자기조직화 신경망에 근거한 2단계 기계-부품 그룹 형성 알고리듬

Abstract

The machine-part group formation is to group the sets of parts having similar processing requirements into part families, and the sets of machines needed to process a particular part family into machine cells. The purpose of this study is to develop a two-phase machine-part group formation algorithm based on Self-Organizing Maps(SOM). In phase Ⅰ, it forms machine cells from the machine-part incidence matrix by means of SOM whose output layer is one-dimension and the number of output nodes is the twice as many as the number of input nodes in order to spread out the input vectors. In phase Ⅱ, it generates part families which are assigned to machine cells by means of machine ratio related with processing part and it gives machine-part group formation. The proposed algorithm performs remarkably well in comparison with well-known algorithms for the machine-part group formation problems.