factory Lifecycle with Digital Twins and AI**
*Presented by Shekar Krishnaswamy*
- **Intelligent Manufacturing for Advanced Packaging: Powered by One MES**
*Presented by EELu Lee*
- **Accelerating Yield with AI-Powered Insights from Limited Data**
*Presented by SJ Wang*
- **Next-Gen Scheduling: Reinforcement Learning for Intelligent Queue Time Management**
*Presented by Samantha Duchscherer*
*\* Presentations are subject to change.*
Register Now
All fields marked * are mandatory.
Form is closed
#### For questions, contact
[Waikin\_Chua@amat.com](mailto:Waikin_Chua@amat.com)
**Event Category:** Semiconductor
---
### [APF Webinar: SmartFactory AI™ Productivity and RTD Private Cloud](https://appliedsmartfactory.com/events/semiconductor-event/apf-webinar-ai-productivity-rtd-private-cloud/)
**Published:** November 1, 2024
**Author:** Applied Smartfactory
**Content:**
# APF Webinar: SmartFactory AI™ Productivity and RTD Private Cloud
#### December 11/12, 2024
### APF Webinar: SmartFactory AI Productivity and RTD Private Cloud
Join our APF webinar to learn how our SmartFactory AI Productivity and RTD Private Cloud capabilities will help you amplify your productivity. Don’t miss this opportunity to view our real-world use cases and live demos in action.
Note: Registration is required. Content is identical in both sessions.
### Session 1 - North America & Europe
Wednesday, December 11, 2024
8:00 – 9:30 am Pacific
5:00 – 6:30 pm Central Europe
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_6gbrjMYqSy204yh_G7Q5sw)
### Session 2 - Asia
Thursday, December 12, 2024
9:00 – 10:30 am China, Taiwan, Singapore
10:00 – 11:30 am Japan, Korea
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_TjEM7nXFTdmOmbOlUKudNA)
**Event Category:** Semiconductor
---
### [APF Webinar: SmartFactory AI™ Productivity and RTD Private Cloud](https://appliedsmartfactory.com/events/semiconductor-event/apf-webinar-ai-productivity-rtd-private-cloud/)
**Published:** November 1, 2024
**Author:** Applied Smartfactory
**Content:**
# APF Webinar: SmartFactory AI™ Productivity and RTD Private Cloud
#### December 11/12, 2024
### APF Webinar: SmartFactory AI Productivity and RTD Private Cloud
Join our APF webinar to learn how our SmartFactory AI Productivity and RTD Private Cloud capabilities will help you amplify your productivity. Don’t miss this opportunity to view our real-world use cases and live demos in action.
Note: Registration is required. Content is identical in both sessions.
### Session 1 - North America & Europe
Wednesday, December 11, 2024
8:00 – 9:30 am Pacific
5:00 – 6:30 pm Central Europe
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_6gbrjMYqSy204yh_G7Q5sw)
### Session 2 - Asia
Thursday, December 12, 2024
9:00 – 10:30 am China, Taiwan, Singapore
10:00 – 11:30 am Japan, Korea
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_TjEM7nXFTdmOmbOlUKudNA)
**Event Category:** Semiconductor
---
### [Boost Manufacturing with AI + Digital Twin](https://appliedsmartfactory.com/events/semiconductor-event/boost-manufacturing-with-ai-digital-twin/)
**Published:** November 11, 2025
**Author:** Applied Smartfactory
**Content:**
##### SmartFactory Japan Webinar
### Boost Manufacturing with AI + Digital Twin
#### December 9, 2025
[ Register Now ](#register)
Discover how integrating SmartFactory AI™ with digital twin technology can boost productivity and enhance quality. We’ll also share insights into the latest innovations shaping the future of manufacturing.
#### Highlights:
- SmartFactory AI Overview – Vision, key benefits, and its connection to digital twin technology
- Practical Applications – How AI supports productivity and quality
- Gen AI – Emerging opportunities
- Interactive features to let you share your thoughts and have your questions answered
### Presented By
Samantha Duchscherer
##### Global Product Manager
Applied Materials | Automation Products Group
SJ Wang
##### Process Quality Global Product Manager
Applied Materials | Automation Products Group
### The calendar invite will automatically adjust to your time zone.
[ Register Now ](https://amat.zoom.us/webinar/register/WN_aV5c_pB0TA62FCq9FJ8yNw)
#### Asia
Tuesday, December 9, 2025
9:00 – 10:00 am China, Taiwan, Southeast Asia
10:00 – 11:00 am Japan, Korea
#### North America
Monday, December 8, 2025
5:00 – 6:00 pm Pacific Time
8:00 – 9:00 pm Eastern Time
#### Registration Note
Registration is required using your company email.
**Event Category:** Semiconductor
---
### [Boost Manufacturing with AI + Digital Twin](https://appliedsmartfactory.com/events/semiconductor-event/boost-manufacturing-with-ai-digital-twin/)
**Published:** November 11, 2025
**Author:** Applied Smartfactory
**Content:**
##### SmartFactory Japan Webinar
### Boost Manufacturing with AI + Digital Twin
#### December 9, 2025
[ Register Now ](#register)
Discover how integrating SmartFactory AI™ with digital twin technology can boost productivity and enhance quality. We’ll also share insights into the latest innovations shaping the future of manufacturing.
#### Highlights:
- SmartFactory AI Overview – Vision, key benefits, and its connection to digital twin technology
- Practical Applications – How AI supports productivity and quality
- Gen AI – Emerging opportunities
- Interactive features to let you share your thoughts and have your questions answered
### Presented By
Samantha Duchscherer
##### Global Product Manager
Applied Materials | Automation Products Group
SJ Wang
##### Process Quality Global Product Manager
Applied Materials | Automation Products Group
### The calendar invite will automatically adjust to your time zone.
[ Register Now ](https://amat.zoom.us/webinar/register/WN_aV5c_pB0TA62FCq9FJ8yNw)
#### Asia
Tuesday, December 9, 2025
9:00 – 10:00 am China, Taiwan, Southeast Asia
10:00 – 11:00 am Japan, Korea
#### North America
Monday, December 8, 2025
5:00 – 6:00 pm Pacific Time
8:00 – 9:00 pm Eastern Time
#### Registration Note
Registration is required using your company email.
**Event Category:** Semiconductor
---
### [SmartFactory Productivity User Group Register](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-productivity-user-group-register/)
**Published:** February 23, 2026
**Author:** Sushmita Kumari
**Content:**
### SmartFactory Productivity User Group
## Registration Form
#### [Michael\_Frenna@amat.com ](mailto:Michael_Frenna@amat.com
)
#### April 14-15, 2026
Sheraton Hsinchu Hotel, Taiwan
#### Michael Frenna
##### Global Product Manager
#### [Michael\_Frenna@amat.com ](mailto:Michael_Frenna@amat.com)
#### Productivity User Group
- RTD
- Real Time Scheduling
- Activity Manager®
- FullAuto
- Reporting
- Advanced Scheduling
- Enterprise Planning
- Production Control
- AutoSched ®
#### Agenda Highlights
- Factory Productivity Vision
- APF Product & Solution Roadmaps
- SmartFactory Genie and Agentic AI
- AI Use Cases and Demos
- New Release Feature Highlights
- Customer Presentations
#### April 14, 2026 - Day 1
**9:00 am – 12:00 pm:** Joint Session
**1:00 pm – 5:00 pm:** Product Sessions Cocktail Reception **5:00 pm**
#### April 15, 2026 - Day 2
**9:00 am – 12:00 pm:** Product Sessions
**1:00 pm – 5:00 pm:** Joint Session
Productivity User Group
**Registration Form**
All fields marked * are mandatory.
First Name: \*
Last Name: \*
Business Email: \*
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
**Event Category:** Semiconductor
---
### [SmartFactory User Group 2026 - OLD](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-user-group/)
**Published:** February 5, 2026
**Author:** Applied Smartfactory
**Content:**
# SmartFactory User Group:
### Deep Dive and First Looks
April 14-15, 2026
[ Register ](#)
### Get ready—our most focused SmartFactory user sessions of the year are coming to Taiwan. Connect with peers, share insights, and get exclusive first looks at what’s next. These are two days you won’t want to miss!
### SmartFactory User Group
#### April 14-15, 2026
Sheraton Hsinchu Hotel, Taiwan
### Session Highlights
#### Product Roadmaps
Hands-on Training
User Stories & Live Demos
## Product Manager Organizers
#### [Christopher\_Reeves@amat.com](mailto:Christopher_Reeves@amat.com)
[Siddharth\_Agarwal@amat.com ](mailto:Siddharth_Agarwal@amat.com)
[Michael\_Frenna@amat.com ](mailto:Michael_Frenna@amat.com)
### Register now for one user group.
#### (registration required with valid business email)
#### User Group A
RTD
Real Time Scheduling
Activity Manager®
FullAuto
Reporting
Advanced Scheduling
Enterprise Planning
Production Control
AutoSched®
[ **Register** ](#)
#### User Group B
Fault Detection
Run-to-Run
Knowledge Advisor
Recipe Management
[ **Register** ](#)
#### User Group C
300works®
FACTORYworks 3
FACTORYworks 2
MES for ATP (back-end)
[ **Register** ](#)
#### User Group D
Maintenance Management
[ **Register** ](#)
#### User Group E
Material Control (MCS)
[ **Register** ](#)
**Event Category:** Semiconductor
---
### [SmartFactory MES User Group Register](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-mes-user-group/)
**Published:** February 23, 2026
**Author:** Sushmita Kumari
**Content:**
### SmartFactory MES User Group
## Registration Form
#### [Siddharth\_Agarwal@amat.com ](mailto:Siddharth_Agarwal@amat.com
)
#### April 14-15, 2026
Sheraton Hsinchu Hotel, Taiwan
#### Siddharth Agarwal
##### Global Product Manager
#### [Siddharth\_Agarwal@amat.com ](mailto:Siddharth_Agarwal@amat.com)
#### MES User Group
- 300works®
- FACTORYworks®
- MES for ATP (back-end)
#### Agenda Highlights
- MES Roadmap
- Feature Deep-Dive & Demos—Advanced Security, Experiments, and more.
- AI Use Cases in MES
- Modernized Operator UI and Design Approach
- Updated Release Cadence, Versioning, and Obsolescence
#### April 14, 2026 - Day 1
**9:00 am – 12:00 pm:** Joint Session
**1:00 pm – 5:00 pm:** Product Sessions
Cocktail Reception **5:00 pm**
#### April 15, 2026 - Day 2
**9:00 am – 12:00 pm:** Product Sessions
**1:00 pm – 5:00 pm:** Joint Session
MES User Group
**Registration Form**
All fields marked * are mandatory.
First Name: \*
Last Name: \*
Business Email: \*
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
**Event Category:** Semiconductor
---
### [Smartfactory Promis MES VUG](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-promis-mes-vug/)
**Published:** October 8, 2024
**Author:** Applied Smartfactory
**Content:**
# SmartFactory PROMIS® MES Virtual User Group
#### Tue, October 29, 2024 & Wed, October 30, 2024
### SmartFactory PROMIS MES Virtual User Group
Learn about the latest PROMIS updates, roadmap, and recent customer experiences. We’re also excited to preview the SmartFactory Durables Management System and SmartFactory Productivity Solutions.
Note: Registration is required. Content is identical in both sessions.
### Session 1 - North America & Europe
Tuesday, October 29, 2024
7:00 – 8:30 AM, Pacific
4:00 – 5:30 PM, Central Europe
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_swOGKrk_RBSAgJuxgFReLw#/registration)
### Session 2 - Asia
Wednesday, October 30, 2024
8:00 – 9:30 AM, China, Taiwan, South-East Asia
9:00 – 10:30 AM, Japan, Korea
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_hHqRVz8MQ6CjxoZDlKih5A#/registration)
### Agenda
### Latest PROMIS updates and roadmap
### SmartFactory Durables Management overview
### Early deployment learning from a recent PROMIS RHEL migration
### SmartFactory Productivity Solutions overview
## For questions, contact
[Siddharth\_Agarwal@amat.com](mailto:Siddharth_Agarwal@amat.com)
**Event Category:** Semiconductor
---
### [Smartfactory Promis MES VUG](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-promis-mes-vug/)
**Published:** October 8, 2024
**Author:** Applied Smartfactory
**Content:**
# SmartFactory PROMIS® MES Virtual User Group
#### Tue, October 29, 2024 & Wed, October 30, 2024
### SmartFactory PROMIS MES Virtual User Group
Learn about the latest PROMIS updates, roadmap, and recent customer experiences. We’re also excited to preview the SmartFactory Durables Management System and SmartFactory Productivity Solutions.
Note: Registration is required. Content is identical in both sessions.
### Session 1 - North America & Europe
Tuesday, October 29, 2024
7:00 – 8:30 AM, Pacific
4:00 – 5:30 PM, Central Europe
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_swOGKrk_RBSAgJuxgFReLw#/registration)
### Session 2 - Asia
Wednesday, October 30, 2024
8:00 – 9:30 AM, China, Taiwan, South-East Asia
9:00 – 10:30 AM, Japan, Korea
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_hHqRVz8MQ6CjxoZDlKih5A#/registration)
### Agenda
### Latest PROMIS updates and roadmap
### SmartFactory Durables Management overview
### Early deployment learning from a recent PROMIS RHEL migration
### SmartFactory Productivity Solutions overview
## For questions, contact
[Siddharth\_Agarwal@amat.com](mailto:Siddharth_Agarwal@amat.com)
**Event Category:** Semiconductor
---
### [SEMICON India 2025](https://appliedsmartfactory.com/events/semiconductor-event/symposiumindia2025/)
**Published:** June 26, 2025
**Author:** Applied Smartfactory
**Content:**
### Register Now!
### SmartFactory Symposium India
#### Wed Sep 3 at 1:00 – 4:00 pm
#### IICC Conference Room 404-A
##### Yashobhoomi (IICC) New Delhi
#### Register Now
### SmartFactory Symposium India
#### Wed Sep 3 at 1:00 – 4:00 pm
IICC Conference Rooms 401 and 402
Don’t miss our **SmartFactory Symposium** during SEMICON India 2025
Join us at SEMICON India to learn how semiconductor manufacturers are leveraging our Applied SmartFactory® fully integrated automation solutions to enhance quality and productivity in factories of any size.
#### Activity Highlights:
#### SmartFactory Symposium
##### Wed Sep 3 at 1:00 - 4:00 pm
IICC Conference Room 404-A
[ Register Now ](https://portal.semiconindia.org/visitor/registration)
(required to attend)
#### Applied Materials India
Visit Booth #1102
If you have questions or want to
connect at the event, reach out to [Joy\_Thomas@amat.com](mailto:Joy_Thomas@amat.com)
Joy Thomas
Applied Materials India
Bengaluru, India
Form is closed
### Presentation:
Smart Manufacturing
### Tuesday, Sep 2 at 13:10 - 13:45 pm
Shekar Krishnaswamy
##### Sr. Director of Business Development
Applied Materials | Automation Products Group
**Event Category:** Semiconductor
---
### [Advanced Semiconductor Manufacturing Conference - 2026](https://appliedsmartfactory.com/events/semiconductor-event/asmc/)
**Published:** April 26, 2026
**Author:** Sushmita Kumari
**Content:**
# Advanced Semiconductor Manufacturing Conference (ASMC)
Hilton Albany, New York
May 11-14, 2026
## Using Reinforcement Learning (RL) to maintain coherence between multiple control systems
Wed May 13, 2026 at 3:45 pm
### Session 11: Advanced Process Control 1
#### This paper outlines an approach that uses AI and machine learning—specifically reinforcement learning—to keep two connected control systems aligned. Rather than relying on multiple rule-based or heuristic methods, we train a model to choose the best setting for shared tuning parameters in real time. This can support tighter process control, faster fault detection and correction, and ultimately higher production yields.
Pratik Kotcher
R2R Solution Architect
Automation Products Group, Applied Materials
## Applied Materials Authors:
### Pratik Kotcher
### Kasturi Sarang
### Venu Bollepalli
#### For questions or to schedule a demo, contact
[pratik\_kotcher@amat.com](mailto:pratik_kotcher@amat.com)
#### To view full conference agenda
[ Visit agenda ](https://asmc2026.exordo.com/programme/sessions/2026-05-13)
**Event Category:** Semiconductor
---
### [Advanced Semiconductor Manufacturing Conference - 2025](https://appliedsmartfactory.com/events/semiconductor-event/asmc-2025/)
**Published:** April 7, 2025
**Author:** Applied Smartfactory
**Content:**
# Advanced Semiconductor Manufacturing Conference (ASMC)
Hilton Albany, New York
May 5-8, 2025
## Implementation & Application of coherent control systems: Digital Twin (high frequency open loop) with Run-to-Run (low frequency closed loop)
Tue, May 6, 2025 at 1:15 pm – 2:40 pm
### Session 3: Advanced Process Control 1
#### This session discusses process control schemes utilizing advanced data analytics, computational algorithms and statistical methods to improve wafer process steps, yield and cost.
