基于PSO-GA混合算法的转向架混流装配车间生产调度研究  

Research on production scheduling of bogie mixed flow assembly shop based on PSO-GA hybrid algorithm

作　　者：雷斌[1,2,3] 刘同朝 Lei Bin;Liu Tongchao(Mechatronics T&R Institute,Lanzhou Jiaotong University,Lanzhou 730070,China;Gansu Provincial Engineering Technology Center for Informatization of Logistics&Transport Equipment,Lanzhou 730070,China;Gansu Provincial Industry Technology Center of Logistics&Transport Equipment,Lanzhou 730070,China)

机构地区：[1]兰州交通大学机电技术研究所,兰州730070 [2]甘肃省物流及运输装备信息化工程技术研究中心,兰州730070 [3]甘肃省物流与运输装备行业技术中心,兰州730070

出　　处：《现代制造工程》2020年第7期19-24,共6页Modern Manufacturing Engineering

基　　金：国家自然科学基金资助项目(61563029);甘肃省高等学校科研资助项目(2018C-10);兰州市科技计划项目(2019-1-33)。

摘　　要：转向架混合流水(混流)装配车间生产调度是一个典型的离散变量NP-hard问题,为了优化其生产作业流程,提高生产效率,对某机车车辆有限公司的转向架混合流水装配车间生产线生产调度进行数学模型的构建,以全部工件完成时间为目标函数,采用随机权重法,引入遗传算法(Genetic Algorithm,GA)的选择、交叉和变异操作,设计了一种基于排列的3层编码PSO-GA混合算法,并进行仿真研究,通过对粒子群优化(Particle Swarm Optimization,PSO)算法、GA和PSO-GA混合算法这3种算法进行比较分析,验证了PSO-GA混合算法的有效性,并得到了该转向架混合流水装配车间的生产调度甘特图。The production scheduling of bogie mixed flow assembly shop is a typical discrete variable NP-hard problem.In order to optimize the production process and improve the production efficiency,constructs a mathematical model for the production line of bogie mixed flow assembly shop of a rolling stock Co.,Ltd.,taking the completion time of all workpieces as the objective function,adopts the random weight method and introduces the Genetic Algorithm(GA).A three-layer coding PSO-GA hybrid algorithm based on permutation was designed for selection,crossover and mutation operation of PSO-GA,and simulation research was carried out.Through the comparative analysis of Particle Swarm Optimization(PSO)algorithm,GA and PSO-GA hybrid algorithm three algorithms,the effectiveness of the PSO-GA hybrid algorithm is verified and the Gantt chart of production sequencing between the hybrid assembly line vehicles is obtained.

关 键 词：混合流水 转向架 生产调度 PSO-GA混合算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]