GENERALIZED MACHINE CELL-FORMATION CONSIDERING MATERIAL FLOW AND PLANT LAYOUT USING MODIFIED SELF-ORGANIZING FEATURE MAPS

In this paper, we develop a new generalized machine cell formation tec hnique considering production sequences, lot sizes processing times, o f machine grouping, and the plant layout via the self-organizing featu re maps (SOFM). In particular, second layer node architecture is const ruct to reflect the above factors. From the result of SOFM learning, a generalized machine cell formation matrix is obtained such that the m aterial now is reduced and the spacial restriction for the layout is r easonably considered. The adopted performance measures include the rec overy ratio of bond energy, the grouping efficacy, the total inter-cel l movement and the computational time. The results are compared with t he rank order clustering method (ROC), the direct clustering analysis method (DCA), and the spark clustering analysis. The experimental resu lt shows that the proposed method performs well in the sense of materi al now reduction and layout efficiency, as well as in the sense of rob ustness and some other functionalities. (C) 1997 Elsevier Science Ltd.