Pratik Kotcher
R2R Solution Architect
Automation Products Group, Applied Materials
## Applied Materials Authors:
### Pratik Kotcher
### Kasturi Sarang
### Miller Allen
### Siva Dhandapani
#### For questions or to schedule a demo, contact
[pratik\_kotcher@amat.com](mailto:pratik_kotcher@amat.com)
#### To view full conference agenda
[ Visit agenda ](https://asmc2025.exordo.com/programme/presentation/12)
**Event Category:** Semiconductor
---
### [Advanced Semiconductor Manufacturing Conference - 2025](https://appliedsmartfactory.com/events/semiconductor-event/asmc-2025/)
**Published:** April 7, 2025
**Author:** Applied Smartfactory
**Content:**
# Advanced Semiconductor Manufacturing Conference (ASMC)
Hilton Albany, New York
May 5-8, 2025
## Implementation & Application of coherent control systems: Digital Twin (high frequency open loop) with Run-to-Run (low frequency closed loop)
Tue, May 6, 2025 at 1:15 pm – 2:40 pm
### Session 3: Advanced Process Control 1
#### This session discusses process control schemes utilizing advanced data analytics, computational algorithms and statistical methods to improve wafer process steps, yield and cost.
Pratik Kotcher
R2R Solution Architect
Automation Products Group, Applied Materials
## Applied Materials Authors:
### Pratik Kotcher
### Kasturi Sarang
### Miller Allen
### Siva Dhandapani
#### For questions or to schedule a demo, contact
[pratik\_kotcher@amat.com](mailto:pratik_kotcher@amat.com)
#### To view full conference agenda
[ Visit agenda ](https://asmc2025.exordo.com/programme/presentation/12)
**Event Category:** Semiconductor
---
### [SmartFactory Process Quality User Group Register](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-process-quality-user-group-register/)
**Published:** February 20, 2026
**Author:** Sushmita Kumari
**Content:**
### SmartFactory Process Quality User Group
## Registration Form
#### [Christopher\_Reeves@amat.com](mailto:Christopher_Reeves@amat.com)
#### April 14-15, 2026
Sheraton Hsinchu Hotel, Taiwan
#### Christopher Reeves
##### Global Product Manager
#### [Christopher\_Reeves@amat.com](mailto:Christopher_Reeves@amat.com)
#### Process Quality User Group
- Fault Detection
- Run-to-Run
- Knowledge Advisor
- Recipe Management
- SPC
#### Agenda Highlights
- Process Quality & Unified Process Control Vision
- AI Use Cases and Demo
- Utilizing AI for Development and QA
- Product Roadmaps including: E3 Platform, Fault Detection, Run-to-Run, SPC / SPACE, KA
- Customer Feedback Session
#### April 14, 2026 - Day 1
**9:00 am – 12:00 pm:** Joint Session
**1:00 pm – 5:00 pm:** Product Sessions
Cocktail Reception **5:00 pm**
#### April 15, 2026 - Day 2
**9:00 am – 12:00 pm:** Product Sessions
**1:00 pm – 5:00 pm:** Joint Session
Process Quality User Group
**Registration Form**
All fields marked * are mandatory.
First Name: \*
Last Name: \*
Business Email: \*
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
**Event Category:** Semiconductor
---
### [SmartFactory MCS User Group Register](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-mcs-user-group/)
**Published:** February 24, 2026
**Author:** Sushmita Kumari
**Content:**
### SmartFactory MCS User Group
## Registration Form
#### [Daniel\_Meier@amat.com ](mailto:Daniel_Meier@amat.com)
#### April 14-15, 2026
Sheraton Hsinchu Hotel, Taiwan
#### Daniel Meier
##### Global Product Manager
#### [Daniel\_Meier@amat.com ](mailto:Daniel_Meier@amat.com)
#### MCS User Group
- Material Control (MCS)
#### Agenda Highlights
- MCS Roadmap
- AMRs, Cobots, Humanoids—it’s a new robot world!
- Universal Control for Mixed-Robot Environments
- AI Use Cases for Material Control
- Metrics for MCS Reliability
- Cloud MCS
#### April 14, 2026 - Day 1
**9:00 am – 12:00 pm:** Joint Session
**1:00 pm – 5:00 pm:** Product Sessions
Cocktail Reception **5:00 pm**
#### April 15, 2026 - Day 2
**9:00 am – 12:00 pm:** Product Sessions
**1:00 pm – 5:00 pm:** Joint Session
MCS User Group
**Registration Form**
All fields marked * are mandatory.
First Name: \*
Last Name: \*
Business Email: \*
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
**Event Category:** Semiconductor
---
### [SmartFactory Maintenance Management User Group Register](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-maintenance-management-user-group/)
**Published:** February 24, 2026
**Author:** Sushmita Kumari
**Content:**
### SmartFactory Maintenance Management User Group
## Registration Form
#### [Yoram\_Barak@amat.com ](mailto:Yoram_Barak@amat.com)
#### April 14-15, 2026
Sheraton Hsinchu Hotel, Taiwan
#### Yoram Barak
##### Global Product Manager
#### [Yoram\_Barak@amat.com ](mailto:Yoram_Barak@amat.com)
#### Maintenance Management User Group
- Maintenance Management
#### Agenda Highlights
- Market Trends
- Roadmap and Obsolescence
- Upcoming Release 3.10 Features
- Roadmap Overview: Dynamic Quals, Spares 2.1, Decoupling, Loaders Convergence, OOB Improvements, Pass-down, Certification, Reports & Analytics, PdM Integration
- GenAI
#### April 14, 2026 - Day 1
**9:00 am – 12:00 pm:** Joint Session
**1:00 pm – 5:00 pm:** Product Sessions
Cocktail Reception **5:00 pm**
#### April 15, 2026 - Day 2
**9:00 am – 12:00 pm:** Product Sessions
**1:00 pm – 5:00 pm:** Joint Session
Maintenance Management User Group
**Registration Form**
All fields marked * are mandatory.
First Name: \*
Last Name: \*
Business Email: \*
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
You may withdraw your consent at any time by sending an email to DataProtection@amat.com
Δ
**Event Category:** Semiconductor
---
### [SmartFactory APF Virtual User Group](https://appliedsmartfactory.com/events/semiconductor-event/apf-virtual-user-group/)
**Published:** February 13, 2026
**Author:** Applied Smartfactory
**Content:**
# SmartFactory APF Virtual User Group
#### Wed March 11, 2026 and Thu March 12, 2026
#### (Identical content across sessions)
[ Register Now ](#register)
### Explore What’s New
Don’t miss our roadmap reviews, new features, and user stories covering APF RTD®, Activity Manager®, AutoSched®, AI initiatives, APF Cloud, and SmartFactory Productivity Solutions.
### Choose Your Session & Register
- Both sessions cover the same content—select the time that works best for you
- Company email address required
- Personal email addresses (e.g., Gmail, Yahoo) will not be accepted
#### Session 1 - North America & Europe
Wednesday, March 11th, 2026
8:00 – 9:30 am Pacific
11:00 – 12:30 am Eastern
5:00 – 6:30 pm Central Europe
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_IKVNJs5wSHefXec5_REBgg#/registration)
#### Session 2 - Asia
Thursday, March 12th, 2026
10:00am – 11:30 am China, Japan, Taiwan
9:00am – 10:30 am Singapore
6:00 pm – 7:30 pm Pacific (3/11 Wednesday evening)
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_osThHiCxQLiXaRF5r1ArNg#/registration)
Questions? Contact: [Siddharth\_Agarwal@amat.com](mailto:Siddharth_Agarwal@amat.com)
**Event Category:** Semiconductor
---
### [PROMIS Virtual User Group](https://appliedsmartfactory.com/events/semiconductor-event/promis-virtual-user-group/)
**Published:** September 15, 2025
**Author:** Applied Smartfactory
**Content:**
# SmartFactory PROMIS® Virtual User Group
#### October 14 & 15, 2025
#### (Identical content across sessions)
[ Register Now ](#register)
### Explore What’s Ahead for PROMIS
Join us to learn about the latest roadmap updates, the transition to Red Hat Linux, integration options, and expanded capabilities. Hear directly from a customer who recently migrated to Red Hat Linux and discover what new opportunities this unlocks.
### Choose Your Session & Register
- Both sessions cover the same content—select the time that works best for you
- Company email address required
- Personal email addresses (e.g., Gmail, Yahoo) will not be accepted
#### Session 1 - North America & Europe
Tuesday, October 14, 2025
7:00 – 8:30 am Pacific
4:00 – 5:30 pm Central Europe
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_I5r7zgP_TnGHWHzf0JlqFw)
#### Session 2 - Asia
Wednesday, October 15, 2025
8:00 – 9:30 am China, Taiwan, Southeast Asia
9:00 – 10:30 am Japan, Korea
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_RrFXGEXPSaulw6lVNsXRxQ)
Questions? Contact: [Siddharth\_Agarwal@amat.com](mailto:Siddharth_Agarwal@amat.com)
**Event Category:** Semiconductor
---
### [APC Europe 2025](https://appliedsmartfactory.com/events/semiconductor-event/apc-europe-2025/)
**Published:** March 4, 2025
**Author:** Applied Smartfactory
**Content:**
# Striving for Zero Defects
SmartFactory Process Quality solutions fully integrated
### apc|m europe
Prague, Czech Republic
April 8-10, 2025
[ Schedule Onsite Demo ](/events/semiconductor/schedule-onsite-demo/)
### Prime Sponsorship Presentation
### Wed, April 9, 2025 at 10:30
Christopher Reeves
Global Product Manager – E3
Applied Materials
## A Model Based Method of Non-Threaded R2R Control with Expectation-Maximization (EM) Optimization
### Wed, April 9, 2025 at 15:00
Dr. Jianping Zou
Senior Member of Technical Staff
Applied Materials
## Our team of quality solution experts are here to
### Explore your challenges in the factory
### Host 1:1 onsite demos of our fully integrated quality and productivity solutions
### Identify how you can achieve synergy of these processes and when to leverage AI
#### For questions or to schedule a demo, contact
[Christopher\_Reeves@amat.com](mailto:Christopher_Reeves@amat.com)
[ Schedule Onsite Demo ](/events/semiconductor/schedule-onsite-demo/)
#### To view full conference agenda
[ Visit agenda ](https://www.apcm-europe.eu/conference/agenda)
**Event Category:** Semiconductor
---
### [APC Europe 2025](https://appliedsmartfactory.com/events/semiconductor-event/apc-europe-2025/)
**Published:** March 4, 2025
**Author:** Applied Smartfactory
**Content:**
# Striving for Zero Defects
SmartFactory Process Quality solutions fully integrated
### apc|m europe
Prague, Czech Republic
April 8-10, 2025
[ Schedule Onsite Demo ](/events/semiconductor/schedule-onsite-demo/)
### Prime Sponsorship Presentation
### Wed, April 9, 2025 at 10:30
Christopher Reeves
Global Product Manager – E3
Applied Materials
## A Model Based Method of Non-Threaded R2R Control with Expectation-Maximization (EM) Optimization
### Wed, April 9, 2025 at 15:00
Dr. Jianping Zou
Senior Member of Technical Staff
Applied Materials
## Our team of quality solution experts are here to
### Explore your challenges in the factory
### Host 1:1 onsite demos of our fully integrated quality and productivity solutions
### Identify how you can achieve synergy of these processes and when to leverage AI
#### For questions or to schedule a demo, contact
[Christopher\_Reeves@amat.com](mailto:Christopher_Reeves@amat.com)
[ Schedule Onsite Demo ](/events/semiconductor/schedule-onsite-demo/)
#### To view full conference agenda
[ Visit agenda ](https://www.apcm-europe.eu/conference/agenda)
**Event Category:** Semiconductor
---
### [SmartFactory Joint User Group](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-apf-user-group/)
**Published:** June 27, 2025
**Author:** Applied Smartfactory
**Content:**
SmartFactory User Group
We’re hosting multiple user groups on **Tuesday, September 9** at the **Sheraton Hsinchu Hotel Taiwan.**
Please register now (registration required)
[ APF User Group ](/events/semiconductor/smartfactory-apf-user-group/)
[ E3 User Group ](/events/semiconductor/smartfactory-e3-user-group-2025/)
[ MES User Group ](/events/semiconductor/smartfactory-mes-user-group-2025/)
[ MCS User Group ](/events/semiconductor/smartfactory-mcs-user-group-2025/)
[ Maintenance Management User Group ](/events/semiconductor/smartfactory-maintenance-management-user-group-2025/)
[ PROMIS User Group ](/events/semiconductor/smartfactory-promis-user-group-2025/)
#### Full Day:
##### Register for one user group
APF User Group: [Michael\_Frenna@amat.com](mailto:Michael_Frenna@amat.com)
E3 User Group: [Chris\_Reeves@amat.com](mailto:Chris_Reeves@amat.com)
MES User Group: [Siddharth\_Agarwal@amat.com](mailto:siddharth_agarwal@amat.com)
MCS User Group: [Siddharth\_Agarwal@amat.com](mailto:siddharth_agarwal@amat.com)
#### Half Day:
##### Morning:
Maintenance Management User Group: [siddharth\_agarwal@amat.com](mailto:siddharth_agarwal@amat.com)
##### Afternoon:
PROMIS User Group: [siddharth\_agarwal@amat.com](mailto:siddharth_agarwal@amat.com)
Form is closed
**Event Category:** Semiconductor
---
### [SmartFactory Maintenance Management Webinar](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-maintenance-management-webinar/)
**Published:** January 14, 2026
**Author:** Applied Smartfactory
**Content:**
# SmartFactory Maintenance Management Webinar
#### February 10, 2026
[ Register Now ](#register)
### Speeding up the flow from sensing to resolution
Shortening the Green-to-Green (G2G) duration relies on the timely execution of the workflow from sensing the problem, triggering an alarm, and running OCAP, to enacting the appropriate Maintenance Management work order with confidence all spares are available to complete the job.
With advancements in GenAI, it will soon be possible to not only predict failure, but also to automatically trigger work orders, confirm the presence and condition of all necessary parts, and optimize planned maintenance schedules.
### Join us as we discuss our approach to enabling these advancements.
### Highlights:
- We’ll explain how the integration layer between SmartFactory Fault Detection (FD), Alarm Management (AMS), SmartFactory Knowledge Advisor (KA) and SmartFactory Maintenance Management (SFMM) supports G2G timeline shortening.
- Use-case demo of how they work together to improve productivity.
- Introduction to SmartFactory GenAI capabilities to accelerate these further.
#### Presented By:
Yoram Barak
##### Maintenance Management
Applied Materials | Global Product Manager
### Explore the[ Maintenance Management](/semiconductor/manufacturing-execution-solutions/maintenance-management/) page to learn more before the webinar.
### **Register Now!**
- Company email address required
- Personal email addresses (e.g., Gmail, Yahoo) will not be accepted
### Session Information
##### Each session covers the same content — choose the day and time that works best for you.
#### Session 1 - Asia
Tuesday, February 10, 2026
9:00 – 10:00 am China, Taiwan, Southeast Asia
10:00 – 11:00 am Japan, Korea
[ Register – Session 1 ](https://amat.zoom.us/webinar/register/WN_fRI5Vu5kRk-qEYymHKg0RQ#/registration)
#### Session 2 - North America and Europe
Tuesday, February 10, 2026
8:00 – 9:00 am Pacific
5:00 – 6:00 pm Central Europe
[ Register – Session 2 ](https://amat.zoom.us/webinar/register/WN_enY_vxgvRW2ZGiJaT0vyjw#/registration)
For additional details
Contact: [Yoram\_Barak@amat.com]()
**Event Category:** Semiconductor
---
### [SMART FACTORY Expo](https://appliedsmartfactory.com/events/semiconductor-event/smart-factory-expo-japan/)
**Published:** November 26, 2025
**Author:** Applied Smartfactory
**Content:**
第10回 スマート工場EXPO
実演デモと革新的なソリューションの説明
##### 2026年1月21日～23日 | 東京ビッグサイト
### 第10回スマート工場EXPOにご参加ください
製造業がどのようにスマートファクトリー統合自動化ソフトウェアを活用し、効率を最大化し、品質を向上させ、生産性を様々な工場で高めているかをご紹介します。
#### 当社ブース（S15-30）では以下をご覧いただけます：
- AI駆動の自動化を実演するライブソリューションデモ
- スマート製造に向けたDX（デジタルトランスフォーメーション）戦略のインサイト
**私たちのプレゼンテーションをお見逃しなく**
**AIの真価を解き明かす――理論から実践へ**
##### 会場： 新製品・新技術セミナー～New Tech Trend～ 会場⑥
##### 開催時間： 2026年1月 22日 （木）午後 15:00 - 15:30
David Hanny
##### Senior Director
Applied Materials | Automation Products Group
[ 詳細はこちら ](https://www.nepconjapan.jp/tokyo/ja-jp/conference/ex-presentation/session-details.4718.257704.ai%E3%81%AE%E7%9C%9F%E4%BE%A1%E3%82%92%E8%A7%A3%E3%81%8D%E6%98%8E%E3%81%8B%E3%81%99%E2%80%95%E2%80%95%E7%90%86%E8%AB%96%E3%81%8B%E3%82%89%E5%AE%9F%E8%B7%B5%E3%81%B8.html)
**バッテリー製造におけるAIの基礎：品質向上のためのステップバイステップロードマップ**
##### 会場： 新製品・新技術セミナー～New Tech Trend～ 会場⑥
##### 開催時間： 2026年1月 23日 （金）午後 15:00 - 15:30
Agnes Sowa
##### Battery Segment Manager
Applied Materials | Automation Products Group
[ 詳細はこちら ](https://www.nepconjapan.jp/tokyo/ja-jp/conference/ex-presentation/session-details.4719.257708.foundations-for-ai-in-battery-quality-step_by_step-roadmap.html)
お問い合わせ先：
[ Shin\_Sekido@amat.com](mailto:Shin_Sekido@amat.com)
**Event Category:** Semiconductor
---
### [SMART FACTORY Expo](https://appliedsmartfactory.com/events/semiconductor-event/smart-factory-expo-japan/)
**Published:** November 26, 2025
**Author:** Applied Smartfactory
**Content:**
SMART FACTORY Expo
Live Demos. Solution Breakthroughs.
