Optimization of global production scheduling with deep reinforcement learning
- Industrie 4.0 introduces decentralized, self-organizing and self-learning systems for production control. At the same time, new machine learning algorithms are getting increasingly powerful and solve real world problems. We apply Google DeepMind’s Deep Q Network (DQN) agent algorithm for Reinforcement Learning (RL) to production scheduling to achieve the Industrie 4.0 vision for production control. In an RL environment cooperative DQN agents, which utilize deep neural networks, are trained with user-defined objectives to optimize scheduling. We validate our system with a small factory simulation, which is modeling an abstracted frontend-of-line semiconductor production facility.
Author: | Bernd Waschneck, André Reichstaller, Lenz BelznerORCiD, Thomas Altenmüller, Thomas Bauernhansl, Alexander Knapp, Andreas Kyek |
---|---|
Language: | English |
Document Type: | Article |
Conference: | 51st CIRP Conference on Manufacturing Systems, Stockholm (Sweden), 16.-18.05.2018 |
Year of first Publication: | 2018 |
published in (English): | Procedia CIRP |
Publisher: | Elsevier |
Place of publication: | Amsterdam |
ISSN: | 2212-8271 |
Volume: | 2018 |
Issue: | 72 |
First Page: | 1264 |
Last Page: | 1269 |
Review: | peer-review |
Open Access: | ja |
Version: | published |
Tag: | Machine Learning in Manufacturing; Production Scheduling; Reinforcement Learning |
URN: | urn:nbn:de:bvb:573-15735 |
Related Identifier: | https://doi.org/10.1016/j.procir.2018.03.212 |
Release Date: | 2022/04/13 |