ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Dynamic scheduling for flexible job shop using a deep reinforcement learning approach

Gui, Yong; Tang, Dunbing*; Zhu, Haihua; Zhang, Yi; Zhang, Zequn南京航空航天大学
COMPUTERS & INDUSTRIAL ENGINEERING2023-6DOI: 10.1016/j.cie.2023.109255
46被引11阅读
引用收藏
分享

摘要

Due to the influence of dynamic changes in the manufacturing environment, a single dispatching rule (SDR) cannot consistently attain better results than other rules for dynamic scheduling problems. Dynamic selection of the most appropriate rule from several SDRs based on the Deep Q-Network (DQN) offers better scheduling performance than using an individual SDR. However, the discreteness of action space caused by the DQN and the simplicity of the action as an SDR limit the selection range and restrict performance improvement. Thus, in this paper, we propose a scheduling method based on deep reinforcement learning for the dynamic flexible job-shop scheduling problem (DFJSP), aiming to minimize the mean tardiness. Firstly, a Markov decision process with composite scheduling action is provided to elaborate the flexible job-shop dynamic scheduling process and transform the DFJSP into an RL task. Subsequently, a composite scheduling action aggregated by SDRs and continuous weight variables is designed to provide a continuous rule space and SDR weight selection. Moreover, a reward function related to mean tardiness performance criteria is designed such that maximizing the cumulative reward is equivalent to minimizing the mean tardiness. Finally, a policy network with states as inputs and weights as outputs is constructed to generate the scheduling decision at each decision point. Also, the deep deterministic policy gradient (DDPG) algorithm is used to train the policy network to select the most appropriate weights at each decision point, thereby aggregating the SDRs into a better rule. Results from numerical experiments reveal that the proposed scheduling method achieves significantly better scheduling results than an SDR and the DQN-based method in dynamically changeable manufacturing environments.

学科与关键词

关键词
Dynamic flexible job -shop scheduling problemSingle dispatching ruleMarkov decision processDeep reinforcement learningDeep deterministic policy gradient
相关
加载中…
  • Dynamic Jobshop Scheduling Algorithm Based on Deep Q Network
    Zhao, Yejian; Wang, Yanhong*; Tan, Yuanyuan; Zhang, Jun; Yu, HongxiaIEEE Access, 2021, 9: 122995-123011.被引 36
  • Deep reinforcement learning for dynamic distributed job shop scheduling problem with transfers
    Lei, Yong; Deng, Qianwang*; Liao, Mengqi; Gao, ShuochengEXPERT SYSTEMS WITH APPLICATIONS, 2024, 251: 123970.被引 4
  • Deep reinforcement learning for dynamic flexible job shop scheduling problem considering variable processing times
    Zhang, Lu; Feng, Yi; Xiao, Qinge; Xu, Yunlang; Li, Di; Yang, Dongsheng; Yang, Zhile*JOURNAL OF MANUFACTURING SYSTEMS, 2023, 71: 257-273.被引 1
查看全部 →

发表信息

论文状态
公开发表
期刊
COMPUTERS & INDUSTRIAL ENGINEERING
发表日期
2023-06
卷期
第 180 卷
页码
109255
DOI
10.1016/j.cie.2023.109255
语言
MULTI-LANGUAGE
成果收录
SCIE
资助标注
National Natural Science Foundation of China [52075257]; Key Research and Development Program of Jiangsu Province [BE2021091]; National Key Research and Development Program of China [2020YFB1710500]

作者

  • G

    Gui, Yong (第一作者)

    nanjing univ aeronaut & astronaut

  • T

    Tang, Dunbing (通讯)

    nanjing univ aeronaut & astronaut

查看全部 5 位作者收起作者
  • Z

    Zhu, Haihua

    nanjing univ aeronaut & astronaut

  • Z

    Zhang, Yi

    nanjing univ aeronaut & astronaut

  • Z

    Zhang, Zequn

    nanjing univ aeronaut & astronaut

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417