##### Jan 21-23, 2026 | Tokyo Big Sight, Japan
### Join Us at SMART FACTORY Expo
Discover how manufacturers are transforming operations with SmartFactory integrated automation software—designed to maximize efficiency, improve quality, and boost productivity across any factory environment.
#### Visit our booth S15-30 for:
- Live solution demos showcasing AI-driven automation
- Insights into digital transformation strategies for smart manufacturing
**Don’t miss our presentations:**
**AI Unveiled, from Theory to Practice**
##### Location: Exhibitors' Product/Technology Seminar ~New Tech Trend~ Venue⑥
##### Date: Thursday, January 22, 2026 at 15:00-15:30 JST
David Hanny
##### Senior Director
Applied Materials | Automation Products Group
[ More Information ](https://www.nepconjapan.jp/tokyo/en-gb/conference/ex-presentation/session-details.4719.257707.ai-unveiled-from-theory-to-practice.html)
**Foundations for AI in Battery Quality: Step-by-Step Roadmap**
##### Location: Exhibitors' Product/Technology Seminar ~New Tech Trend~ Venue⑥
##### Date: Friday, January 23, 2026 at 15:00-15:30 JST
Agnes Sowa
##### Battery Segment Manager
Applied Materials | Automation Products Group
[ More information ](https://www.nepconjapan.jp/tokyo/en-gb/conference/ex-presentation/session-details.4719.257708.foundations-for-ai-in-battery-quality-step_by_step-roadmap.html)
For more information
Contact: [ Shin\_Sekido@amat.com](mailto:Shin_Sekido@amat.com)
**Event Category:** Semiconductor
---
### [Schedule Onsite Demo](https://appliedsmartfactory.com/events/semiconductor-event/schedule-onsite-demo/)
**Published:** March 2, 2023
**Author:** Applied Smartfactory
**Content:**
# Schedule Onsite Demo
Form is closed
**Event Category:** Semiconductor
---
### [Innovation Forum Automation 2026](https://appliedsmartfactory.com/events/semiconductor-event/innovation-forum-automation-2026/)
**Published:** November 24, 2025
**Author:** Applied Smartfactory
**Content:**
### Keynote. Demos. Breakthroughs.
Experience SmartFactory innovation with fellow experts.
Jan 29-30,2026 | Dresden, Germany
### Join Us at the Innovation Forum for Automation
Don’t miss the premier gathering for automation leaders. As a Platinum Sponsor, we’ll take center stage with a keynote presentation and showcase live demos of breakthrough SmartFactory integrated software solutions.
Discover how innovation is reshaping automation worldwide—and what it means for the future of manufacturing.
For more information
Contact:
**Event Category:** Semiconductor
---
### [AEC/APC Symposium 2025](https://appliedsmartfactory.com/events/semiconductor-event/aec-apc-symposium-2025/)
**Published:** October 9, 2025
**Author:** Applied Smartfactory
**Content:**
AEC/APC Symposium Asia
検出から診断へ:
SPC 向け AI 駆動型根本原因分析
ゲスト講演者
Vishali Ragam
2025年11月26日（水）
午前10:10~10:30
**AEC/APC Symposium AsiaでVishali Ragamの講演にご参加ください。**
SmartFactoryは、SPC（統計的工程管理）、FDC（故障検出制御）、そしてAIによる視覚言語モデル（VLM）を融合し、プロセス制御の新たなステージを切り開いています。本講演では、この革新的なアプローチによって、根本原因分析の自動化を実現し、診断時間を15%以上短縮することで、エンジニアがより迅速かつ的確に問題を解決できる仕組みをご紹介します。
### イベントの見どころ
Vishali Ragamによるプレゼンテーション：
*“「検出から診断へ: AIがSPCを進化させる根本原因分析」”*
Vishali Ragam
##### Global Product Manager, SPC Process Quality
Applied Materials | Automation Products Group
日付
2025年11月26日（水）
午前10:10~10:30
2日目 | セッション 3 | PTL-015
**会場情報：**
福岡国際会議場
〒812-0032 福岡県福岡市博多区石城町２−１
日本、福岡県
[ 詳細情報はこちら ](https://www.semiconportal.com/AECAPC/program_e.html)
**ご質問について**
連絡先: [Vishali\_Ragam@amat.com](mailto:Vishali_Ragam@amat.com)
**Event Category:** Semiconductor
---
### [AEC/APC Symposium 2025](https://appliedsmartfactory.com/events/semiconductor-event/aec-apc-symposium-2025/)
**Published:** October 9, 2025
**Author:** Applied Smartfactory
**Content:**
**Live at AEC/APC Symposium Asia**
From Detection to Diagnosis: Enhancing SPC with AI-Powered Root Cause Analysis
Guest Speaker
Vishali Ragam
Wed Nov 26, 2025
10:10-10:30 am
**See Vishali Ragam at the AEC/APC Symposium Asia**
Learn how SmartFactory is transforming process control by combining SPC, FDC, and AI-powered Visual Language Models (VLMs). This innovative approach automates root cause analysis, cuts diagnosis time by over 15%, and helps engineers—from junior to expert—solve problems faster.
### Event Highlights
Vishali Ragam presents:
*“From Detection to Diagnosis: Enhancing SPC with AI-powered Root Cause Analysis”*
Vishali Ragam
##### Global Product Manager, SPC Process Quality
Applied Materials | Automation Products Group
Date and Time
Wednesday, November 26, 2025
10:10 – 10:30 am
Day 2 | Session 3 | PTL-015
**Location:**
Fukuoka International Congress Center
2-1 Sekijyo-machi, Hakata-ku, Fukuoka-shi, 812-0032
Fukuoka, Japan
[ More Info ](https://www.semiconportal.com/AECAPC/program_e.html)
**Questions**
Contact: [Vishali\_Ragam@amat.com](mailto:Vishali_Ragam@amat.com)
**Event Category:** Semiconductor
---
### [Alarm Containment to Resolution Webinar](https://appliedsmartfactory.com/events/semiconductor-event/alarm-containment-to-resolution-webinar/)
**Published:** October 22, 2025
**Author:** Applied Smartfactory
**Content:**
# Alarm Containment to
Resolution Webinar
#### November 25, 2025
[ Register Now ](#register)
### Move beyond critical alerts to prescriptive actions
Alarm management is not just about silencing the noise—it’s about amplifying the signal. With the right tools and data-driven strategies, semiconductor manufacturers can change alarms from a source of frustration into a foundation for smarter, safer, and more efficient operations.
Join us to learn how our integrated solutions can help stop a tool to prevent further action, as well as fix the underlying problem to return it to production.
### Highlights
- We’ll explain how the integration layer we built between SmartFactory Alarm Management (AMS) and SmartFactory Knowledge Advisor (KA) supports both containment and corrective actions with structured workflows for resolving alarms.
- Use-case demo of how they work together to improve yield and productivity.
- Introduction to SmartFactory Genie.
### Register Now!
- Company email address required
- Personal email addresses (e.g., Gmail, Yahoo) will not be accepted
### Session Information
#### Session 1 - Asia
Tuesday, November 25, 2025
9:00 – 10:00 am China, Taiwan, Southeast Asia
10:00 – 11:00 am Japan, Korea
[ Register – Session 1 ](https://amat.zoom.us/webinar/register/WN_pAslnZ2KQoe3y9OF9hL90Q)
#### Session 2 - North America and Europe
Tuesday, November 25, 2025
8:00 – 9:00 am Pacific
5:00 – 6:00 pm Central Europe
[ Register – Session 2 ](https://amat.zoom.us/webinar/register/WN_oAI8w1OoRMKWlgujb8mkGA)
Questions?
Contact: [Yoram\_Barak@amat.com]()
**Event Category:** Semiconductor
---
### [Digital Twin Standards by SJ Wang](https://appliedsmartfactory.com/events/semiconductor-event/digital-twin-standards-by-sj-wang/)
**Published:** October 1, 2025
**Author:** Applied Smartfactory
**Content:**
NSF Center for Digital Twins in Manufacturing
Project Planning Workshop
Thursday, October 9, 2025
Join SJ Wang at Project Planning Workshop at NSF Center for Digital Twins in Manufacturing
SJ Wang shares how AppliedTwin helps fabs act faster with real-time insights.
Discover how AppliedTwin uses process, product, and equipment digital twins to deliver real-time insights that help semiconductor manufacturers detect issues early and respond faster. By combining historical and runtime data, this integrated approach supports smarter decisions that improve ramp, yield, and overall fab performance.
# Project Planning Workshop Highlights
SJ Wang, PhD presents:
*"Equipment Health Monitoring and Product Health Monitoring Using Semiconductor Manufacturing Digital Twins"*
SJ Wang
##### Process Quality Global Product Manager
Applied Materials | Automation Products Group
Date and Time
Thursday, October 9, 2025
9:45 am – 12:15 pm MT
Sponsors
NSF Center for Digital Twins in Manufacturing
Location
Polytechnic Campus of Arizona State University
Interdisciplinary Science and Technology 12 (ISTB-12) 6155 S. Innovation Way West
Mesa, AZ 85212
[ More Info ](https://sites.google.com/umich.edu/digitaltwincenter)
[ Agenda ](https://docs.google.com/document/d/1vEomQb4GMcVJoGHz8Kw3DjIsoI7Eq2eZSnPaJxceOOE/edit?tab=t.0)
[ Register Now ](https://forms.gle/uAyQ5sgo3LKW3kZQ9)
**Questions**
Contact: [Shijing\_Wang@amat.com](mailto:Shijing_Wang@amat.com)
**Event Category:** Semiconductor
---
### [Lunch Session in Smart Manufacturing Pavilion Theater - Semicon West](https://appliedsmartfactory.com/events/semiconductor-event/semicon-west-2025/)
**Published:** October 1, 2025
**Author:** Applied Smartfactory
**Content:**
Join Scott Rothenberg
Smart Manufacturing
Lunch Session
Tuesday, Oct 7, 2025 at 1:00-2:00 PM MT
Lunch Session in Smart Manufacturing Pavilion Theater
# Smart Manufacturing Lunch Session Highlights
Panel Topic
Ecosystem-Connected Digital Twins:
Transforming Semiconductor Fabs with NVIDIA Omniverse
Time & Location
Tue Oct 7 | 1:00-2:00 PM MT
Smart Manufacturing Pavilion Theater, North Building, Lower Level, Expo Floor
# Meet the Panel
Moderator
**Vikram Natarajan,** Managing Director
NVIDIA Omniverse, NVIDIA
Panelist
**Scott Rothenberg,** Managing Director & Deputy General Manager
Applied Materials, Automation Products Group
Panelist
**Jin Lim,** Corporate Vice President
SK Hynix
Panelist
**Alex Schafgans,** Vice President & Head of Development & Engineering
ASLM
**Questions**
Contact:
[ Learn more ](https://semiconwest2025.eventscribe.net/fsPopup.asp?Mode=sessioninfo&PresentationID=1675762)
**Event Category:** Semiconductor
---
### [SmartFactory MES 300works® Virtual User Group](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-mes-300works-virtual-user-group/)
**Published:** September 19, 2025
**Author:** Applied Smartfactory
**Content:**
# SmartFactory MES 300works® Virtual User Group
#### October 28, 2025
[ Register Now ](#register)
### Explore What’s Ahead for 300works
Join us to get a sneak peek at what’s next for 300works and ATP—including stronger security and smoother supportability. We’ll also discuss opportunities for AI-driven MES innovations, explore new roadmap highlights, and show how you can personalize FactoryView dashboards.
### Register Now!
- Company email address required
- Personal email addresses (e.g., Gmail, Yahoo) will not be accepted
#### Session Information - North America & Europe
Tuesday, October 28, 2025
8:00 – 10:00 am Pacific
5:00 – 7:00 pm Central Europe
[ Register Now ](https://amat.zoom.us/webinar/register/WN_TMvy1DTQTWi2AORV7_xOLQ)
Questions? Contact: [Christian\_Elggren@amat.com ]()
**Event Category:** Semiconductor
---
### [Agnes Session](https://appliedsmartfactory.com/events/battery-event/agnes-sowa-at-battery-tech-theatre/)
**Published:** September 15, 2025
**Author:** Applied Smartfactory
**Content:**
Discussion:
Using semiconductor-proven Fault Detection to reduce downtime in ramp-up and high-volume electrode process.
**When**: Wednesday, Oct 8 at 10:00 AM – 10:45 AM Eastern
**Where**: Battery Tech Theatre | Booth 6050
Live at The Battery Show – Huntington Place, Detroit, MI
Gigafactories are scaling rapidly, leveraging automation, Industry 4.0, and agentic AI and taking best practices from electronics and automotive manufacturing.
This session highlights how fault detection—proven in semiconductor fabs—can be applied to high-volume battery cell manufacturing to identify defects and optimize maintenance.
Attendees will learn how to progress from SPC methods and Fault Detection to Predictive Algorithms that extend maintenance intervals and reduce unplanned costly downtime to maximize value of their data to improve operational efficiency.
**Questions? Contact:** [Agnes\_Sowa@amat.com](mailto:Agnes_Sowa@amat.com)
Discussion:
Using semiconductor-proven Fault Detection to reduce downtime in ramp-up and high-volume electrode process.
**When**: Wednesday, Oct 8 at 10:00 AM – 10:45 AM Eastern
**Where**: Battery Tech Theatre | Booth 6050
**Event Category:** Battery
---
### [SmartFactory Asset Trace Webinar](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-asset-trace-webinar/)
**Published:** August 8, 2025
**Author:** Applied Smartfactory
**Content:**
# SmartFactory Asset Trace Webinar
#### *(formerly Durables Management)*
#### Wed Sep 17, 2025
### Automate Asset Tracking for Better Yield and Productivity
Discover how automating mobile asset tracking —like durables and consumables— can drive quality and efficiency in your fab. We’ll explore how integrated systems like Asset Trace and SPC enhance supplier quality and share early insights into our GenAI capabilities.
Yoram Barak, PhD
Asset Trace Global Product Manager
Applied Materials, Automation Products Group
### Registration is required.
Please register using your company email address.
*Personal email addresses (e.g., Gmail, Yahoo) will not be accepted.*
### Session Information
Each session covers the same content —choose the time that works best for you.
