In this paper, a manufacturing work cell with a gantry that is in charge of moving materials/parts between machines and buffers is considered. With the effect of the gantry movement, the system performance becomes quite different from traditional serial production lines. In this paper, reinforcement learning is used to develop a gantry scheduling policy in order to improve system production. The gantry learns to take proper actions under different situations to reduce system production loss by using Q-Learning algorithm and finds the optimal moving policy. A two-machine one-buffer work cell with a gantry is used for case study, by which reinforcement learning is applied. Compare with the FCFS policy, the fidelity and effectiveness of the reinforcement learning method are also demonstrated.
Skip Nav Destination
ASME 2017 12th International Manufacturing Science and Engineering Conference collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing
June 4–8, 2017
Los Angeles, California, USA
Conference Sponsors:
- Manufacturing Engineering Division
ISBN:
978-0-7918-5075-6
PROCEEDINGS PAPER
Gantry Scheduling for Two-Machine One-Buffer Composite Work Cell by Reinforcement Learning Available to Purchase
Xinyan Ou,
Xinyan Ou
Stony Brook University, Stony Brook, NY
Search for other works by this author on:
Qing Chang
Qing Chang
Stony Brook University, Stony Brook, NY
Search for other works by this author on:
Jorge Arinez
General Motors R&D, Warren, MI
Xinyan Ou
Stony Brook University, Stony Brook, NY
Qing Chang
Stony Brook University, Stony Brook, NY
Paper No:
MSEC2017-2854, V004T05A025; 7 pages
Published Online:
July 24, 2017
Citation
Arinez, J, Ou, X, & Chang, Q. "Gantry Scheduling for Two-Machine One-Buffer Composite Work Cell by Reinforcement Learning." Proceedings of the ASME 2017 12th International Manufacturing Science and Engineering Conference collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing. Volume 4: Bio and Sustainable Manufacturing. Los Angeles, California, USA. June 4–8, 2017. V004T05A025. ASME. https://doi.org/10.1115/MSEC2017-2854
Download citation file:
25
Views
Related Proceedings Papers
Related Articles
Opportunity Window for Energy Saving and Maintenance in Stochastic Production Systems
J. Manuf. Sci. Eng (December,2016)
Modeling and Analysis of Operator Effects on Process Quality and Throughput in Mixed Model Assembly Systems
J. Manuf. Sci. Eng (April,2011)
Three-Dimensional Paddle Shift Modeling for IC Packaging
J. Electron. Packag (September,2005)
Related Chapters
A New Concept for Concurrent Multipath Transfer in Wireless Network Connectivity
International Conference on Computer and Electrical Engineering 4th (ICCEE 2011)
Introduction and Definitions
Handbook on Stiffness & Damping in Mechanical Design
Physical Activation of Saudi Arabia Date Palm Tree's Foliar, Frond and Thorn
Proceedings of the 2010 International Conference on Mechanical, Industrial, and Manufacturing Technologies (MIMT 2010)