A flexible manufacturing assembly system with deep reinforcement learning

Traditional assembly line requires a significant amount of designs from engineers, especially in the case of multi-species and small-lot production. Recently, intelligent algorithms based on reinforcement learning are proposed to address this issue. However, the lower success rate and safety reasons...

Full description

Saved in:
Bibliographic Details
Published inControl engineering practice Vol. 118; p. 104957
Main Authors Li, Junzheng, Pang, Dong, Zheng, Yu, Guan, Xinping, Le, Xinyi
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.01.2022
Subjects
Assembly line
Digital twin
Flexible manufacture
Reinforcement learning
Assembly line
Digital twin
Flexible manufacture
Reinforcement learning
Online AccessGet full text
ISSN0967-0661
1873-6939
DOI10.1016/j.conengprac.2021.104957

Cover

More Information
Summary:Traditional assembly line requires a significant amount of designs from engineers, especially in the case of multi-species and small-lot production. Recently, intelligent algorithms based on reinforcement learning are proposed to address this issue. However, the lower success rate and safety reasons limit their industrial applications. In this article, we proposed a systematic solution, including the automatic planning of assembly motions and the monitoring system of the production lines. In the planning stage, we built the digital twin model of the assembly line, then trained a deep reinforcement learning agent to assembly the workpieces. In the production stage, the digital twin model is used to monitor the assembly lines and predict failures. To validate the system we proposed, we conducted a peg-in-hole assembly experiment, and reached a 90% success rate for a single assembly attempt. During the whole experiment, no collision happens in the real world.
ISSN:0967-0661
1873-6939
DOI:10.1016/j.conengprac.2021.104957