### Session 1 – Asia
Wednesday, September 17, 2025
9:00 – 10:00 am China, Taiwan, Southeast Asia
10:00 – 11:00 am Japan, Korea
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_TB463fg-Ru-ulRaPPefIeg#/registration)
### Session 2- North America and Europe
Wednesday, September 17, 2025
8:00 – 9:00 am Pacific
5:00 – 6:00 pm Central Europe
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_AuSLFlRZTT2SueDBYzzBWw)
### Contact
[Yoram\_Barak@amat.com](mailto:Yoram_Barak@amat.com)
**Event Category:** Semiconductor
---
### [APCSM Conference 2024](https://appliedsmartfactory.com/events/semiconductor-event/apcsm-conference-2024/)
**Published:** September 13, 2024
**Author:** Applied Smartfactory
**Content:**
# APCSM Conference 2024
## スマート製造向けの高度なプロセス制御（APC）
#### 2024年10月7日（月）～10日（木） ｜ カナダ，トロント
技術セッション・アジェンダ
### ニューラルネットワークによるRun-to-Runの最適化：非スレッド型コンセプトの活用
発表者：Ivan Chen（Applied Material）
日時：2024年10月8日（火）午後1:00～1:30（米国東部時間）
[ 今すぐ登録 ](https://www.apcsmconference.com/event/312dd91f-731d-420a-87d5-a90b07f30ab3/regProcessStep1:7388af2f-c4a7-43cc-a2dd-5de41c913676)
### プレゼンテーションのハイライト
### 当社の革新的な機械学習制御手法により、非スレッド制御を容易に実現します。
### この手法では、コンテキスト情報と物理的知識を組み合わせることで、すべてのスレッドに対するデータ収集の必要性を排除しています。ぜひ、この手法が実際の生産現場で生み出した驚くべき成果をご覧ください。
### PythonによるHA/LB（高可用性／負荷分散）アーキテクチャで、MLシステムの安定性と効率性を向上させます。また、MLサーバーを構築することで、実環境での信頼性の高いR2R性能予測を実現します。
### 機械学習制御の未来を探る：2020年には、RNNとCNPモデル構造を用いてプロセスドリフトの予測可能性を実証しました。
### 機械学習の真の可能性を、実環境での制御において解き放ちましょう。
## 著者一覧
- Ivan Chen
- Tony Li
- Shijing Wang
- Yeo Zi Ping Leonard
- Ko Ko Win
- Tristan Yu
- Allen Yang
要旨番号：24003
## ご質問やイベントについては、Shijing Wang [（shijing\_wang@amat.com）](mailto:shijing_wang@amat.com)までお問い合わせください。
**Event Category:** Semiconductor
---
### [Innovation Forum Automation 2025](https://appliedsmartfactory.com/events/semiconductor-event/innovation-forum-automation-2025/)
**Published:** November 26, 2024
**Author:** Applied Smartfactory
**Content:**
# 既存資産の最適化
## 完全統合されたSmartFactory Productivity
ソリューション
22nd Innovation Forum for Automation
2025年1月30日（木）ー 31日（金） ❘ ドイツ，ドレスデン
## 基調講演：スケーラブルなAIソリューションの統合と運用
### 2025年1月30日
### Samantha Duchscherer
##### グローバルプロダクトマネージャー
Applied Materials | Automation Products Group
### Shijing (SJ) Wang
##### グローバルプロダクトマネージャー
Applied Materials | Automation Products Group
### 基調講演のハイライト
### 当社の統一されたアプローチにより、欠陥を最小限に抑え、スループットを最大化するAIソリューションの導入をご紹介します。
### Run-to-RunコントローラーにAI構成を実装することで、ツールや
プロセスの経時的な変動を効率的に補正し、少量多品種の環境でも
ゼロ・ディフェクト（欠陥ゼロ）を目指すことが可能です。
### 歩留まりとスループットの同時最適化を実現するために、AIがリアルタイムスケジューリングに必要な最適な意思決定を自動で構成します。
### ご質問は以下までお問い合わせください：
[Thomas\_Wimmer@amat.com](mailto:Thomas_Wimmer@amat.com)
**Event Category:** Semiconductor
---
### [SmartFactory Durables Management Webinar: Unlocking the Power of Automation](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-durables-management-webinar/)
**Published:** January 29, 2025
**Author:** Applied Smartfactory
**Content:**
# SmartFactory Durables Management Webinar: Unlocking the Power of Automation
#### 2025年2月19日（水）
### SmartFactory Durables Management Webinar: Unlocking the Power of Automation
耐久財と消耗品の管理を、SPC（統計的工程管理）やリアルタイムディスパッチングなどのシステムと組み合わせることで、資産を最大限に活用するための比類なき強力な仕組みが実現します。このウェビナーでは、統合ソリューションによってどのように競争優位性を獲得できるのかをご紹介します。ぜひご参加ください。
Chandramouli Sankaranarayanan
マネジャー，ソフトウェアエンジニア（AGS）
Applied Materials | Automation Products Group
Yoram Barak, 博士
Durables Managementグローバルプロダクトマネージャー
Applied Materials | Automation Products Group
### セッション1ーアジア向け
2025年2月19日（水）
中国・台湾・東南アジア：午前9:00 ～ 10:00
日本・韓国：午前10:00 ～ 11:00
[ セッション1に登録する ](https://amat.zoom.us/webinar/register/WN_yJGmrK3LT0qtsGRQMouANQ#/registration)
### セッション2ー北米 & 欧州向け
2025年2月19日（水）
北米（太平洋時間）：午前8:00 ～ 9:00
ヨーロッパ（中央ヨーロッパ時間）：午後5:00 ～ 6:00
[ セッション2に登録する ](https://amat.zoom.us/webinar/register/WN_BQj1SVCUQK6T9xh9_xSewg#/registration)
**Event Category:** Semiconductor
---
### [Applied SmartFactory Symposium Malaysia](https://appliedsmartfactory.com/events/semiconductor-event/malaysiasymposium2024/)
**Published:** May 23, 2024
**Author:** Applied Smartfactory
**Content:**
# Applied SmartFactory Symposium Malaysia
## Applied SmartFactory のソフトウェアの力を解き放つ
半導体工場における品質と生産性の向上
[ Register Now ](https://lp.constantcontactpages.com/ev/reg/b79zp4s)
#### 2024年7月25日（木）｜午前8:45〜午後4:30｜マレーシア・ペナン
### お見逃しなく！
技術セッション、ユーザーストーリー、製品のライブデモを通じて、スマート製造に情熱を持つ専門家たちと交流しましょう。業界のエキスパートから、半導体工場の品質と生産性を向上させる方法を学ぶことができます。
### アジェンダ ハイライト：
08:45 – 09:15 受付・チェックイン
09:15 – 12:00 午前のセッション
12:00 – 13:15 昼食 & 製品ライブデモ
13:15 – 16:30 午後のセッション
## プレゼンテーション内容：
受付・チェックイン
発表者：Sean Yong（Applied Material）
08:45 - 09:15
開会の挨拶およびアジェンダ紹介
発表者：Sean Yong（Applied Material）
09:15 - 09:25
オープニング挨拶
発表者：Scott Rothenberg（Applied Material）
09:25 - 09:30
未来の製造業への変革
発表者：Dato’ KL Bock（ウエスタンデジタル）
09:30 - 10:10
スマート製造の未来を形作る自動化のトレンド
発表者：David Hanny（Applied Material）
10:10 - 10:45
半導体製造業は、結果を予測する効果的な方法を常に模索しています。工場内のばらつきをこれまで以上に減らすために、先進技術が活用されています。このセッションでは、スマート製造を推進する業界トレンドを紹介します。
未来の工場設計
発表者：Fernando Tjia（マイクロン）
10:45 - 11:20
半導体自動化AIのための統合プロセス制御
発表者：Chris Reeves（Applied Material）
11:20 - 11:55
半導体製造業界は、品質基準の向上という高まる期待に応えるため、現行の基準を超えるプロセス制御能力が求められています。このセッションでは、レイテンシーの削減、新たなアクティブ制御の導入、学習の取り込み、セットアッププロセスの自動化など、新しいパラダイムについて紹介します。
昼食 & デモ
12:00 - 13:15
革新的な故障検出による歩留まりの改善
発表者：Dr. Mohamad Zambri bin Mohd Darudin（SilTerra）
13:15 - 13:50
スマート製品構成による出力の最大化
発表者：Madhu Mamillapalli（Applied Material）
13:50 - 14:25
SmartFactory Planningソリューションは、既存のキャパシティに対して最適な部品構成を戦略的に提案することで、工場の需要負荷を最適化し、スループットを最大化します。生産効率と資源活用の向上を重視した加重最適化技術が紹介されます。
RTD Back 2 Back Tool：RTDルール出力のエンドツーエンドテストにおける適切なツールの重要性
発表者：Patrick Chua / Lee Chao Seng（インフィニオン）
14:25 - 15:00
休憩 & デモ
15:00 - 15:30
工場の生産性向上に向けたAIの旅
発表者：Samantha Duchscherer（Applied Material）
15:30 - 16:05
生産性の課題に対応するスケーラブルなAIソリューションを製造業に提供します。ロットのサイクルタイム予測や自律型リアルタイムスケジューリングエンジンの開発など、AI活用事例を紹介します。
閉会の挨拶
発表者：Scott Rothenberg（Applied Material）
16:05 – 16:10
アンケート & プレゼント抽選
発表者：Sean Yong（Applied Material） 16:10 – 16:30
*※プレゼンテーション内容は変更される場合があります。*
### お問い合わせ先
[Sean\_Yong@amat.com](mailto:Sean_Yong@amat.com)
[ Register Now ](https://lp.constantcontactpages.com/ev/reg/b79zp4s)
### マレーシア・ペナン
Courtyard by Marriott Penang
218D Jalan Macalister, George Town, 10400
## SmartFactory Symposium Malaysia
July 25, 2024
**Event Category:** Semiconductor
---
### [SmartFactory APF User Group](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-apf-user-group-2024/)
**Published:** August 29, 2024
**Author:** Applied Smartfactory
**Content:**
# SmartFactory E3 & APF Joint User Groupへの参加にご興味はありますか？
[ E3 User Group ](/ja/events/semiconductor/smartfactory-e3-user-group/)
APF User Group
#### フォームは閉じています
**Event Category:** Semiconductor
---
### [SmartFactory E3 User Group](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-e3-user-group/)
**Published:** August 29, 2024
**Author:** Applied Smartfactory
**Content:**
# SmartFactory E3 & APF Joint User Groupへの参加にご興味はありますか？
E3 User Group
[ APF User Group ](/ja/events/semiconductor/smartfactory-apf-user-group-2024/)
#### フォームは閉じています
**Event Category:** Semiconductor
---
### [Semicon India 2024](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2024/)
**Published:** August 23, 2024
**Author:** Applied Smartfactory
**Content:**
# 半導体の未来を形づくる
#### 2024年9月11日～13日｜インド・グレーター・ノイダ（デリー首都圏）India Expo Mart
SEMICON® Indiaにて、あらゆる規模の工場で品質と生産性を向上させるために、半導体メーカーがApplied SmartFactory®の統合自動化ソリューションをどのように活用しているかをご紹介します。
### また、Scott Rothenberg氏は、Smart Manufacturing Trackで、インドの未来型自律ファブの構築に関する講演を行う予定です。
#### 基調講演
「スマート工場の進化：先進の工場自動化への飛躍を目指すインドの教訓」
### 講演者：Scott Rothenberg
マネージングディレクター、副ゼネラルマネージャー
Applied Materials｜オートメーション製品グループ
日時： 2024年9月11日（水）
トラック： スマートマニュファクチャリング – インドのAI駆動型自律工場の構築
講演時間： 13:35～13:50
会場： ホール2（2階）
## Applied Materialsブース（ホール6｜H6A01）にて、最先端の統合工場自動化ソリューションをご覧いただけます。ソリューションのエキスパートチームとも直接お話しいただけます。
イベント: [](https://www.semiconindia.org/)
ブース：ホール6｜H6A01
日時：2024年9月11日～13日
## ご質問やイベントに関しては、Joy Thomas[（Joy\_Thomas@amat.com）](mailto:Joy_Thomas@amat.com)までお問い合わせください。
Joy Thomas
Applied Materials India (P) Ltd.
バンガロール
**Event Category:** Semiconductor
---
### [SmartFactory E3 User Group](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-e3-user-group/)
**Published:** August 29, 2024
**Author:** Applied Smartfactory
**Content:**
# Interested in attending our SmartFactory E3 and APF Joint User Group?
E3 User Group
[ APF User Group ](/events/semiconductor/smartfactory-apf-user-group-2024/)
#### Form is Closed.
**Event Category:** Semiconductor
---
### [SmartFactory APF User Group](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-apf-user-group-2024/)
**Published:** August 29, 2024
**Author:** Applied Smartfactory
**Content:**
# Interested in attending our SmartFactory E3 and APF Joint User Group?
[ E3 User Group ](/events/semiconductor/smartfactory-e3-user-group/)
APF User Group
#### Form is Closed.
**Event Category:** Semiconductor
---
### [Winter Simulation Conference 2024](https://appliedsmartfactory.com/events/semiconductor-event/winter-simulation-conference-2024/)
**Published:** November 11, 2024
**Author:** Applied Smartfactory
**Content:**
# 2024 Winter Simulation Conference
#### 2024年12月15日ー30日❘フロリダ州，オーランド
SmartFactoryチームは、技術セッションにおいて、当社のソリューションが、あらゆる規模の工場において計画の最適化と歩留まりの向上をどのように実現しているかをご紹介します。ぜひご参加ください。
### AutoSched®シミュレーションによる高度な計画とAIソリューションの解放
2024年12月16日（月）
午前10:00～10:45
[ セッション1に登録する ](https://amat.zoom.us/webinar/register/WN_6gbrjMYqSy204yh_G7Q5sw)
### ディスパッチングルール調整のための深層強化学習による歩留まりの改善
2024年12月17日（火）
午前10:00～10:30
[ セッション2に登録する ](https://amat.zoom.us/webinar/register/WN_TjEM7nXFTdmOmbOlUKudNA)
### 装置稼働時間の変動指標とサイクルタイムの関係を評価する比較研究
2024年12月17日（火）
午前11:00～11:30
[ セッション3に登録する ](https://amat.zoom.us/webinar/register/WN_TjEM7nXFTdmOmbOlUKudNA)
全[スケジュール](https://meetings.informs.org/wordpress/wsc2024/schedule/)を見る
**Event Category:** Semiconductor
---
### [SmartFactory Durables Management Webinar: Unlocking the Power of Automation](https://appliedsmartfactory.com/events/semiconductor-event/smartfactory-durables-management-webinar/)
**Published:** January 29, 2025
**Author:** Applied Smartfactory
**Content:**
# SmartFactory Durables Management Webinar: Unlocking the Power of Automation
#### February 19, 2025
### SmartFactory Durables Management Webinar: Unlocking the Power of Automation
Combining durables and consumables management with systems such as SPC and Real-Time Dispatching creates an unparalleled powerhouse for running assets at peak efficiency. Come join us as we present how you can gain a competitive advantage with integrated solutions.
Chandramouli Sankaranarayanan
Manager, Software Engineer (AGS)
Applied Materials | Automation Products Group
Yoram Barak, PhD
Durables Management Global Product Manager
Applied Materials | Automation Products Group
### Session 1 – Asia
Wednesday, February 19, 2025
9:00 – 10:00 am China, Taiwan, Southeast Asia
10:00 – 11:00 am Japan, Korea
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_yJGmrK3LT0qtsGRQMouANQ#/registration)
### Session 2 – North America and Europe
Wednesday, February 19, 2025
8:00 – 9:00 am Pacific
5:00 – 6:00 pm Central Europe
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_BQj1SVCUQK6T9xh9_xSewg#/registration)
**Event Category:** Semiconductor
---
### [SMART FACTORY Expo videos – Tokyo 2025](https://appliedsmartfactory.com/events/semiconductor-event/smart-factory-expo-japan-2025-videos/)
**Published:** December 18, 2024
**Author:** Applied Smartfactory
**Content:**
# SMART FACTORY Expo - 2025
Tokyo Big Sight, Japan
Jan 22-24, 2025
### Together we’re redefining the power of factory automation without limits.
### Improve efficient decision-making with
#### SmartFactory Quality solutions
By Vishali Ragam
[ Watch now ](#)
### Drive manufacturing excellence with
#### SmartFactory MES solutions
By Dan Meier
[ Watch now ](#)
### Optimize factory assets with
#### SmartFactory Productivity solutions
By Michael Frenna
[ Watch now ](#)
### Accelerate robot integration with
#### SmartFactory AutoReady solutions
By John Robinson
[ Watch now ](#)
**Event Category:** Semiconductor
---
### [SMART FACTORY Expo – Tokyo 2025](https://appliedsmartfactory.com/events/semiconductor-event/smart-factory-expo-japan-2025/)
**Published:** November 15, 2024
**Author:** Applied Smartfactory
**Content:**
[ 日本語 (Japanese) ](/ja/events/semiconductor-ja/smart-factory-expo-japan-2025/)
[ English (英語) ](#)
# SMART FACTORY Expo - 2025
Tokyo Big Sight, Japan
Jan 22-24, 2025
Join us at SMART FACTORY Expo to learn how manufacturers are advancing factory automation with fully integrated SmartFactory solutions, using data-driven intelligence to improve quality and enhance productivity in any factory.
**Visit booth S30-14** to see our live solution demos and meet our team of technology experts.
Don’t miss our presentation:
## Increasing Manufacturing Output by Advanced Technology
### **South Hall, 2nd floor, New Product/New Technology Seminar - New Tech Trend - Room (South 1)**
### Friday, January 24 at 12:00 p.m. JST
### Highlights:
- Cutting-edge technologies
- Real-world use cases
- Live solution demos
David Hanny
##### Senior Director
Automation Products Group | Applied Materials
[ More Information ](https://www.fiweek.jp/tokyo/en-gb.html#/%20)
### If you have questions or want to connect at the event, reach out to
[Shin\_Sekido@amat.com](mailto:Shin_Sekido@amat.com)
**Event Category:** Semiconductor
---
### [Semicon India 2024](https://appliedsmartfactory.com/events/semiconductor-event/semicon-india-2024/)
**Published:** August 23, 2024
**Author:** Applied Smartfactory
**Content:**
# Shaping the Semiconductor Future
#### September 11 - 13, 2024 | India Expo Mart, Greater Noida, Delhi NCR
Join us at SEMICON® India to learn how semiconductor manufacturers are leveraging our Applied SmartFactory® fully integrated automation solutions to enhance quality and productivity in factories of any size.
### We’re delighted to announce that Scott Rothenberg will be presenting in during the Smart Manufacturing Track – Building India’s Autonomous Fab of the Future.
#### Presentation
“Evolution of Smart Manufacturing: Lessons for India’s Leap Ahead to Advanced Factory Automation.”
### Scott Rothenberg
Managing Director, Deputy General Manager
Applied Materials | Automation Products Group
Date: Wednesday, September 11, 2024
Track: Smart Manufacturing – Building India’s AI-Driven Autonomous Factory of the Future
Presentation Time: 13:35 – 13:50
Location: Hall 2 (Level 2)
## Visit our Applied Materials booth in Hall-6, H6A01 to explore our cutting-edge integrated factory automation solutions and meet our team of solution experts.
