本文对制造系统的聚类分析(即单元构造)问题进行了研究。首先以距离最大为原则选择机器聚类块的“种子”,保证“种子”具有代表性,然后根据聚类块的中心距,对某些相似的聚类块进行合并,完成机器成组,根据机器成组信息,构造工件族的理想工件作为工件聚类时的“种子”,将全部工件划分成工件族,数值例子验算表明,本文提出的算法可以很好地解决制造系统中单元构造问题。 This paper studies the clustering analysis (ie, cell structure) of manufacturing systems. Firstly, the “seeds” of the machine clustering block are selected based on the principle of maximum distance to ensure that the “seeds” are representative. Then, according to the center distance of the clustering block, some similar clustering blocks are merged to complete the machine grouping, Machine grouping information, constructing the ideal workpiece of the workpiece family as the “seed” when the workpiece is clustered, and dividing all the workpiece into the workpiece family. Numerical examples show that the algorithm proposed in this paper can solve the problem of cell structure in the manufacturing system well.