基于改进量子粒子群算法的柔性车间调度与预测性维护协同优化管控方法  

Improved quantum particle swarm-based collaborative optimisation and control method for flexible job shop scheduling and predictive maintenance

作　　者：马亚杰[1] 管理 姜斌[1] 陈丽君[2] 黄斌达 黄玉莹 MA YaJie;GUAN Li;JIANG Bin;CHEN LiJun;HUANG BinDa;HUANG YuYing(School of Automation,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China;Aviation Industry Jincheng Nanjing Electromechanical Hydraulic Engineering Research Center,Nanjing 211106,China)

机构地区：[1]南京航空航天大学自动化学院,南京211106 [2]航空工业金城南京机电液压工程研究中心,南京211106

出　　处：《中国科学:技术科学》2025年第2期295-308,共14页Scientia Sinica(Technologica)

基　　金：国家重点研发计划(编号:2021YFB3301300)资助项目。

摘　　要：针对柔性车间设备传统周期性维护存在过维修现象,导致维修资源和生产成本的浪费,本文研究了柔性车间多目标调度与预测性维护协同管控方法.考虑订单工艺路径和产线机器资源复杂耦合特性,建立以最大完工时间,最大设备负荷和设备总负荷为优化目标的柔性车间调度模型;采用威布尔分布准确刻画车间设备的恶化效应,基于设备预测性维护模型设计最优维护策略;提出基于改进量子粒子群算法的柔性车间多目标调度与预测性维护协同优化方法,设计混合初始化方法以获得高质量的初始种群,构造三种邻域搜索算子和两种变异算子,提升调度与维护协同优化算法的搜索能力与搜索精度.实验结果验证了所提算法的有效性和可行性.Aiming at the over-repair phenomenon of the traditional cyclic maintenance of flexible workshop equipment,which leads to waste of maintenance resources and production costs,we study the synergistic control method of multi-objective scheduling and predictive maintenance.Considering the complex coupling characteristics of order process path and production line machine resources,a flexible workshop scheduling model is established with maximum completion time,maximum equipment load,and total equipment load as the optimization objectives;a Weibull distribution is used to accurately portray the deterioration effect of workshop equipment,and the optimal maintenance strategy is designed based on the predictive maintenance model of the equipment;a multiobjective scheduling method with predictive maintenance co-optimization is proposed based on the improved quantum particle swarm optimization algorithm and a multi-objective scheduling method is designed based on the improved quantum particle swarm optimization algorithm.A multi-objective scheduling and predictive maintenance co-optimization method based on improved quantum particle swarm optimization algorithm is proposed.A hybrid initialization method is designed to obtain a high-quality initial population,and three neighborhood search operators and two variational operators are constructed to improve the search capability and accuracy of the scheduling and maintenance co-optimization algorithm.The experimental results verify the effectiveness and feasibility of the proposed algorithm.

关 键 词：柔性车间调度问题 多目标优化 协同优化 量子粒子群算法 预测性维护 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]