Event: [](https://www.semiconindia.org/)
Date: September 11-13, 2024
Booth: Applied Materials booth in Hall-6 | H6A01
## If you have questions or want to connect at the event, reach out to [Joy\_Thomas@amat.com](mailto:Joy_Thomas@amat.com)
Joy Thomas
Applied Materials India (P) Ltd.
Bengaluru
**Event Category:** Semiconductor
---
### [APCSM Conference 2024](https://appliedsmartfactory.com/events/semiconductor-event/apcsm-conference-2024/)
**Published:** September 13, 2024
**Author:** Applied Smartfactory
**Content:**
# APCSM Conference 2024
## Advanced Process Control – Smart Manufacturing
#### October 7-10 | Toronto, Canada
Technical Session Agenda
### Optimizing Neural Network Run-to-Run with Nonthreaded Concept
Presenter: Ivan Chen, Applied Materials
Date and Time: Tuesday, October 8, 1:00 – 1:30 pm EDT
[ Register Now ](https://www.apcsmconference.com/event/312dd91f-731d-420a-87d5-a90b07f30ab3/regProcessStep1:7388af2f-c4a7-43cc-a2dd-5de41c913676)
### Presentation Highlights
### Discover how our innovative machine learning control method handles non-thread control effortlessly.
### Our approach eliminates the need for data collection for every thread by combining context information and physical knowledge. Witness the impressive real production results of this method.
### Enhance ML system stability and efficiency with our Python HA/LB architecture. Build ML servers for reliable R2R performance prediction in real-world applications.
### Explore the future of ML controls. In 2020, we showcased the potential of neural networks in forecasting process drift with our RNN and CNP model structure.
### Unlock the true potential of machine learning in real-world controls.
## Authors
- Ivan Chen
- Tony Li
- Shijing Wang
- Yeo Zi Ping Leonard
- Ko Ko Win
- Tristan Yu
- Allen Yang
Abstract Number: 24003
## If you have questions or want to connect at the event, reach out to SJ Wang at [shijing\_wang@amat.com](mailto:shijing_wang@amat.com)
**Event Category:** Semiconductor
---
### [Winter Simulation Conference 2024](https://appliedsmartfactory.com/events/semiconductor-event/winter-simulation-conference-2024/)
**Published:** November 11, 2024
**Author:** Applied Smartfactory
**Content:**
# 2024 Winter Simulation Conference
#### Dec 15-18, 2024 | Orlando,FL
Please join us at our technical sessions listed below to learn how SmartFactory solutions are optimizing planning and improving yield in any size factory.
### Unlocking Enhanced Planning and AI Solutions with AutoSched® Simulation
Monday, December 16, 2024
10:00 – 10:45 am
[ Register for session 1 ](https://amat.zoom.us/webinar/register/WN_6gbrjMYqSy204yh_G7Q5sw)
### Yield Improvement Using Deep Reinforcement Learning for Dispatch Rule Tuning
Tuesday, December 17, 2024
10:00 – 10:30 am
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_TjEM7nXFTdmOmbOlUKudNA)
### Comparison Study to Evaluate the Relationship Between Equipment Uptime Variability Metrics and Cycle Time
Tuesday, December 17, 2024
11:00 – 11:30 am
[ Register for session 2 ](https://amat.zoom.us/webinar/register/WN_TjEM7nXFTdmOmbOlUKudNA)
View full [schedule](https://meetings.informs.org/wordpress/wsc2024/schedule/)
**Event Category:** Semiconductor
---
### [SMART FACTORY Expo – Tokyo 2025](https://appliedsmartfactory.com/events/semiconductor-event/smart-factory-expo-japan-2025/)
**Published:** November 15, 2024
**Author:** Applied Smartfactory
**Content:**
[ 日本語 (Japanese) ](#)
[ English (英語) ](/events/semiconductor/smart-factory-expo-japan-2025/)
# スマート工場EXPO
東京ビッグサイト（南ホール）
2025年1月22日ー24日
第9回スマート工場EXPOに出展します。
完全に統合された SmartFactory ソリューションにより、製造業者がどのようにデータに基づくインテリジェンスを活用し、あらゆる工場で品質を向上させ、生産性を高め、工場の自動化を推進しているのかをご確認いただけます。
ブース S30-14 にお越しいただき、当社のソリューションのライブデモをご覧いただくともに、技術エキスパートチームとも直接お話しいただけます。
私たちのプレゼンテーションをお見逃しなく
## 生産性の向上を実現する最先端技術
### **セミナー会場位置 ：南ホール 2 階 「新製品・新技術セミナー～New Tech Trend～ 会場（南①）」**
### 2025年1月24日 12:00 PM
### ハイライト
- 最先端技術
- 実際の使用例
- ソリューションのライブデモ
David Hanny
##### シニアディレクター
オートメーションプロダクツグループ | アプライドマテリアルズ
[ 詳細情報 ](https://www.fiweek.jp/tokyo/ja-jp/about/sfe.html)
### お問い合わせ、ご質問はこちらまで
[Shin\_Sekido@amat.com](mailto:Shin_Sekido@amat.com)
**Event Category:** Semiconductor
---
### [Innovation Forum Automation 2025](https://appliedsmartfactory.com/events/semiconductor-event/innovation-forum-automation-2025/)
**Published:** November 26, 2024
**Author:** Applied Smartfactory
**Content:**
# Optimizing existing assets
## SmartFactory productivity solutions fully integrated
22nd Innovation Forum for Automation
January 30/31, 2025 | Dresden, Germany
## Keynote | **Orchestrating Scalable AI Solutions**
### January 30, 2025
### Samantha Duchscherer
##### Global Product Manager
Applied Materials | Automation Products Group
### Shijing (SJ) Wang
##### Global Product Manager
Applied Materials | Automation Products Group
### Keynote Highlights:
### Discover our unified approach for deploying AI solutions that minimize defects and maximize throughput.
### Strive for zero defects by implementing AI configurations in a Run-to-Run controller, enabling efficient compensation for tool and process drifts over time, even in high-mix and low-volume scenarios.
### Co-Optimize yield and throughput by AI automatically configuring the optimal decision required for real-time scheduling.
### For questions, contact
[Thomas\_Wimmer@amat.com](mailto:Thomas_Wimmer@amat.com)
**Event Category:** Semiconductor
---
### [Applied SmartFactory Symposium Malaysia](https://appliedsmartfactory.com/events/semiconductor-event/malaysiasymposium2024/)
**Published:** May 23, 2024
**Author:** Applied Smartfactory
**Content:**
# Applied SmartFactory Symposium Malaysia
## Unleashing the Power of Applied SmartFactory Software
Improving quality and productivity in semiconductor factories
[ Register Now ](https://lp.constantcontactpages.com/ev/reg/b79zp4s)
#### 8:45 AM – 4:30 PM | Thursday July 25, 2024 | Penang, Malaysia
### Don’t miss out!
Join us for a day of technical sessions, user stories, and live product demos. Learn from industry experts how to improve quality and productivity in semiconductor factories. Network with professionals who share your passion for smart manufacturing.
### Agenda Highlights:
08:45 – 09:15 Check-in Reception
09:15 – 12:00 Morning Sessions
12:00 – 13:15 Lunch and Live Product Demos
13:15 – 16:30 Afternoon Sessions
## Presentations:
Check-in Reception
Presented by Sean Yong, Applied Materials
08:45 - 09:15
Welcome and Agenda
Presented by Sean Yong, Applied Materials
09:15 - 09:25
Welcome Remarks
Presented by Scott Rothenberg, Applied Materials
09:25 - 09:30
Transforming Manufacturing for the Future
Presented by Dato’ KL Bock, Western Digital
09:30 - 10:10
Automation Trends Shaping the Smart Manufacturing Landscape
Presented by David Hanny, Applied Materials
10:10 - 10:45
Semiconductor manufacturing is in constant search of effective methods to predict outcomes. Advanced technologies are being used to reduce variability in the factory to a higher degree than has been experienced. This session will cover industry trends that advance smart manufacturing initiatives.
Design of a Future Factory
Presented by Fernando Tjia, Micron
10:45 - 11:20
Unified Process Control for Semiconductor Automation AI
Presented by Chris Reeves, Applied Materials
11:20 - 11:55
The semiconductor manufacturing industry is under increasing pressure to meet rising expectations and demands for higher quality standards. To address this, there is a need for enhanced process control capabilities that go beyond current standards, leading to the development of new paradigms focused on reducing latency, implementing a new set of active controls, capturing learning, and automating setup processes.
Lunch and Demos
12:00 - 13:15
Yield Improvement through Innovative Fault Detection
Presented by Dr. Mohamad Zambri bin Mohd Darudin, SilTerra
13:15 - 13:50
Maximizing Output with Smart Product Mix
Presented by Madhu Mamillapalli, Applied Materials
13:50 - 14:25
SmartFactory Planning solution optimizes factory demand loading to maximize throughput by strategically suggesting part mix combinations for existing capacity. It emphasizes the importance of enhancing production efficiency and resource utilization through weighted optimization techniques.
RTD Back 2 Back Tool : Importance of right tools for end-to-end testing of RTD Rule Output
Presented by Patrick Chua / Lee Chao Seng, Infineon
14:25 - 15:00
Break and Demos
15:00 - 15:30
An AI Journey to Increase Factory Productivity
Presented by Samantha Duchscherer, Applied Materials
15:30 - 16:05
We empower manufacturing with scalable AI solutions that address productivity challenges. Use cases that navigate the AI movement include predicting lot cycle time and developing an autonomous real-time scheduling engine.
Closing Remarks
Presented by Scott Rothenberg, Applied Materials
16:05 – 16:10
Survey and Giveaways
Presented by Sean Yong, Applied Materials
16:10 – 16:30
*\*Presentations are subject to change.*
### For questions, contact
[Sean\_Yong@amat.com](mailto:Sean_Yong@amat.com)
[ Register Now ](https://lp.constantcontactpages.com/ev/reg/b79zp4s)
### Penang, Malaysia
Courtyard by Marriott Penang
218D Jalan Macalister, George Town, 10400
## SmartFactory Symposium Malaysia
July 25, 2024
**Event Category:** Semiconductor
---
### [Lorem Ipsum是什麼？](https://appliedsmartfactory.com/zh-hans/events/%event-category%/lorem-ipsum是什麼？/)
**Published:** August 2, 2024
**Author:** Applied Smartfactory
**Content:**
Lorem Ipsum是什麼？ 是印刷和排版行業的簡單虛擬文本。自 1500 年代以來，Lorem Ipsum 一直是行業標準的虛擬文本，當時一位不知名的印刷商拿走了一堆字體並將其打亂以製作一本字體樣本簿。它不僅經歷了五個世
---
### [Applied SmartFactory Symposium Malaysia](https://appliedsmartfactory.com/events/semiconductor-event/malaysiasymposium2024/)
**Published:** May 23, 2024
**Author:** Applied Smartfactory
**Content:**
# Applied SmartFactory Symposium Malaysia
## Unleashing the Power of Applied SmartFactory Software
Improving quality and productivity in semiconductor factories
[ Register Now ](https://lp.constantcontactpages.com/ev/reg/b79zp4s)
#### 8:45 AM – 4:30 PM | Thursday July 25, 2024 | Penang, Malaysia
### Don’t miss out!
Join us for a day of technical sessions, user stories, and live product demos. Learn from industry experts how to improve quality and productivity in semiconductor factories. Network with professionals who share your passion for smart manufacturing.
### Agenda Highlights:
08:45 – 09:15 Check-in Reception
09:15 – 12:00 Morning Sessions
12:00 – 13:15 Lunch and Live Product Demos
13:15 – 16:30 Afternoon Sessions
## Presentations:
Check-in Reception
Presented by Sean Yong, Applied Materials
08:45 - 09:15
Welcome and Agenda
Presented by Sean Yong, Applied Materials
09:15 - 09:25
Welcome Remarks
Presented by Scott Rothenberg, Applied Materials
09:25 - 09:30
Transforming Manufacturing for the Future
Presented by Dato’ KL Bock, Western Digital
09:30 - 10:10
Automation Trends Shaping the Smart Manufacturing Landscape
Presented by David Hanny, Applied Materials
10:10 - 10:45
Semiconductor manufacturing is in constant search of effective methods to predict outcomes. Advanced technologies are being used to reduce variability in the factory to a higher degree than has been experienced. This session will cover industry trends that advance smart manufacturing initiatives.
Design of a Future Factory
Presented by Fernando Tjia, Micron
10:45 - 11:20
Unified Process Control for Semiconductor Automation AI
Presented by Chris Reeves, Applied Materials
11:20 - 11:55
The semiconductor manufacturing industry is under increasing pressure to meet rising expectations and demands for higher quality standards. To address this, there is a need for enhanced process control capabilities that go beyond current standards, leading to the development of new paradigms focused on reducing latency, implementing a new set of active controls, capturing learning, and automating setup processes.
Lunch and Demos
12:00 - 13:15
Yield Improvement through Innovative Fault Detection
Presented by Dr. Mohamad Zambri bin Mohd Darudin, SilTerra
13:15 - 13:50
Maximizing Output with Smart Product Mix
Presented by Madhu Mamillapalli, Applied Materials
13:50 - 14:25
SmartFactory Planning solution optimizes factory demand loading to maximize throughput by strategically suggesting part mix combinations for existing capacity. It emphasizes the importance of enhancing production efficiency and resource utilization through weighted optimization techniques.
RTD Back 2 Back Tool : Importance of right tools for end-to-end testing of RTD Rule Output
Presented by Patrick Chua / Lee Chao Seng, Infineon
14:25 - 15:00
Break and Demos
15:00 - 15:30
An AI Journey to Increase Factory Productivity
Presented by Samantha Duchscherer, Applied Materials
15:30 - 16:05
We empower manufacturing with scalable AI solutions that address productivity challenges. Use cases that navigate the AI movement include predicting lot cycle time and developing an autonomous real-time scheduling engine.
Closing Remarks
Presented by Scott Rothenberg, Applied Materials
16:05 – 16:10
Survey and Giveaways
Presented by Sean Yong, Applied Materials
16:10 – 16:30
*\*Presentations are subject to change.*
### For questions, contact
[Sean\_Yong@amat.com](mailto:Sean_Yong@amat.com)
[ Register Now ](https://lp.constantcontactpages.com/ev/reg/b79zp4s)
### Penang, Malaysia
Courtyard by Marriott Penang
218D Jalan Macalister, George Town, 10400
## SmartFactory Symposium Malaysia
July 25, 2024
**Event Category:** Semiconductor
---
## Webinars
### [自动化资产追踪，提升良率与生产力](https://appliedsmartfactory.com/webinars/semiconductor-webinar/automate-semiconductor-asset-tracking-for-better-yield-and-productivity/)
**Published:** September 25, 2025
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 了解如何通过自动化追踪移动资产（如耐用品和消耗品）来提升晶圆厂的质量与效率。在本次网络研讨会中，Yoram Barak 将为您详解 Asset Trace 和 SPC 等集成系统如何提升供应商质量，并分享 SmartFactory GenAI 功能的早期洞察。
**Content:**
#### 观看网络研讨会
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [Speeding up the flow from sensing to resolution](https://appliedsmartfactory.com/webinars/semiconductor-webinar/speeding-up-sensing-to-resolution-with-genai/)
**Published:** March 11, 2026
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** In this webinar, Yoram Barak, David Wilson and Charles Largo detail how the integration layer between SmartFactory Fault Detection (FD), Alarm Management (AMS), SmartFactory Knowledge Advisor (KA) and SmartFactory Maintenance Management (SFMM) supports G2G timeline shortening.
**Content:**
#### Watch Webinar
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [利用AI和机器学习技术帮助制造企业提高良率](https://appliedsmartfactory.com/zh-hans/webinars/semiconductor-webinar/increase-yield-through-ai/)
**Published:** August 25, 2022
**Author:** SJ Wang
**Excerpt:** 了解应用材料公司 E3™ 平台如何利用基于AI和机器学习技术的平台，通过 FDC、SPC、run-to-run (R2R) 软件协作运行，实时优化制程，提高设备利用率，降低缺陷，提高良率。
**Content:**
#### 观看网络研讨会
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [SmartFactory SPC：卓越质量管控之道](https://appliedsmartfactory.com/webinars/semiconductor-webinar/smartfactory-spc-mastering-quality/)
**Published:** June 7, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Vishali Ragam 将主讲本次网络研讨会，深入探讨统计过程控制 (SPC) 在工艺质量管理中的关键作用。
**Content:**
#### 观看网络研讨会
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [实现人工流程自动化](https://appliedsmartfactory.com/webinars/semiconductor-webinar/automating-the-manual/)
**Published:** June 7, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 在本次网络研讨会中，Selim Nahas、Yoram Barak 和 Chandramouli Sankaranarayanan 将探讨耐用设备监控在半导体制造中的关键作用。
**Content:**
#### 观看网络研讨会
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [释放自动化潜能](https://appliedsmartfactory.com/webinars/semiconductor-webinar/unlocking-the-power-of-automation/)
**Published:** February 28, 2025
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** 在本次网络研讨会中，Yoram Barak 和 Chandramouli Sankaranarayanan 将探讨如何通过耐用设备与耗材管理优化资产效率。
**Content:**
#### 观看网络研讨会
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [Automate asset tracking for better yield and productivity](https://appliedsmartfactory.com/webinars/semiconductor-webinar/automate-semiconductor-asset-tracking-for-better-yield-and-productivity/)
**Published:** September 25, 2025
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Discover how automating mobile asset tracking—like durables and consumables—can drive quality and efficiency in your fab. In this webinar, Yoram Barak explains how integrated systems like Asset Trace and SPC enhance supplier quality. He also shares early insights into SmartFactory’s GenAI capabilities.
