吉林大学学报(工学版)2024,Vol.54Issue(7) :2086-2092.DOI:10.13229/j.cnki.jdxbgxb.20230129

连续生产流水线深度强化学习优化调度算法

Deep reinforcement learning optimization scheduling algorithm for continuous production line

朱广贺 朱智强 袁逸萍
吉林大学学报(工学版)2024,Vol.54Issue(7) :2086-2092.DOI:10.13229/j.cnki.jdxbgxb.20230129

连续生产流水线深度强化学习优化调度算法

Deep reinforcement learning optimization scheduling algorithm for continuous production line

朱广贺 1朱智强 2袁逸萍3
扫码查看

作者信息

  • 1. 新疆师范大学 计算机科学技术学院,乌鲁木齐 830000
  • 2. 新疆大学 软件工程学院,乌鲁木齐 830000
  • 3. 新疆大学 机械工程学院,乌鲁木齐 830000
  • 折叠

摘要

为了提高连续生产流水线的调度效果,提升生产线的加工效率,提出连续生产流水线深度强化学习优化调度算法.首先,结合蒙特卡罗算法和贝叶斯评估方法降低连续生产线流水线问题的数据复杂度;其次,采用深度神经网络模型优化流水线调度参数,对其进行评估及编码;最后,将迭代贪婪算法与深度强化学习方法结合,对调度数据问题实施模型求解,实现连续生产流水线调度.试验结果表明:本文算法的调度结果最优,综合评价结果均高于0.9531,工序延时优化至5 min以下,收敛速度较快,提升了生产线的加工效率.

Abstract

In order to improve the scheduling effect of the continuous production line and improve the processing efficiency of the production line,a deep reinforcement learning optimization scheduling algorithm for the continuous production line is proposed.Combining Monte Carlo algorithm and Bayesian evaluation method to reduce the data complexity of the continuous production line problem;A deep neural network model is used to optimize the pipeline scheduling parameters,evaluate and code them;The iterative greedy algorithm is combined with the deep reinforcement learning method to solve the scheduling data problem and realize the continuous production line scheduling.The experimental results show that the optimal comprehensive evaluation results of the scheduling results of the proposed algorithm are higher than 0.9531,and the process delay is optimized to less than 5 min,which improves the processing efficiency of the production line.

关键词

深度强化学习/流水线生产/调度优化/迭代贪婪算法/数据降维

Key words

deep reinforcement learning/assembly line production/scheduling optimization/iterative greedy algorithm/data dimension reduction

引用本文复制引用

基金项目

国家自然科学基金项目(71961029)

出版年

2024
吉林大学学报(工学版)
吉林大学

吉林大学学报(工学版)

CSTPCD北大核心
影响因子:0.792
ISSN:1671-5497
参考文献量18
段落导航相关论文