Digitalisation is driving increased demand for microchips and shortening the product lifecycle, and the high variety of customer specific devices leads to a growing need for high-mix low-volume (HMLV) semiconductor production.
In this setting, the Autonomous Integrated Scheduling for Semiconductor Industr (AISSI) initiative, supported by the EUREKA Cluster AI Call 2020, researches and develops, integrates and applies novel AI-based approaches for production scheduling and other operations management purposes in Semiconductor Manufacturing. By applying reinforcement learning and knowledge graphs in a continual improvement framework for autonomous, integrated production and maintenance scheduling, competition can be outperformed in terms of efficiency, cost effectiveness and quality.
This cross-continental collaboration project is led by Robert Bosch GmbH on the Europe side and D-SIMLAB Technologies Pte Ltd on the Singapore, with Nexperia Germany GmbH, Systema GmbH and Karlsruhe Institute of Technology being additional partners. It is supported by the German Federal Ministry for Economic Affairs and Energy (BMWi) and Enterprise Singapore.
D-SIMLAB plays a critical role in this initiative through two major contributions:
- Development of Self-Learning and Self-Adapting Production and Maintenance Scheduling and Dispatching (SLSAS) techniques, driven by the underlying question what would be the best dispatching or scheduling mechanisms under changing situations in a wafer fabrication facility.
- Simulation-enabled Digital Twins representing wafer fab production lines to generate training data sets for the learning algorithms of the scheduling procedures to be developed.
The project builds upon D-SIMLAB’s expertise and long track record in wafer fab material flow planning and capacity optimisation and will add a new dimension to D-SIMLAB’s capability to enable ‘intelligent’, Industry 4.0 compliant manufacturing environments.
The Project Kick-off Meeting was held on 24 August 2021, and the project duration will be until 30 June 2024.
For further enquiries please contact:
Gan Boon Ping, CEO, boonping@d-simlab.com