**Content:**
#### Watch Webinar
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [Automating the Manual](https://appliedsmartfactory.com/webinars/semiconductor-webinar/automating-the-manual/)
**Published:** June 7, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** このウェビナーでは、Selim Nahas氏、Yoram Barak氏、Chandramouli Sankaranarayanan氏が、半導体製造における耐久財のモニタリングの重要性についてお話しします。
**Content:**
#### ウェビナーを見る
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [Unlocking the power of automation](https://appliedsmartfactory.com/webinars/semiconductor-webinar/unlocking-the-power-of-automation/)
**Published:** February 28, 2025
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** In this webinar, Yoram Barak and Chandramouli Sankaranarayanan discuss how to maximize efficiency of assets through durables and consumables management.
**Content:**
#### Watch Webinar
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [Automating the Manual](https://appliedsmartfactory.com/webinars/semiconductor-webinar/automating-the-manual/)
**Published:** June 7, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** In this webinar, Selim Nahas, Yoram Barak and Chandramouli Sankaranarayanan discuss the importance of durables monitoring in semiconductor manufacturing.
**Content:**
#### Watch Webinar
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
### [SmartFactory SPC: Mastering Quality](https://appliedsmartfactory.com/webinars/semiconductor-webinar/smartfactory-spc-mastering-quality/)
**Published:** June 7, 2024
**Author:** SmartFactory Automation Solution Experts Team
**Excerpt:** Vishali Ragam leads a webinar focused on statistical process control and how it fits into process quality.
**Content:**
#### Watch Webinar
### Watch webinar replay
Please fill the form to view this webinar. All fields are mandatory.
First Name: \*
Last Name: \*
Company Email: \*
Country: \*
—Please choose an option—AfghanistanAlbaniaAlgeriaAmerican SamoaAndorraAngolaAnguillaAntarcticaAntigua and BarbudaArgentinaArmeniaArubaAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral European RepublicChadChileChinaColombiaComorosCongoCosta RicaCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEast TimorEcuadorEgyptEl SalvadorEnglandEquatorial GuineaEritreaEstoniaEthiopiaFalkland IslandsFaroe IslandsFinlandFranceFrench GuianaGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuineaGuinea-BissauGuyanaHaitiHeard Island and McDonald IslandsHoly See (Vatican City State)HondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsraelItalyIvory CoastJamaicaJapanJordanKazakhstanKenyaKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyan Arab JamahiriyaLiechtensteinLithuaniaLuxembourgMacaoNorth MacedoniaMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroOpen SansMoroccoMozambiqueMyanmarNamibiaNepalNetherlandsNetherlands AntillesNew ZealandNicaraguaNigerNigeriaNorth KoreaNorthern IrelandNorwayOmanPakistanPalestinePanamaPapua New GuineaParaguayPeruPhilippinesPolandPortugalPuerto RicoQatarReunionRomaniaRussian FederationRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and the GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaScotlandSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSomaliaSouth AMESouth KoreaSouth SudanSpainSri LankaSudanSurinameSvalbard and Jan MayenSwazilandSwedenSwitzerlandSyriaTaiwan, ChinaTajikistanTanzaniaThailandThe Democratic Republic of CongoTogoTrinidad and TobagoTunisiaTurkeyTurkmenistanTurks and Caicos IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVenezuelaVietnamVirgin Islands, BritishVirgin Islands, U.S.WalesWestern SaharaYemenZambiaZimbabwe
Company Name: \*
Applied Materials, Inc. is located at 3050 Bowers Avenue, P.O. Box 58039, Santa Clara, CA 95054-3299, United States. Applied Materials' websites and communications are subject to our [Privacy Policy](https://www.appliedmaterials.com/privacy) and [Terms of Use](https://www.appliedmaterials.com/terms-of-use). By submitting this form, you consent to Applied Materials processing your personal information to be contacted by our sales specialist.
Δ
**Webinar Category:** Semiconductor Webinars
---
## Battery Blog
### [Powering the future: exploring process quality solutions in the battery sector](https://appliedsmartfactory.com/battery-blog/automation/battery-manufacturing-process-quality-solutions/)
**Published:** April 1, 2025
**Author:** Agnes Sowa and Vishali Ragam
**Excerpt:** How to achieve higher quality, reliability and efficiency with statistical process control and fault detection
**Content:**
## What’s Inside
- [ Enhanced process understanding ](#index1)
- [ Improved process control ](#index2)
- [ Data driven decision making ](#index3)
- [ Example ](#index4)
- [ Predictive maintenance ](#index5)
- [ Conclusion ](#index6)
With the fast EV transition, legacy battery manufacturers whose practices have stayed largely the same for 30 or more years are building new factories to scale with demand, making massive investments often far from home. In this era of IoT connectivity, that can produce information overload if the operations attempt to do things the same way as they have in the past. It is in their best interest to extract meaningful facts about their operations based on evidence. As we speak of faster resolutions, knowledge discovery in real time becomes a key component; one such discovery is to replace decades of tribal knowledge by identifying causal relationships and connections among data from different sources. In this blog, statistical process control (SPC) is studied and characterized based on its relationship with equipment performance sensor data through Fault Detection (FD).
### Enhanced process understanding
By analyzing the relationship between SPC data (e.g., coating thickness variations in the electrode process) and equipment sensor data (e.g., coating head temperature, roller speed, vibration signature or pressure), manufacturers can gain a deeper understanding of how equipment conditions influence process outcomes.
This integrated analysis can uncover hidden correlations that might not be apparent when examining individual data streams in isolation. For example, subtle changes in equipment vibration might correlate with increasing coating thickness variations, as shown in figure 1 below. With fault detection, meanwhile, we typically set limits to monitor alarms and understand how a system runs under nominal conditions for a given recipe. However, variation within univariate analysis (UVA) limits is meaningful to the strategy of correlating sight measurements with sensor data. While the ability to assign a diagnosis in real time can be achieved using an automated system, a human would be hard-pressed to identify and mitigate risk to electrodes quickly enough.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/04/figure1-1.jpg) Figure 1: Interrelationship between equipment vibrations and the coating thickness showing inverse correlation.
It must be acknowledged that setting boundaries on the data used to interpret limits and actions is always challenging. For example, environment fluctuations or equipment interventions, such as replacing equipment components, can result in variations. Also, different devices with different topographies tend to add variations of their own for the same recipe. The secret is to discern the appropriate period, events and subset of sensors to monitor and understand the actual capabilities of the process for a given product and recipe. As battery OEMs ramp up production, this must become an automated exercise, or it will not scale to meet the factory’s rate and yield needs. Throughout, it must be continuously validated against the SPC data using automation.
### Improved process control
By continuously monitoring SPC data alongside equipment sensor data, as shown in figure 2, process engineers or automation systems can make real-time adjustments to equipment settings and process parameters to maintain optimal performance and minimize variations.
Additionally, if they proactively address equipment-related issues that impact product quality, manufacturers can significantly reduce scrap rates and improve overall yield.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/04/figure2-2.jpg) Figure 2: Equipment sensors correlations with SPC inline measurements with calculated Pearson Coefficient
### Data-driven decision making
The integrated data provides a more comprehensive view of the manufacturing process, enabling data-driven decisions regarding equipment maintenance, process optimization, and overall production strategy.
### Example
Imagine a scenario where an increase in coating thickness variations is observed in the SPC data. By analyzing this data in conjunction with equipment sensor data (e.g., a gradual decrease in coating head temperature), maintenance personnel can suspect a potential issue with the temperature control system (see figure 3). Proactive maintenance can then be scheduled to prevent the issue from escalating and causing higher scrap rates.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/04/figure3-1.jpg) Figure 3. This recipe chart shows sensor trace data that an integrated system would continuously correlate to the SPC chart shown in Figures 1 or 2.
### Predictive maintenance
Equipment sensor data (temperature, vibration, pressure, current draw, etc.) often shows subtle changes before a major failure occurs. For experienced manufacturers, this shows up as tribal knowledge in the teams who have worked on the shop floor for decades. As these companies scale production, build new factories, and hire new workers (often oceans away from home), they are challenged to replace that tribal knowledge in the new facilities. By overlaying this data with SPC data, manufacturers can identify early warning signs of impending equipment issues and run their new factories with the same or better yields than their home-based operations.
Predictive maintenance allows for proactive maintenance scheduling, minimizing unplanned downtime and maximizing equipment utilization. By addressing potential issues before they escalate, manufacturers can extend the lifespan of their equipment and reduce maintenance costs.
### Conclusion
As battery manufacturing continues to advance, the role of SPC and FD correlation analysis will only become more important. Manufacturers embracing this integrated approach are poised to stay ahead of the curve, meeting the demands of today’s EV market with confidence and agility.
SmartFactory Process Control explicitly exposes the behavior of manufacturing tools and processes for customized, continuous, and automated adjustments. This enables battery manufacturers to achieve high quality standards, at higher roll speeds and efficiency. SmartFactory is committed to delivering best-in-class practices developed in the semiconductor industry to battery manufacturers with a focus on maximizing production yields and efficiency.
## About the Authors
Agnes Sowa, Battery Manufacturing Segment Manager
Agnes is the segment manager overseeing battery manufacturing and strategic alliances. Prior to joining Applied Materials Automation Product Group, Agnes was Manager of Smart Factory Partnerships at Panasonic Connect, overseeing manufacturing technology implementations of productivity, automation, MES and maintenance software. She holds an M.B.A. in Finance from DePaul University, and a B.S. in Mechanical Engineering from Illinois Institute of Technology in Chicago.
Vishali Ragam, Global Product Manager, SPC
Vishali has been working in the semiconductor industry for more than 15 years. Prior to joining Applied Materials, she worked at Micron Technology, first as a process engineer and then as a senior quality engineer. She has been with Applied for seven years, having joined the company as a quality solutions architect. Vishali is currently a Global Product Manager overseeing SmartFactory SPC3D ®, an advanced process control (APC) engine that runs statistics to determine if processes are within spec to improve product yield. Vishali has an MS in mechanical engineering from Oklahoma State University, and a bachelor’s in mechanical engineering from Osmania University, in Hyderabad, Telangana, India.
**Battery Category:** Battery Automation, Battery Manufacturing
---
### [Cutting downtime with integrated quality and predictive maintenance](https://appliedsmartfactory.com/battery-blog/automation/battery-gigafactory-anomaly-detection-ensemble-case-study/)
**Published:** December 9, 2025
**Author:** Agnes Sowa, Battery Manufacturing Segment Manager
**Excerpt:** Case study: How deploying Anomaly Detection Ensemble saved millions
**Content:**
[ Part 1](/battery-blog/automation/battery-gigafactory-cutting-downtime-with-integrated-quality-predictive-maintenance/)
## This 2-part blog series was inspired by a live presentation delivered at The Battery Show North America on October 8, 2025
## Live Presentation
“Using semiconductor-proven Fault Detection to reduce downtime in ramp-up and high-volume electrode process.”
### Agnes Sowa
Battery Segment Manager
Applied Materials | Automation Products Group
## What’s Inside
- [ Early manufacturing ](#index1)
- [ Stone to steam ](#index2)
- [ Buzzwords vs. blueprints ](#index3)
- [ Focus on the goal ](#index4)
- [ Up next ](#index5)
India can skip over the decades and billions of dollars that its peers invested to develop the cutting-edge smart manufacturing technologies that are best practice today. In doing so, new semiconductor factories in India, both wafer fab and packaging, can enjoy improved time to market while optimizing yield, cost, and output. In short, India’s semiconductor industry can benefit from the collective work, investment and learnings of the rest of the world to build the smartest, most productive factories, building the highest quality products at the lowest cost. They can shift the S-curve, as we say, to produce more good die at every stage of the factory lifecycle.
In this first blog, we’ll look at the origins of manufacturing and what it means to make it “smart.”
### Background
In our [previous article](/battery-blog/automation/battery-gigafactory-cutting-downtime-with-integrated-quality-predictive-maintenance/), we discussed how gigafactories are leveraging best practices from electronics and semiconductor manufacturing, such as fault detection, to optimize maintenance. We also introduced our Anomaly Detection Ensemble (ADE) solution. This case study looks at the deployment of ADE to simplify the process of automating maintenance, resulting in significant cost savings to the customer.
### Making maintenance objectives quality objectives
Quality teams concentrate on yields, which translate directly into free cash flow for the business. This makes them much more tightly connected to company profitability than the maintenance team, whose focus is typically on asset uptime and availability (throughput)—but if they are doing their jobs right, they are removed from the main daily operations. Having a competitive battery gigafactory means you are getting maximum overall equipment effectiveness (OEE)—to oversimplify, running highest throughput at highest yield.
By reframing maintenance objectives as quality objectives—aiming to prevent defects tied to equipment downtime—you’re effectively aligning your maintenance operations with the quality team that holds the key priorities, resources, and strong links to business goals. In practice, process engineers review statistical process control (SPC) data, leverage fault detection (FD) to find root causes (the why in a process 8D), and build process Failure Mode Effects Analyses (FMEAs), all of which help keep the maintenance schedule alive as an active tool to reduce process failures. Whenever a new failure mode or lesson arises, you have another team, the quality team, supporting your work.
### Use case
In this case, we worked with a gigafactory that manufactures cells for the automotive industry. Looking at the factory’s fault detection trace data in figure 1, below, the trough in the data indicates a breakdown of the equipment. We hypothesized that implementation of ADE could potentially improve the customer’s operation by approximately $6-800K by extending their maintenance intervals.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/12/blog-2-figure-1.webp) Figure 1: Fault detection trace data for EV battery gigafactory, where BM indicates the breakdown of equipment.
Our engineers looked at the historical data from the customer’s site and concluded that there was no indication in the trace data or any of the derivative signals in the chart that breakdown was about to happen. However, what you see with ADE in figure 2 is the data from the chart combined with a prediction index. This was derived by taking multiple flows from fault detection sensors, combining them into an index, and using machine learning to make a prediction. The result is a prediction index showing the issue with two to three hours of advanced notice before there’s an equipment breakdown.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/12/blog-2-figure-2.webp) Figure 2: FD data from Fig 1 has been combined into ADE prediction index which anticipates the breakdown by over 2 hours
With this approach, it took just three months to install ADE, customize it, choose the right algorithms, and run it in live production—realizing enough value that the customer expanded it across their plant and other global sites.
Our main hypothesis was cutting maintenance events and downtime, which we did, but we also shifted unplanned maintenance toward scheduled, planned interventions—cutting scrap and resulting in a recalculated operational savings in the millions of dollars.
Considering each phase and the resources needed for this type of implementation, there are some factors to note: data resources and careful algorithm selection is important and working with the process engineers is critical to success. The goal is to link your maintenance, trace, test, alignment, and fault detection data together.
Picking and prioritizing use cases that fit the business model is crucial. Sometimes, a preventive maintenance work instruction lets you skip steps, but the real gain from doing so can be small (you’ve already got the cover open and a tech onsite, so there’s minimal extra time). This is where your maintenance team’s expertise guides decision-making based on ROI and cost-benefit, and that’s how you build the model.
With ADE, we believe we’ve made automating maintenance implementation simpler and effectively automated the scheduling for cell manufacturing.
### Conclusion
The semiconductor industry addresses quality and predictive maintenance in an integrated fashion—quality leads and maintenance follows in support of yield and performance. For giga manufacturers to adopt this best practice – and do it well—start with SPC to answer the ‘what’ of your process, build from there using FD software to connect equipment sensors, then move into predictive maintenance modeling ADE to boost maintenance operations, extend service intervals, and reduce downtime.
**Battery Category:** Battery Automation, Battery Manufacturing
---
### [Cutting downtime with integrated quality and predictive maintenance](https://appliedsmartfactory.com/battery-blog/automation/battery-gigafactory-cutting-downtime-with-integrated-quality-predictive-maintenance/)
**Published:** December 9, 2025
**Author:** Agnes Sowa, Battery Manufacturing Segment Manager
**Excerpt:** How battery gigafactories can tie their quality story into their maintenance operation
**Content:**
[Part 2 ](/battery-blog/automation/battery-gigafactory-anomaly-detection-ensemble-case-study/)
## This 2-part blog series was inspired by a live presentation delivered at The Battery Show North America on October 8, 2025
## Live Presentation
“Using semiconductor-proven Fault Detection to reduce downtime in ramp-up and high-volume electrode process.”
### Agnes Sowa
Battery Segment Manager
Applied Materials | Automation Products Group
## What’s Inside
- [ Early manufacturing ](#index1)
- [ Stone to steam ](#index2)
- [ Buzzwords vs. blueprints ](#index3)
- [ Focus on the goal ](#index4)
- [ Up next ](#index5)
India can skip over the decades and billions of dollars that its peers invested to develop the cutting-edge smart manufacturing technologies that are best practice today. In doing so, new semiconductor factories in India, both wafer fab and packaging, can enjoy improved time to market while optimizing yield, cost, and output. In short, India’s semiconductor industry can benefit from the collective work, investment and learnings of the rest of the world to build the smartest, most productive factories, building the highest quality products at the lowest cost. They can shift the S-curve, as we say, to produce more good die at every stage of the factory lifecycle.
