Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/100392
Title: Reinforcement learning based predictive maintenance for a machine with multiple deteriorating yield levels
Authors: Wang, Xiao
Wang, Hongwei
Qi, Chao
Sivakumar, Appa Iyer
Keywords: DRNTU::Engineering::Mechanical engineering::Control engineering
Issue Date: 2014
Source: Wang, X., Wang, H., Qi, C., & Sivakumar, A. I. (2014). Reinforcement learning based predictive maintenance for a machine with multiple deteriorating yield levels. Journal of computational information systems, 10(1), 9-19.
Series/Report no.: Journal of computational information systems
Abstract: This paper proposes a predictive maintenance methodology for a machine in manufacturing with deterior- ating quality states represented by multiple deteriorating yield levels. Imperfect minor maintenance and perfect major repair are considered. The underlying yield level cannot be directly obtained. Instead, product quality inspection information is used as the observed system state. The optimal maintenance policy associated with each possible observed system state is learnt by modeling the problem as hidden semi-Markov decision processes and solving it using policy iteration based Q-P learning. Then the future maintenance time can be estimated by re-simulating the system model using the learned maintenance policy. A set of experimental studies is conducted to testify the effectiveness of the proposed methodology and to investigate the impacts of involved system parameters.
URI: https://hdl.handle.net/10356/100392
http://hdl.handle.net/10220/25689
Rights: © 2014 Binary Information Press Limited. This paper was published in Journal of Computational Information Systems and is made available as an electronic reprint (preprint) with permission of Binary Information Press Limited. The paper can be found at the following URL: [http://www.jofcis.com/publishedpapers/2014_10_1_9_19.pdf]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:MAE Journal Articles

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.