Evaluation of Cell Formation Algorithms and Implementation of MOD-SLC Algorithm as An effective Cellular Manufacturing System in a Manufacturing Industry

Abstract

Benefits of cellular manufacturing system depend on major factors namely the design of machine cells and part family, setup time and method of operation. Cellular Manufacturing System (CMS) become a failure when these two factors are not properly employed. This work incorporates five array-based clustering algorithms namely Single linkage clustering method (SLC), Modified-Single Linkage Clustering method (MOD-SLC), Direct Clustering Analysis (DCA), Rank Order Clustering (ROC) and Rank Order Clustering-2 (ROC-2) for analyzing real time manufacturing delay with manufacturing cell formation. In the present study, Modified-Single Linkage Clustering (MOD-SLC) method outperforms the other four methods, regardless of the measure used, irrespective of any additional prevalence of exceptional elements in the data set. The results are validated with real time manufacturing systems data.