In this first blog, we’ll look at the origins of manufacturing and what it means to make it “smart.”
### Background
Gigafactories are scaling rapidly, leveraging automation, Industry 4.0, and agentic AI alongside best practices from electronics and semiconductors manufacturing. One such adopted resource is fault detection. Proven in semiconductor fabs, it can be applied to high-volume battery cell manufacturing to identify defects and optimize maintenance.
### From semi to battery
Major battery cell manufacturers began in electronics manufacturing or semiconductor production and used these best practices as demand for batteries drove their ramp up needs. This cross-pollination of industries laid the foundation for our work in electric vehicle (EV) cell manufacturing, where we’ve been delivering solutions for more than five years. In fact, 39% of cells manufactured in North America are built using some form of SmartFactory software.
### Automotive’s inflection point
The automotive space is going through an inflection point. Cars are becoming more like the electronics we all know and love (or hate) in a shift visible in today’s software-defined vehicles. Today a car rolling off the assembly line with a fixed manufacturing bill of materials (MBOM) is capable of evolving its features post-sale. You can purchase a car and, two months later, subscribe for a few hundred dollars to unlock self-driving capabilities—enabled remotely by the manufacturer.
Typical new vehicles contain thousands of computer chips and millions of lines of code. The software and electronics are no longer just components, but integral to what drivers love about their cars. In essence, cars are becoming iPhones on wheels, with EV battery cells sharing many similarities with computer chips inside personal devices. Both are hybrids of chemical and physical properties that together determine performance.
The process used to manufacture battery cells also mirrors that of semiconductors: a continuous flow that transitions into batch processing and ultimately results in discrete units. Both industries demand highly controlled environments—dry rooms, clean rooms, and precise environmental controls integrated with Manufacturing Execution Systems (MES), Statistical Process Control (SPC), and process data.
### Shared challenges: precision and loss minimization
Failure in either domain—semiconductors or batteries—leaves little room for rework. There are no easy reentry loops. That’s why both industries focus intensely on minimizing losses and waste.
Fault detection and classification entails looking at the combination of physical, chemical, and visible inspection data combined with equipment sensor data to conduct classification and detection. In wafer fabs, however, this is done at a much higher scale and volume of data. A typical tech stack for a semi wafer fab, as shown in figure 1, has everything necessary to run lights out manufacturing. This includes automation of material movements, the manufacturing execution system, process quality, productivity (including scheduling), asset management, and preventive maintenance. It is the soup-to-nuts solution for a wafer fab.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/12/blog-figure-1-scaled.webp) Figure 1: Typical tech stack for a semiconductor wafer fab, with applicable battery process solutions detailed.
For the moment, we’ll just look more closely at process quality solutions within this stack, and how they can bring about savings to the giga factory via improved process quality: SPC, fault detection (FD), and predictive maintenance.
### SPC and FD: what and why
Simply put, SPC will answer your ‘what.’ Fault detection will answer ‘why,’ and predictive maintenance will tell you how and when.
Both wafer fabs and giga factories frequently employ SPC for monitoring process limits and maintaining control. This standard use of SPC typically involves advanced process controls, out of control action plans (OCAP), and analysis of process trends. Control charts serve as time series data, essentially identifying your set limits and revealing how your process is performing at present.
Fault detection is also used to answer why incidents occur. When process drift occurs, such as a sequence of points with measurement anomalies, you might look at a burr count after electrode slitting. The FD system, on the other hand, monitors equipment sensors and begins observing parameters such as roller tension which might contribute to burr formation in slitting. Additionally, it examines other critical data to help correlate and determine the underlying reasons for process failures at the conclusion of processing.
This use of FD still tends to be very reactive, initiated only when the process engineer first identifies an issue. Fault detection is a familiar and intuitive tool for process engineers. It relies on time series data and, since the process is highly continuous, unit IDs aren’t present at this stage. What they’ll typically see is a chart with the mean and the sigma, max, and range. While they’ll be able to identify outliers, further analytics such as calculating slope and combining sensor signals into composite indices allow for extra computational insights to help determine underlying causes—the why. As with SPC, however, this method remains mostly reactive as it is typically performed after a failure occurs on the process side.
### Prevention
FD is also an essential tool that enables manufacturers to begin to predict or even prevent future failures. The level of data it generates can be used in unison by process and quality and maintenance teams to extrapolate when a threshold likely to cause a failure will be crossed. Identifying time to failure (the time from now until the threshold will be reached) enables preventive maintenance to be planned first.
This is likely a process used by most battery gigafactories, albeit through manual actions. Working with customers, we found many built preventive maintenance schedules through a mix of vendor consultations, input from process engineers, and accumulated best practices—layered with whatever connected data fed into preventive maintenance—all aimed at devising the most effective predictive maintenance schedule possible for their organization.
### Predictive maintenance
To move away from these manual processes to optimize the benefits of preventive maintenance, we developed the Anomaly Detection Ensemble (ADE) solution. Through a series of machine learning algorithms, it produces an extrapolation with a confidence window that results in a much tighter window of maintenance intervals on the time axis. This enables process engineers to take more risks when rescheduling preventive maintenance—to extend the time between maintenance events. In terms of operational benefit, manufacturers can schedule maintenance further into the future and gain more equipment up time.
### Up next: how
While all these individual solutions have been around, what is innovative is how wafer fabs have done this. This can be summed up in two points: having a common software platform that is looking at that time series data from the perspective of your process engineer, and presenting that data in a way your process engineers know how to interpret. This automates the connection between why your maintenance team is taking certain actions and prioritizing those — aligning their objectives to quality objectives. In the next article, we’ll share a case study demonstrating how this type of implementation can make these practices systemic and enable significant savings in the process.
**Battery Category:** Battery Automation, Battery Manufacturing
---
### [バッテリー製造の未来：先進的な自動化ソリューションの導入](https://appliedsmartfactory.com/battery-blog/automation/embracing-advanced-automation-solutions/)
**Published:** February 21, 2025
**Author:** Agnes Sowa, Battery Manufacturing Segment Manager
**Excerpt:** 効率・品質・安全性を最大化し、コストの削減を実現
**Content:**
## 内容一覧
- [ 生産効率と生産性の向上 ](#index1)
- [ 品質と一貫性の改善 ](#index2)
- [ コスト削減 ](#index3)
- [ 柔軟性と拡張性 ](#index4)
- [ リスクの最小化と安全性の向上 ](#index5)
- [ データに基づく意思決定 ](#index6)
- [ まとめ ](#index7)
急速に変化する現代世界では、高品質なバッテリーの需要が急増しています。2025年には、世界中で8,500万台の電気自動車が走行することを支えるため、リチウムイオン電池の生産能力が2倍になると予測されています。このような成長は、かつて半導体業界でも見られたもので、アプライドにとっては馴染みのある話ですが、製造業者にとっては圧倒されることもあるでしょう。この需要に応えるため、バッテリー製造業者は先進的な自動化ソリューションを導入しています。これらの技術は、生産性と効率を高めるだけでなく、品質と歩留まりの向上にも貢献します。
### 生産効率と生産性の向上
自動化の最大の利点の一つは、生産速度の劇的な向上です。自動化システムはプロセスを効率化し、手作業の介入を減らし、連続運転を可能にします。これにより、出力が増加し、サイクルタイムが短縮されます。たとえば、工場内の資材移動を調整する高度なスケジューリング・ディスパッチシステムは、遅延やライン停止を最小限に抑えます。現在のバッテリー工場では、コンベア、AGV、ASRSなどの搬送機器や、Class 5 MCSのようなソフトウェアを活用し、必要な資材を適切なタイミングで適切な場所に届けています。
### 品質と一貫性の改善
自動化は、品質の一貫性を保つ上で重要な役割を果たします。特に新設工場では、生産と歩留まりの目標を達成するためにプロセスの微調整が必要です。プロセスのばらつきを減らし、不良を効果的に管理することで、より高い歩留まりが実現します。SPC（統計的工程管理）データは、プロセスや品質エンジニアにリアルタイムで提供され、装置のレシピを即座に調整することで、迅速なOCAP（異常時の対応計画）対応が可能になります。
### コスト削減
自動化ソリューションの導入は、大幅なコスト削減につながります。たとえば、リアルタイムのエラー検出により、より良い意思決定と的確な対応が可能になり、コスト削減が実現します。人件費の削減や資源の有効活用により、運用コストを抑えることができます。さらに、高品質を維持することで、不良品に伴うコストを回避し、収益性を高めることができます。
### 柔軟性と拡張性
自動化ソリューションは、柔軟かつ拡張可能に設計されています。新しい製造技術や材料を容易に取り入れることができ、市場の変化に迅速に対応できます。また、生産需要の変動に応じてシステムを拡張・縮小できるため、ダイナミックな市場においても柔軟に対応可能です。プロジェクト開始時にすべての答えを持っている必要はなく、運用の成長に応じてプロセスにステップやチェックを追加・変更できます。理想的には、技術ソリューションが簡単に変更できる設計であり、現場のチームが自ら改善できることが望ましいです。
### リスクの最小化と安全性の向上
製造現場において安全性は最優先事項であり、特にGW（ギガワット）級の電力を蓄えるバッテリーの製造では重要です。自動化はエラーのリスクを最小限に抑え、形成・エージング工程前のセルの詳細なインライン検査を可能にします。これにより、安全性が向上し、生産性も高まります。
### データに基づく意思決定
先進的な自動化の最も魅力的な点の一つは、データを活用した意思決定が可能になることです。生産量が倍増すれば、最適な運用に関する洞察も倍増します。リアルタイムのモニタリングと分析により、製造プロセスに関する貴重な洞察が得られ、的確な判断が可能になります。予知保全も高度な分析によって実現し、設備の故障を予測してメンテナンスを計画的に行うことで、ダウンタイムを削減し、スムーズな運用を維持できます。
### まとめ
先進的な自動化ソリューションの導入は、もはや贅沢品ではなく、バッテリー製造業者にとって必要不可欠なものです。効率性の向上、品質の改善、コスト削減、安全性の確保により、これらの技術は市場での競争力を高めます。進化し続けるバッテリー製造の世界で先を行くためには、自動化の導入が鍵となります。
**Battery Category:** バッテリー製造自動化
**Battery Tag:** Featured
---
### [統合プロセス制御でバッテリーメーカーの意思決定を改善](https://appliedsmartfactory.com/battery-blog/automation/improve-decision-making-with-unified-process-control/)
**Published:** March 17, 2025
**Author:** Agnes Sowa and Christopher Reeves
**Excerpt:** 設備とプロセスの全体像を把握し、パフォーマンスと品質の向上を実現
**Content:**
## 内容一覧
- [ 従来の手法 ](#index1)
- [ 統合プラットフォームの構築 ](#index2)
- [ イベント検出の高速化 ](#index3)
- [ まとめ ](#index4)
製造現場では、ビッグデータ、デジタルツイン、AI、機械学習といったツールの選定や導入に注力しがちです。「インダストリー4.0」といったバズワードが目標のように感じられることもありますが、実際の目標は常に、工場のパフォーマンスを向上させることにあります。バッテリー工場が生産量を拡大する中で、歩留まりに関する課題がパレート図の上位に現れることが予想されます。
歩留まり改善を促進するためのKPIには、問題の検出にかかる時間、意思決定が製品品質に与える影響（図1）、そしてそれらのイベントにかかるコストなどがあります。これらの指標を改善する容易さや拡張性は、システムの基盤的な実装方法に大きく依存します。
 Figure 1: Making quality decisions quickly requires that we trust our data
### 従来の手法
まずは、工場における設備およびプロセスの健全性評価に関する従来の手法を見てみましょう。多くの場合、イベントはドメインごとに分断されて評価されます。設備に関する問題はプロセスエンジニアの領域であり、設備エラーが発生すると、設備エンジニアがツールデータを分析して解決策を提示します。一方、SPC（統計的工程管理）エンジニアは製品を担当し、SPCイベントが発生すると計測チャートを確認して対応を決定します。
理想的には両者が連携すべきですが、実際にはそうならないことが多いのです。多くのバッテリーメーカーはグローバルに展開しており、設備エンジニアは本社に、プロセスエンジニアは現地工場にいることもあります。ドメイン、言語、タイムゾーンを超えて対応するには高いコストがかかり、それはスループット、製品品質、設備投資に影響します。
### 統合プラットフォームの構築
こうしたコストを大幅に削減するには、ドメインの統合が必要です。そのためには、統合プラットフォームの構築が不可欠です。私たちが考える「統合」とは、すべてのプロセス制御システムを基盤レベルで統合することを意味し、以下の要素が求められます： - 高度な分析やAI/ML活用に不可欠な標準化されたデータ構造
- イベントへの対応を標準化するための共通ツール
- すべてのアプリケーションで一貫性のあるユーザーインターフェース
- アプリケーション管理を効率化する統一された管理機能
- 専門知識を再利用し、投資を抑える標準化されたナレッジベース
- 工場の成長に応じて拡張可能なスケーラブルなアーキテクチャ
### イベント検出の高速化
これらのシステムを統合することで、プロセスの分断が解消され、設備とプロセスの健全性評価の方法が変わります。イベントが発生した際には、ドメインを横断したデータ分析に基づく統合的なアクションプランが実行され、問題の解決だけでなく、プロセスの最適化も同時に可能になります。
ドメインを超えた分析により、イベントの早期検出が可能となり、リアクティブ（事後対応）からプロアクティブ（予防的対応）への移行が実現します。
### まとめ
設備とプロセスの健全性を包括的に把握することで、初回から正しい判断が可能となり、システム間の接続性が向上します。これにより、エンジニアはより迅速かつ高品質な意思決定ができるようになります。統合されたシステムとチーム間での情報共有により、イベントの影響やコストを最小限に抑えることができ、品質を損なうことなく工場のパフォーマンスを迅速に向上させることが可能になります。
## 著者について
Agnes Sowa，バッテリー製造セグメントマネージャー
バッテリー製造と戦略的アライアンスを担当するセグメントマネージャーです。Applied Materials Automation Product Groupに入社する前は、Panasonic Connectでスマートファクトリーパートナーシップのマネージャーとして、生産性、自動化、MES、保守ソフトウェアの導入を担当していました。また、DePaul大学でファイナンスのMBA、イリノイ工科大学で機械工学の学士号を取得しています。
Christopher Reeves，E3グローバルプロダクトマネージャー
Applied E3自動化プラットフォームのグローバルプロダクトマネージャーです。以前はGlobalFoundriesでプロセスおよび設備制御のシニアエンジニアを務めしました。ニューヨーク州立大学プラッツバーグ校で物理学の学士号と中等教育の修士号を取得。
**Battery Category:** バッテリー製造自動化
---
### [未来を支える力：バッテリー業界におけるプロセス品質ソリューション](https://appliedsmartfactory.com/battery-blog/automation/battery-manufacturing-process-quality-solutions/)
**Published:** April 1, 2025
**Author:** Agnes Sowa and Vishali Ragam
**Excerpt:** 統計的工程管理と故障検出によって、より高い品質・信頼性・効率性を実現
**Content:**
## 内容一覧
- [ プロセス理解の深化 ](#index1)
- [ プロセス制御の向上 ](#index2)
- [ データに基づく意思決定 ](#index3)
- [ 事例 ](#index4)
- [ 予知保全 ](#index5)
- [ まとめ ](#index6)
EV（電気自動車）への急速な移行に伴い、30年以上にわたり大きな変化のなかった従来型のバッテリーメーカーは、需要に応じて新たな工場を建設し、しばしば本拠地から遠く離れた場所に巨額の投資を行っています。IoTの接続が進むこの時代では、過去と同じ方法でオペレーションを続けると、情報過多に陥る可能性があります。したがって、エビデンスに基づいてオペレーションに関する有意義な事実を抽出することが重要です。
迅速な問題解決が求められる中、リアルタイムでの知識発見が鍵となります。その一例が、長年の属人的な知識を、異なるデータソース間の因果関係や関連性を特定することで置き換えることです。本ブログでは、統計的工程管理（SPC）を、故障検出（FD）を通じた装置性能センサーデータとの関係に基づいて分析・特徴づけます。
### プロセス理解の深化
SPCデータ（例：電極工程における塗布厚みの変動）と装置センサーデータ（例：塗布ヘッドの温度、ローラー速度、振動パターン、圧力）との関係を分析することで、装置の状態がプロセス結果にどのように影響するかを深く理解できます。
この統合分析により、個別のデータストリームを単独で見ているだけでは見逃されがちな隠れた相関関係を明らかにできます。たとえば、装置の微細な振動変化がコーティング厚さの変動増加と相関している場合があります（図1参照）。FDでは通常、アラーム監視のための限界値を設定し、特定のレシピにおける標準状態を理解します。しかし、単変量分析（UVA）の範囲内の変動も、視覚測定とセンサーデータの相関戦略においては意味を持ちます。リアルタイムで診断を下す能力は自動化システムで実現可能ですが、人間が迅速に電極のリスクを特定・緩和するのは困難です。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/04/figure1-1.jpg) 図1：装置の振動と塗布厚みの逆相関関係
データの解釈に用いる限界値やアクションの設定は常に難題です。たとえば、環境の変動や装置部品の交換などの介入が変動を引き起こすことがあります。また、異なるトポロジーを持つ装置は、同じレシピでも独自の変動を加える傾向があります。重要なのは、適切な期間、イベント、監視すべきセンサーのサブセットを見極め、製品とレシピに対するプロセスの実力を理解することです。バッテリーOEMが生産を拡大する中で、これは自動化されなければ、工場のスループットや歩留まりの要求に対応できません。常にSPCデータと照合しながら自動化によって検証される必要があります。
### プロセス制御の向上
図2に示すように、SPCデータと装置センサーデータを継続的に監視することで、プロセスエンジニアや自動化システムは、装置設定やプロセスパラメータをリアルタイムで調整し、最適な性能を維持しつつ変動を最小限に抑えることができます。
さらに、製品の品質に影響を与える装置関連の問題に積極的に対処することで、不良率を大幅に削減し、全体の歩留まりを向上させることが可能です。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/04/figure2-2.jpg) 図2：装置センサーとSPCインライン測定の相関（ピアソン相関係数付き）
### データに基づく意思決定
統合されたデータにより、製造プロセスのより包括的な視点が得られ、装置保守、プロセス最適化、全体的な生産戦略に関するデータに基づいて意思決定を行うが可能になります。
### 事例
SPCデータでコーティング厚さの変動が増加していることが観察されたとします。このデータを装置センサーデータ（例：コーティングヘッド温度の徐々な低下）と組み合わせて分析することで、保守担当者は温度制御システムに潜在的な問題があると疑うことができます（図3参照）。これにより、問題が深刻化して廃棄率が上昇する前に、予防保守を計画できます。
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/04/figure3-1.jpg) 図3：このレシピチャートは、統合システムが図1または図2に示されたSPCチャートと継続的に相関させるセンサートレースデータを示しています。
### 予知保全
装置センサーデータ（温度、振動、圧力、電流など）は、大きな故障が発生する前に微細な変化を示すことがあります。経験豊富な製造業者では、これは現場で長年働いてきたチームの属人的な知識として現れます。企業が生産を拡大し、新工場を建設し、新たな従業員（しばしば海外）を雇用する中で、この属人的知識を新しい施設で再現することが課題となります。このデータをSPCデータと重ね合わせることで、装置の問題の初期兆候を特定し、本社と同等またはそれ以上の歩留まりで新工場を運営することが可能になります。
予知保全により、予防的な保守スケジューリングが可能となり、突発的なダウンタイムを最小限に抑え、装置の稼働率を最大化できます。問題が深刻化する前に対処することで、装置の寿命を延ばし、保守コストを削減できます。
### まとめ
バッテリー製造が進化を続ける中で、SPCとFDの相関分析の役割はますます重要になります。この統合アプローチを採用するメーカーは、今日のEV市場の要求に自信と柔軟性を持って対応できるでしょう。
SmartFactory Process Controlは、製造装置とプロセスの挙動を明示的に可視化し、カスタマイズされた継続的かつ自動化された調整を可能にします。これにより、バッテリーメーカーは高い品質基準を維持しながら、高速ロールと高効率を実現できます。SmartFactoryは、半導体業界で培った最先端の実践をバッテリー製造に提供し、生産歩留まりと効率の最大化を目指しています。
## 著者について
Agnes Sowa，バッテリー製造セグメントマネージャー
バッテリー製造と戦略的アライアンスを担当するセグメントマネージャーです。Applied Materials Automation Product Groupに入社する前は、Panasonic Connectでスマートファクトリーパートナーシップのマネージャーとして、生産性、自動化、MES、保守ソフトウェアの導入を担当していました。また、DePaul大学でファイナンスのMBA、イリノイ工科大学で機械工学の学士号を取得しています。
