On Scheduling a Photolithograhy Toolset Based on a Deep Reinforcement Learning Approach with Action Filter

Taehyung Kim, Hyeongook Kim, Tae Eog Lee, James Robert Morrison, Eungjin Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Production scheduling of semiconductor manufacturing tools is a challenging problem due to the complexity of the equipment and systems in modern wafer fabs. In our study, we focus on the photolithography toolset and consider it as a non-identical parallel machine scheduling problem with random lot arrivals and auxiliary resource constraints. The proposed methodology strives to learn a near optimal scheduling policy by incorporating WIP, masks, and the tardiness of jobs. An Action Filter (AF) is proposed as a methodology to eliminate illogical actions and speed the learning process of agents. The proposed model was evaluated in a simulation environment inspired by practical photolithography scheduling problems across various settings with reticle and qualification constraints. Our experiments demonstrated improved performance compared to typical rule-based strategies. Relative to our learning methods, weighted shortest processing time (WSPT) and apparent tardiness cost with setups (ATCS) rules perform 28% and 32% worse for weighted tardiness, respectively.

Original languageEnglish
Title of host publication2021 Winter Simulation Conference, WSC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665433112
DOIs
StatePublished - 2021
Event2021 Winter Simulation Conference, WSC 2021 - Phoenix, United States
Duration: Dec 12 2021Dec 15 2021

Publication series

NameProceedings - Winter Simulation Conference
Volume2021-December
ISSN (Print)0891-7736

Conference

Conference2021 Winter Simulation Conference, WSC 2021
Country/TerritoryUnited States
CityPhoenix
Period12/12/2112/15/21

Fingerprint

Dive into the research topics of 'On Scheduling a Photolithograhy Toolset Based on a Deep Reinforcement Learning Approach with Action Filter'. Together they form a unique fingerprint.

Cite this