基于流程时间矩阵的单元化制造系统设计  

Design of Cellular Manufacturing System Based on Matrix Clustering Algorithm

作　　者：祝恒云[1] 叶文华[1] 

机构地区：[1]南京航空航天大学机电工程学院

出　　处：《应用科学学报》2008年第1期100-105,共6页Journal of Applied Sciences

摘　　要：近几年来,单元化制造系统(CMS)作为一种由于能满足不同客户需求、缩短产品生产周期、提高企业的全球竞争力的先进制造组织模式而备受关注.本文提出了一种新的矩阵聚类方法(HERBAL)设计制造单元,并探讨了该方法与其他聚类方法如ROC,ROC2,DCA等方法在成组效率、成组功效等评价指标上的优劣,证明了该方法的可行性和高效率.同时该方法中的设备-零件矩阵(MCM)中的二元值元素,采用反映实际生产的流程时间替代,可使聚类结果更符合实际的生产需求.In recent years, cellular manufacturing system （CMS） is considered as an advanced manufacturing system that can meet variable customer demand, short product life cycle, and increasing, worldwide competition. In this paper, a method for designing CMS based on a new matrix clustering algorithm is proposed. Compared to other clustering algorithms such as ROC, ROC2 and DCA in terms of grouping efficiency and grouping efficacy, the method is feasible and with higher efficiency. The elements in machine component matrix are modified from binary to non-binary elements, which provide information of actual intercellular flows of components. This change can provide a more reasonable clustering resuh than otber methods.

关 键 词：单元化制造 成组 聚类算法 

分 类 号：TH165[机械工程—机械制造及自动化]