Vishali Ragam，SPCグローバルプロダクトマネージャー
半導体業界で15年以上の経験を持っています。Applied Materialsに入社する前は、Micron Technologyでプロセスエンジニアとして、そしてその後はシニア品質エンジニアとして勤務していました。彼女は7年前に品質ソリューションアーキテクトとしてAppliedに入社し、現在、グローバルプロダクトマネージャーとして、SmartFactory SPC3Dを担当しています。これは、プロセスが仕様内に収まっているかどうかを統計的に判断し、製品の歩留まりを向上させるための高度なプロセス制御（APC）エンジンです。彼女はオクラホマ州立大学で機械工学の修士号を、インド・テランガーナ州ハイデラバードにあるオスマニア大学で機械工学の学士号を取得しています。
**Battery Category:** バッテリー製造自動化
---
### [Battery manufacturers can improve decision-making with Unified Process Control](https://appliedsmartfactory.com/battery-blog/automation/improve-decision-making-with-unified-process-control/)
**Published:** March 17, 2025
**Author:** Agnes Sowa and Christopher Reeves
**Excerpt:** Gain a holistic view of equipment and process health for increased performance and quality
**Content:**
## What’s Inside
- [ Legacy practices ](#index1)
- [ Creating a unified platform ](#index2)
- [ Faster event detection ](#index3)
- [ Conclusion ](#index4)
Working in manufacturing technology, it’s easy to get caught up in learning about, choosing and implementing tools such as big data, digital twin, artificial intelligence or machine learning. Buzzwords like Industry 4.0 feel like goals to achieve. In reality, the goal is (and has always been) to enhance factory performance by addressing top contributing issues. As battery factories ramp up volume, yield-related issues are likely to hit the top of the Pareto chart. Various KPIs help drive improved yield. These include how much time it takes to detect a problem and how a decision will impact production quality (Figure 1), as well as the cost of these events. The ease of improving these metrics, as well as how far to expand them, is directly linked to the way systems are implemented at a foundational level.
[  ](https://appliedsmartfactory.com/wp-content/uploads/2025/03/Making-quality-decisions-quickly-requires-that-we-trust-our-data.jpg) Figure 1: Making quality decisions quickly requires that we trust our data
### Legacy practices
With that in mind, we need to first look at legacy practices for assessing equipment and process health in a factory. Often, events are assessed in silos based on their domains, with equipment being the domain of the process engineer. When there is an equipment error event, the equipment engineer analyzes tool data to recommend a resolution to the problem. The SPC engineer’s domain is the product. When there’s a SPC event, this person reviews metrology charts to prescribe action. Hopefully, they talk to each other, but that’s not typically the case. Many battery manufacturers are expanding, setting up factories around the globe, and equipment engineers may be based in the organization’s home country while the process engineers are in the factory. Being able to take action across domains, languages and time zones requires a high cost which is realized through throughput, impact on product quality, and capital investment.
### Creating a unified platform
Integration of these domains can drastically reduce that cost, and that requires creating a unified platform. For us, unification represents integration at a core level across all process control systems and requires:
- A standardized data structure, which is critical for advanced analysis and AI/ML applications.
- Shared tools to help standardize our action and reaction to events.
- A consistent UI which provides the same look and feel across applications.
- Universal management to streamline the administration of the applications.
- A standardized knowledge base that enables us to reuse expertise and lower the overall investment.
- Architecture designed to scale as factories grow.
### Faster event detection
Integrating these systems to de-silo the process changes how equipment and process health is assessed. It enables a new practice through which an event would trigger a combined action plan with the ability to assess data across domains. This results not only in resolution of the event, but in the ability to optimize the process at the same time. A better analysis across domains enables faster detection of events—helping you migrate from a reactive to proactive approach.
### Conclusion
A holistic view of the equipment and process health leads to better, first-time-right decisions and streamlines the connectivity of systems, enabling engineers to make high-quality decisions faster. This mix of integrated systems and shared access among team members lowers the impact of events and costs associated with them. In this way, manufacturers can improve factory performance quickly without compromising quality.
## About the Authors
Agnes Sowa, Battery Manufacturing Segment Manager
Agnes is the segment manager overseeing battery manufacturing and strategic alliances. Prior to joining Applied Materials Automation Product Group, Agnes was Manager of Smart Factory Partnerships at Panasonic Connect, overseeing manufacturing technology implementations of productivity, automation, MES and maintenance software. She holds an M.B.A. in Finance from DePaul University, and a B.S. in Mechanical Engineering from Illinois Institute of Technology in Chicago.
Christopher Reeves, Global Product Manager, E3
As the Global Product Manager for the Applied E3 automation platform, Chris is responsible for the product planning and execution throughout the product lifecycle. Prior to joining Applied Materials Automation Products Group, he was a senior engineer for process and equipment controls at GlobalFoundries. Chris earned his Bachelor of Arts in Physics and Master of Science in Secondary Education and Teaching from the State University of New York at Plattsburgh.
**Battery Category:** Battery Automation, Battery Manufacturing
---
### [The future of battery manufacturing: embracing advanced automation solutions](https://appliedsmartfactory.com/battery-blog/automation/embracing-advanced-automation-solutions/)
**Published:** February 21, 2025
**Author:** Agnes Sowa, Battery Manufacturing Segment Manager
**Excerpt:** Maximize efficiency, quality, safety, and reduce costs
**Content:**
## What’s Inside
- [ Enhanced efficiency and productivity ](#index1)
- [ Improved quality and consistency ](#index2)
- [ Cost savings ](#index3)
- [ Flexibility and scalability ](#index4)
- [ Minimized risk and greater safety ](#index5)
- [ Data-driven decision making ](#index6)
- [ Conclusion ](#index7)
In today’s fast-paced world, the demand for high-quality batteries is skyrocketing; 2025 will see a doubling of lithium-ion battery production capacity to support the 85 million electric vehicles expected to be on the world’s roads by end of the year. We have seen growth like this before, in semiconductors. While a familiar story to Applied, it can feel overwhelming at times for manufacturers. To keep up with this demand, battery manufacturers are turning to advanced automation solutions. These technologies not only leverage best practices in automation to enhance efficiency and productivity but also improve quality and yields. Let’s dive deeper into the benefits of advanced automation for battery manufacturers.
### Enhanced efficiency and productivity
One of the most significant advantages of automation is the dramatic increase in production rates. Automated systems streamline processes, reducing the need for manual intervention and allowing for continuous operation. This leads to higher output and shorter cycle times. For instance, advanced scheduling and dispatching systems that can orchestrate material movements around your factory can minimize delays and line downtime. Today’s battery factories leverage many types of material handling equipment like conveyors, AGV’s, and ASRS, and software like Class 5 MCS can integrate the handovers to deliver the right materials to the right location in time for your scheduled process to start.
### Improved quality and consistency
Automation plays a crucial role in maintaining consistent quality. This process acutely affects greenfield plants as they fine tune their process to reach production and yield targets. By reducing process variations and managing defects effectively, automated systems ensure a higher yield. SPC data informs your process and quality engineers and is used in real time to adjust recipes on equipment running production for much faster OCAP response.
### Cost savings
Implementing automation solutions can lead to substantial cost savings. For instance, real-time error detection provides systems with additional data for better decisions and more targeted responses, leading to significant cost savings. By reducing labor costs and improving resource utilization, manufacturers can lower their operational expenses. Moreover, maintaining high-quality standards helps avoid the costs associated with defective products, further enhancing profitability.
### Flexibility and scalability
Automation solutions are designed to be adaptable and scalable. They can easily incorporate new manufacturing techniques and materials, ensuring that manufacturers stay ahead of the curve. Additionally, automated systems can be scaled up or down to meet changing production demands, providing the flexibility needed in a dynamic market. You don’t need to have all the answers before you start your project; you can add steps or checks into your process and modify as your operation grows. Ideally, your technology solution allows for easy modifications which can be done by your team. They are your experts and know best where your operations can improve.
### Minimized risk and greater safety
Safety is a top priority in any manufacturing environment, especially when manufacturing batteries storing GW of power. Automation minimizes the risk of errors and allows for more detailed inline testing of the cells before the formation and aging steps. This not only improves safety but also enhances overall productivity.
### Data-driven decision making
One of the most exciting aspects of advanced automation is the ability to leverage data for decision-making. As battery manufacturers double their production volumes, they also double the insights to their best operations. Real-time monitoring and analytics provide valuable insights into production processes, enabling manufacturers to make informed decisions. Predictive maintenance, powered by advanced analytics, can predict equipment failures and schedule maintenance, reducing downtime and ensuring smooth operations.
### Conclusion
The adoption of advanced automation solutions is no longer a luxury but a necessity for battery manufacturers. By enhancing efficiency, improving quality, reducing costs, and ensuring safety, these technologies provide a competitive edge in the market. Embracing automation is the key to staying ahead in the ever-evolving landscape of battery manufacturing.
**Battery Category:** Battery Automation, Battery Manufacturing
**Battery Tag:** Featured
---
## Semiconductor Category
### [Semiconductor AI/ML technologies](https://appliedsmartfactory.com/semiconductor-blog-category/ai-ml/)
---
### [Semiconductor Manufacturing Execution](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
---
### [Semiconductor Manufacturing Execution](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
---
### [Semiconductor Smart Manufacturing](https://appliedsmartfactory.com/semiconductor-blog-category/smart-manufacturing/)
---
### [Semiconductor Productivity](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
---
### [Semiconductor Planning](https://appliedsmartfactory.com/semiconductor-blog-category/planning/)
---
### [Semiconductor Productivity](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
---
### [Semiconductor Quality](https://appliedsmartfactory.com/semiconductor-blog-category/quality/)
---
### [Semiconductor Scheduling](https://appliedsmartfactory.com/semiconductor-blog-category/scheduling/)
---
### [Semiconductor Smart Manufacturing](https://appliedsmartfactory.com/semiconductor-blog-category/smart-manufacturing/)
---
### [Semiconductor Use Cases](https://appliedsmartfactory.com/semiconductor-blog-category/use-cases/)
---
### [Semiconductor AI/ML technologies](https://appliedsmartfactory.com/semiconductor-blog-category/ai-ml/)
---
### [Smartclips](https://appliedsmartfactory.com/semiconductor-blog-category/smartclips/)
---
### [Interviews](https://appliedsmartfactory.com/semiconductor-blog-category/interviews/)
---
### [Panel](https://appliedsmartfactory.com/semiconductor-blog-category/panel/)
---
### [Interviews](https://appliedsmartfactory.com/semiconductor-blog-category/interviews/)
---
### [Smartclips](https://appliedsmartfactory.com/semiconductor-blog-category/smartclips/)
---
### [Smartclips](https://appliedsmartfactory.com/semiconductor-blog-category/smartclips/)
---
### [Interviews](https://appliedsmartfactory.com/semiconductor-blog-category/interviews/)
---
### [Panel](https://appliedsmartfactory.com/semiconductor-blog-category/panel/)
---
### [Semiconductor AI/ML technologies](https://appliedsmartfactory.com/semiconductor-blog-category/ai-ml/)
---
### [Panel](https://appliedsmartfactory.com/semiconductor-blog-category/panel/)
---
### [Semiconductor Manufacturing Execution](https://appliedsmartfactory.com/semiconductor-blog-category/manufacturing-execution/)
---
### [Semiconductor Productivity](https://appliedsmartfactory.com/semiconductor-blog-category/productivity/)
---
### [Semiconductor Quality](https://appliedsmartfactory.com/semiconductor-blog-category/quality/)
---
### [Semiconductor Planning](https://appliedsmartfactory.com/semiconductor-blog-category/planning/)
---
### [Semiconductor Scheduling](https://appliedsmartfactory.com/semiconductor-blog-category/scheduling/)
---
### [Semiconductor Smart Manufacturing](https://appliedsmartfactory.com/semiconductor-blog-category/smart-manufacturing/)
---
### [Semiconductor Quality](https://appliedsmartfactory.com/semiconductor-blog-category/quality/)
---
### [Semiconductor Planning](https://appliedsmartfactory.com/semiconductor-blog-category/planning/)
---
### [Semiconductor Scheduling](https://appliedsmartfactory.com/semiconductor-blog-category/scheduling/)
---
### [Semiconductor Use Cases](https://appliedsmartfactory.com/semiconductor-blog-category/use-cases/)
---
## Pharmaceutical Category
### [Uncategorized](https://appliedsmartfactory.com/pharmaceutical-blog-category/uncategorized/)
---
## Webinar Category
### [Semiconductor Webinars](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
---
### [Semiconductor Webinars](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
---
### [Semiconductor Webinars](https://appliedsmartfactory.com/webinar-category/semiconductor-webinar/)
---
## Event Category
### [Semiconductor](https://appliedsmartfactory.com/event-category/semiconductor-event/)
---
### [Semiconductor](https://appliedsmartfactory.com/event-category/semiconductor-event/)
---
### [Semiconductor](https://appliedsmartfactory.com/event-category/semiconductor-event/)
---
### [Battery](https://appliedsmartfactory.com/event-category/battery-event/)
---
## Battery Category
### [Battery Manufacturing](https://appliedsmartfactory.com/battery-blog-category/manufacturing/)
---
### [Battery Automation](https://appliedsmartfactory.com/battery-blog-category/automation/)
---
### [バッテリー製造自動化](https://appliedsmartfactory.com/ja/battery-blog-category/automation-ja/)
---