A Customizable Simulator for Artificial Intelligence Research to Schedule Semiconductor Fabs

Kovács, Benjamin; Tassel, Pierre; Ali, Ramsha; El-Kholany, Mohammed M. S.; Gebser, Martin; Seidel, Georg

doi:10.1109/asmc54647.2022.9792520

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Empirical Evaluation. We evaluate our method on a largescale, continuous, stochastic and dynamic semiconductor simulation model from the literature (Hassoun et al 2019), using an open source event-based semiconductor fabrication plant simulation (Kovacs et al 2022). This testbed was designed to help researchers to assess the performance of integrated dispatching strategies and aims to credibly reflect the complexity of modern semiconductor manufacturing.…”

Section: Introductionmentioning

confidence: 99%

Semiconductor Fab Scheduling with Self-Supervised and Reinforcement Learning

Tassel¹,

Kovács²,

Gebser³

et al. 2023

Preprint

View full text Add to dashboard Cite

Semiconductor manufacturing is a notoriously complex and costly multi-step process involving a long sequence of operations on expensive and quantity-limited equipment. Recent chip shortages and their impacts have highlighted the importance of semiconductors in the global supply chains and how reliant on those our daily lives are. Due to the investment cost, environmental impact, and time scale needed to build new factories, it is difficult to ramp up production when demand spikes. This work introduces a method to successfully learn to schedule a semiconductor manufacturing facility more efficiently using deep reinforcement and self-supervised learning. We propose the first adaptive scheduling approach to handle complex, continuous, stochastic, dynamic, modern semiconductor manufacturing models. Our method outperforms the traditional hierarchical dispatching strategies typically used in semiconductor manufacturing plants, substantially reducing each order's tardiness and time until completion. As a result, our method yields a better allocation of resources in the semiconductor manufacturing process.

show abstract

Section: Introductionmentioning

confidence: 99%