Scheduling algorithm for multi-disturbance job-shop based on cellular automata and reinforcement learning

被引：0
作者：
Chen Y. [1 ]
Wang H. [1 ]
Yi W. [1 ]
Pei Z. [1 ]
Wang C. [1 ]
Wu G. [1 ]
机构：
[1] Department of Industrial Engineering, Zhejiang University of Technology, Hangzhou
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：
Cellular automata; Flexible scheduling; Multi-disturbance job-shop; Reinforcement learning;
D O I：
10.13196/j.cims.2021.12.015
中图分类号：
学科分类号：
摘要：
To solve the problem of large equipment manufacturing enterprises with many disturbances and great influence, a multi-disturbance job-shop production scheduling model was built based on the cellular automata, and the objective function based on the average utilization rate of equipment and the average flow time of workpiece was designed. The model was proved to be scientific by introducing an example.In view of the complexity of multi-disturbance job-shop scheduling, the reinforcement learning algorithm was used to optimize the cellular automata evolution rules to find the global optimal scheduling solution, which contributed to design scheduling strategy for three typical disturbances of equipment failure, emergency insert sheet and new orders interference.A multi-disturbance flexible job-shop scheduling model was established based on cellular automata and reinforcement learning algorithm. A large part manufacturing enterprise was taken as an example to illustrate the specific optimization process of the model, and the effectiveness and reliability of the algorithm and model were verified by simulation. © 2021, Editorial Department of CIMS. All right reserved.
引用
收藏
页码：3536 / 3549
页数：13
相关论文
共 18 条
  • [1] LIU Yanjun, FENG Yu, WU Qianhui, Et al., Distributed real-time data warehouse building technology for condition analysis in equipment industry, Computer Integrated Manufacturing Systems, 23, 10, pp. 2324-2333, (2017)
  • [2] ZHU Chuanjun, QIU Wen, ZHANG Chaoyong, Et al., Multi-objective flexible job shop dynamic scheduling strategy aiming at scheduling stability and robustness, China Mechanical Engineering, 28, 2, pp. 173-182, (2017)
  • [3] TANG Hongtao, FEI Yonghui, CHEN Qingfeng, Et al., Flexible job shop dynamic scheduling based on industrial big data, Computer Integrated Manufacturing Systems, 26, 9, pp. 2497-2510, (2020)
  • [4] TANG Qiuhua, HE Ming, HE Xiaoxia, Et al., Robust optimization scheduling of flexible job shops under stochastic processing times, Computer Integrated Manufacturing Systems, 21, 4, pp. 1002-1012, (2015)
  • [5] LI Congbo, KOU Yang, LEI Yanfei, Et al., Flexible job shop rescheduling optimization method for energy-saving based on dynamic events, Computer Integrated Manufacturing Systems, 26, 2, pp. 288-299, (2020)
  • [6] CHEN Yong, WU Yunxiang, WANG Yaliang, Et al., Multi-assembly line robust scheduling of double resource constrains under uncertain orders, China Mechanical Engineering, 25, 12, pp. 1567-1573, (2014)
  • [7] PAN F S, YE C M, YANG J., Flexible job-shop scheduling problem under uncertainty based on QPSO algorithm, Advanced Materials Research, 605-607, pp. 487-492, (2013)
  • [8] HUANG Zhifeng, The study of reinforcement learning based elevator group scheduling technology, (2016)
  • [9] JDRZEJOWICZ P, RATAJCZAK-ROPEL E., Reinforcement learning strategies for A-team solving the resource-constrained project scheduling problem, Neurocomputing, 146, pp. 301-307, (2014)
  • [10] WANG Haoxiang, YAN Hongsen, WANG Zheng, Adaptive assembly scheduling of aero-engine based on double-layer Q-learning in knowledgeable manufacturing, Computer Integrated Manufacturing Systems, 20, 12, pp. 3000-3010, (2014)
12