多目标U型顺序相依装配线平衡问题的改进NSGA-Ⅲ  

Improved NSGA-Ⅲfor multi-objective U-shaped sequence-dependent assembly line balancing problem

作　　者：夏建平 李尚强 部绍闵 杨庆福 高德优 XIA Jianping;LI Shangqiang;BU Shaomin;YANG Qingfu;GAO Deyou(Avic Chengdu Aircraft Industrial(Group)Co.,Ltd.,Chengdu 610091,China)

机构地区：[1]成都飞机工业(集团)有限责任公司,成都610091

出　　处：《现代制造工程》2023年第12期13-21,共9页Modern Manufacturing Engineering

摘　　要：在产品装配时无先后关系约束的作业之间可能存在装配干扰,使作业时间依赖于装配顺序,导致产品装配时间增加,从而影响装配线的平衡。为此,考虑装配过程中作业间的相互干扰,以工位开启数量、空闲时间均衡指标、总装配时间和装配成本为目标,构建多目标U型顺序相依装配线平衡优化模型,并提出一种改进第三代非支配排序遗传算法(Non-dominated Sorting Genetic Algorithm-Ⅲ,NSGA-Ⅲ)进行求解。所提算法引入了变邻域搜索算法的局部搜索特性以平衡算法的探索与开发关系;设计了基于问题约束下的编码、解码、种群更新和选择操作。最后,通过算例测试和实例分析验证算法的高效性。There may be assembly interference between tasks that are not constrained by precedence relationships during product assembly,which causes the operation time of tasks to depend on the assembly order,increases the product assembly time,and affects the balance of the assembly line.Therefore,considering the mutual interference between tasks during assembly,a multi-objective U-shaped dependent assembly line balancing optimization model is constructed with the objectives of workstation number,idle time balance index,assembly time,and assembly cost,and an improved Non-dominated Sorting Genetic Algorithm-Ⅲ(NSGA-Ⅲ)is proposed for solving it.The proposed algorithm introduces the local search characteristics of the variable neighborhood search algorithm to balance the relationship between exploration and exploitation of the algorithm,and designs encoding,decoding,population updating,and selection operations based on problem constraints.Finally,the efficiency of the algorithm is verified through case studies and practical analysis.

关 键 词：U型装配线平衡 顺序相依 改进第三代非支配排序遗传算法 多目标优化 帕累托 

分 类 号：TH165[机械工程—机械制造及自动化] TP301.6[自动化与计算机技术—计算机系统结构]