Deep Reinforcement Learning for Scheduling in a PCB Matrix Production System

Schwenzow T, Schneider J, Schaefer JM, Liebrecht C, Franke J, Reitelshöfer S (2025)


Publication Type: Conference contribution

Publication year: 2025

Publisher: Springer Science and Business Media Deutschland GmbH

Book Volume: 1426 LNNS

Pages Range: 75-87

Conference Proceedings Title: Lecture Notes in Networks and Systems

Event location: London, GBR

ISBN: 9783031926105

DOI: 10.1007/978-3-031-92611-2_6

Abstract

Matrix production in printed circuit board (PCB) manufacturing presents significant challenges for production planning due to sequence-dependent setup times required between jobs of different setup groups. This study investigates the application of Deep Reinforcement Learning (DRL) for job scheduling, where the agent’s actions represent the selection of jobs. Eight potential modifications are analysed within a Python-based abstraction of the production system. The preliminary results are then applied to integrate the agent into a digital shadow of the matrix production and the performance is compared to standard priority rules. The results demonstrate the overall effectiveness of the approach, with high potential for further improvement.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Schwenzow, T., Schneider, J., Schaefer, J.M., Liebrecht, C., Franke, J., & Reitelshöfer, S. (2025). Deep Reinforcement Learning for Scheduling in a PCB Matrix Production System. In Kohei Arai (Eds.), Lecture Notes in Networks and Systems (pp. 75-87). London, GBR: Springer Science and Business Media Deutschland GmbH.

MLA:

Schwenzow, Tilmann, et al. "Deep Reinforcement Learning for Scheduling in a PCB Matrix Production System." Proceedings of the Computing Conference, CompCom 2025, London, GBR Ed. Kohei Arai, Springer Science and Business Media Deutschland GmbH, 2025. 75-87.

BibTeX: Download