Part-machine grouping using a multi-objective cluster analysis

Abstract

In the existing literature, the part-family formation problem is handled either by the coding systems or the cluster analysis. In this study, we propose a new method that will consider both design and manufacturing attributes and operation sequences simultaneously, in conjunction with the related performance measures such as the machine investment, the amount of workload deviations within and between the cells, and the number of skippings. Finally, the proposed method is compared with the similarity coefficient method under different experimental settings and its robustness is checked against the varying system parameters.