聚类和NSGA-Ⅱ联合算法在混合流水车间的应用研究  

Application Research of Clustering and NSGA-ⅡJoint Algorithm in Hybrid Flow Shop

作　　者：韩树贤 赵文普[1] 闫华[1] HAN Shuxian;ZHAO Wenpu;YAN Hua(China Airborne Missile Academy,Luoyang 471009)

机构地区：[1]中国空空导弹研究院,洛阳471009

出　　处：《舰船电子工程》2024年第4期188-193,共6页Ship Electronic Engineering

基　　金：国家基础科研重点项目(编号:JCKY2019205B012)资助。

摘　　要：为了改善某高端装备制造企业总装车间混流生产调度困难、批处理阶段产品组批困难的问题,以及实现车间多个目标的同步联合优化,研究了含批处理机的混合流水车间多目标优化问题。首先根据车间运行情况建立了多目标优化模型,之后提出了基于K-means聚类算法和非支配排序遗传算法(NSGA-Ⅱ)的联合方法,设计了能够对不相容产品进行分组的聚类流程,以及基于产品组编号和组内产品编号的双层编码方式,为批处理工序设计了完整的组批流程。最后,使用车间生产案例进行测试,并将测试结果同仅使用NSGA-Ⅱ得到的结果进行对比,验证了所提方法的有效性。In order to improve the scheduling difficulty of mixed-flow production in the final assembly shop of a high-end equipment manufacturing enterprise,the difficulty of product group batch in the batch processing stage and realize the joint optimi⁃zation of multi-objective in the workshop,this paper investigates the multi-objective optimization problem of hybrid flow shop with batch processors.Firstly,a multi-objective optimization model is established according to the operation situation of the workshop,and then a joint method based on K-means clustering algorithm and non-dominated sorting Genetic Algorithmⅱ(NSGA-Ⅱ)is proposed.A clustering process is designed to group incompatible products,and a double-layer coding method based on product group number and product number within the group is designed.A complete group batch process is designed for batch operations.Fi⁃nally,the workshop production case is used to test,and the results are compared with the results obtained by only using NSGA-Ⅱ,which verifies the effectiveness of the proposed method.

关 键 词：混合流水车间 并行批处理机 非支配排序遗传算法 K-MEANS算法 

分 类 号：TB497[一般工业技术]