| 注册
首页|期刊导航|河北科技大学学报|基于分层多智能体的轨道车辆装配协同调度优化研究

基于分层多智能体的轨道车辆装配协同调度优化研究

马治林 郭鹏 王祺欣 张志瑶 廖秋涵 朱东 马永敬 孙轶杰

河北科技大学学报2026,Vol.47Issue(2):145-157,13.
河北科技大学学报2026,Vol.47Issue(2):145-157,13.DOI:10.7535/hbkd.2026yx02004

基于分层多智能体的轨道车辆装配协同调度优化研究

Research on hierarchical multi-agent-based collaborative scheduling optimization for rail vehicle assembly

马治林 1郭鹏 2王祺欣 1张志瑶 2廖秋涵 3朱东 3马永敬 4孙轶杰4

作者信息

  • 1. 西南交通大学机械工程学院,四川 成都 610031
  • 2. 西南交通大学机械工程学院,四川 成都 610031||轨道交通运维技术与装备四川省重点实验室,四川 成都 610031
  • 3. 成都川哈工机器人及智能装备产业技术研究院有限公司,四川 成都 610041
  • 4. 中车青岛四方机车车辆股份有限公司,山东 青岛 266111
  • 折叠

摘要

Abstract

To deal with the scheduling problem in rail vehicle assembly,where assembly line task allocation is complex and car body components require frequent cross-station transfers relying on trolleys,this study proposed an end-to-end hierarchical multi-agent deep reinforcement learning framework for scheduling optimization.Firstly,the allocation of assembly tasks across multiple assembly lines was modeled as a sequential decision problem.The high-level agent encoded the assembly task and line features using a Transformer and generated line assignment strategies with a Pointer Network.Secondly,the lower-level agents coordinated the selection of operations,station assignments,and dolly scheduling,and used Graph Attention Networks to extract relational features from heterogeneous nodes.Finally,multiple comparison experiments were conducted to validate the effectiveness of the proposed method.The results show that the method achieves optimal scheduling across different instance scales.The coordination of low-level agent strategies achieves an average maximum makespan gap of 11.36%,which outperforms the 15.00%achieved by the graph isomorphism network method,and the method provides high-quality scheduling with computation efficiency significantly higher than the Late Acceptance Hill Climbing algorithm.The proposed hierarchical collaborative scheduling framework achieves unified modeling and coordinated optimization of assembly task assignment and multi-resource scheduling,providing an efficient and adaptable intelligent optimization approach for rail vehicle assembly sched-uling.

关键词

计算机辅助制造/轨道车辆装配/深度强化学习/多智能体/分层协同调度

Key words

computer aided manufacturing/rail vehicle assembly/deep reinforcement learning/multi-agent/hierarchical collaborative scheduling

分类

信息技术与安全科学

引用本文复制引用

马治林,郭鹏,王祺欣,张志瑶,廖秋涵,朱东,马永敬,孙轶杰..基于分层多智能体的轨道车辆装配协同调度优化研究[J].河北科技大学学报,2026,47(2):145-157,13.

基金项目

国家自然科学基金(52405220) (52405220)

四川省自然科学基金(2024ZHCG0028) (2024ZHCG0028)

河北科技大学学报

1008-1542

访问量0
|
下载量0
段落导航相关论文