Predictive maintenance decision-making for serial production lines based on deep reinforcement learning

被引：0
|
作者：
Cui P. [1 ,2 ]
Wang J. [1 ,2 ]
Zhang W. [1 ,2 ]
Li Y. [1 ,2 ]
机构：
[1] Performance Analysis Center of Production and Operations Systems, Northwestern Polytechnical University, Xi'an
[2] Department of Industrial Engineering, School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an
来源：
Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2021年 / 27卷 / 12期
基金：
中国国家自然科学基金;
关键词：
Deep reinforcement learning; Digital twin workshop; Predictive maintenance decision-making; Serial production line;
D O I：
10.13196/j.cims.2021.12.004
中图分类号：
学科分类号：
摘要：
Predictive maintenance is designed to perform maintenance activities based on the condition of equipment, which can improve the business bottom line by reducing maintenance cost and improving production performance. The modeling, analysis and decision-making of serial production lines with machine degradation process were studied. A Markov chain model was developed by analyzing the dynamics of a serial production line with machine failures and predictive maintenance, and the analytical formulas of transient performance measures were derived. A predictive maintenance decision model was established as a Markov decision process to minimize the work-in-process, backlog and maintenance costs. A deep reinforcement learning method was utilized to explore optimum maintenance policies, which was obtained through the training of neural network with dataset generated from Markov chain model. Case study was performed to validate the effectiveness of the proposed decision model. The results indicated that the maintenance and production related costs were significantly reduced. © 2021, Editorial Department of CIMS. All right reserved.
引用
收藏
页码：3416 / 3428
页数：12
相关论文
共 27 条
  • [1] TAO Fei, ZHANG Meng, CHENG Jiangfeng, Et al., Digital twin workshop-A new paradigm for future workshop, Computer Integrated Manufacturing Systems, 23, 1, pp. 1-9, (2017)
  • [2] TAO Fei, LIU Weiran, LIU Jianhua, Et al., Digital twin and its potential application exploration, Computer Integrated Manufacturing Systems, 24, 1, pp. 1-18, (2018)
  • [3] HORENBEEK A V, PINTELON L., A dynamic predictive maintenance policy for complex multi-component systems, Reliability Engineering & System Safety, 120, pp. 39-50, (2013)
  • [4] JARDINE A K S, LIN D M, BANJEVIC D., A review on machinery diagnostics and prognostics implementing condition-based maintenance[J], Mechanical Systems and Signal Processing, 20, 7, pp. 1483-1510, (2006)
  • [5] WANG J Q, YAN F Y, CUI P H, Et al., Bernoulli serial lines with batching machines: Performance analysis and system-theoretic properties, IISE Transactions, 51, 7, pp. 729-743, (2019)
  • [6] LI Y, CAHNG Q, BRUNDAGE M P, Et al., Market demand oriented data-driven modeling for dynamic manufacturing system control[J], IEEE Transactions on Systems, Man, and Cybernetics: Systems, 45, 1, pp. 109-121, (2014)
  • [7] LI Y, CAHNG Q, BILLER S, Et al., Event-based modeling of distributed sensor networks in battery manufacturing[J], International Journal of Production Research, 52, 14, pp. 4239-4252, (2014)
  • [8] GERSHWIN S B., Manufacturing systems engineering, (1993)
  • [9] LI J S, MEERKOV S M., Production systems engineering, (2008)
  • [10] ALTIOK T, STIDHAM J S., The allocation of interstage buffer capacities in production lines, AIIE Transactions, 15, 4, pp. 292-299, (1983)
123