Modular production control using deep reinforcement learning

  • EU regulations on CO2 limits and the trend of individualization are pushing the automotive industry towards greater flexibility and robustness in production. One approach to address these challenges is modular production, where workstations are decoupled by automated guided vehicles, requiring new control concepts. Modular production control aims at throughput-optimal coordination of products, workstations, and vehicles. For this np-hard problem, conventional control approaches lack in computing efficiency, do not find optimal solutions, or are not generalizable. In contrast, Deep Reinforcement Learning offers powerful and generalizable algorithms, able to deal with varying environments and high complexity. One of these algorithms is Proximal Policy Optimization, which is used in this article to address modular production control. Experiments in several modular production control settings demonstrate stable, reliable, optimal, and generalizable learning behavior. The agent successfully adapts its strategies with respect to the givenEU regulations on CO2 limits and the trend of individualization are pushing the automotive industry towards greater flexibility and robustness in production. One approach to address these challenges is modular production, where workstations are decoupled by automated guided vehicles, requiring new control concepts. Modular production control aims at throughput-optimal coordination of products, workstations, and vehicles. For this np-hard problem, conventional control approaches lack in computing efficiency, do not find optimal solutions, or are not generalizable. In contrast, Deep Reinforcement Learning offers powerful and generalizable algorithms, able to deal with varying environments and high complexity. One of these algorithms is Proximal Policy Optimization, which is used in this article to address modular production control. Experiments in several modular production control settings demonstrate stable, reliable, optimal, and generalizable learning behavior. The agent successfully adapts its strategies with respect to the given problem configuration. We explain how to get to this learning behavior, especially focusing on the agent’s action, state, and reward design.show moreshow less

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Sebastian MayerORCiD, Tobias Classen, Christian EndischORCiD
Subtitle (English):proximal policy optimization
Language:English
Document Type:Article
Year of first Publication:2021
published in (English):Journal of Intelligent Manufacturing
Publisher:Springer Nature
Place of publication:Cham
ISSN:1572-8145
Volume:32
Issue:8
First Page:2335
Last Page:2351
Review:peer-review
Open Access:ja
Version:published
Tag:automotive industry; deep reinforcement learning; modular production; production control; production scheduling; proximal policy optimization
URN:urn:nbn:de:bvb:573-13092
Related Identifier:https://doi.org/10.1007/s10845-021-01778-z
Faculties / Institutes / Organizations:Fakultät Elektro- und Informationstechnik
Institut für Innovative Mobilität (IIMo)
Licence (German):License Logo Creative Commons BY 4.0
Release Date:2022/02/18