定制家具板件自动分拣系统的动态分拣调度优化问题研究  

Dynamic Sorting and Scheduling Optimization of Automatic Sorting Systems for Customized Furniture Panels

作　　者：关依翔 彭乘风 黎展滔[1] 陈庆新[1] GUAN Yixiang;PENG Chengfeng;LI Zhantao;CHEN Qingxin(Key Laboratory of Computer Integrated Manufacturing System of Guangdong Province,Guangdong University of Technology,Guangzhou 510006,China;School of Physics and Electronic Electrical Engineering,Xiangnan University,Chenzhou 423000,China)

机构地区：[1]广东工业大学广东省计算机集成制造系统重点实验室,广东广州510006 [2]湘南学院物理与电子电气工程学院,湖南郴州423000

出　　处：《工业工程》2024年第6期136-144,共9页Industrial Engineering Journal

基　　金：国家自然科学基金资助项目(51975129,6197020346);广东省自然科学基金资助项目(2022A1515011165,2022A1515011175);湖南省自然科学基金资助项目(2020JJ4565);郴州市科技发展计划项目(ZDYF2020161);湖南省校级科研项目(2020XJ05)。

摘　　要：以定制家具板件自动分拣系统为背景,针对受生产环节随机性影响导致板件到库时间不确定的动态分拣调度优化问题开展研究。首先,基于问题特征分析构建混合整数规划模型;其次,针对动态调度问题难以直接通过求解器快速求解和单一启发式算法难以适应动态环境的情况,通过设计动作集合、状态空间和奖赏函数,提出一种基于Q学习的自适应分拣调度算法;最后,通过设计相应的测试算例进行对比实验,发现本文所提算法在订单交付效率与缓冲区堵塞率的优化中均取得优良表现,为分拣调度人员制定分拣计划时提供决策支持。This paper focuses on the dynamic sorting and scheduling optimization problem in automated sorting systems for customized furniture panels,which is affected by the randomness of production links and leads to the uncertainty of panel arrival time.First,a mixed integer programming model is formulated based on the analysis of problem characteristics.Second,due to the difficulty in quickly solving the dynamic scheduling problem with solvers and the challenge of single heuristic algorithms adapting to dynamic environments,an adaptive sorting and scheduling algorithm based on Q-learning is presented by designing an action set,state space and a reward function.Finally,comparison experiments are conducted with designed test cases.It shows that the algorithm proposed in this paper achieves good performance in the optimization of order delivery efficiency and buffer congestion rate,providing decision support for sorting and scheduling personnel in planning sorting strategies.

关 键 词：板式定制家具 自动分拣系统 分拣调度优化 Q学习 

分 类 号：F406[经济管理—产业经济]