Fuzzy c-means clustering approach for virtual cell formation

A virtual cell formation involves grouping of machines to form machine cells, and parts to form part families to improve flexibility in scheduling and effectiveness of cellular manufacturing systems. This paper presents a fuzzy c-mean clustering approach for machine cell formation based on the real life production factors. In fuzzy c-means clustering, a membership function is used to express the strength of association with every machine cell. This gives the decision-maker flexibility in cell formation that depends on the practical constraints. In this work, real life production attributes like processing time, alternative routings, sequence of operation, machine flexibility, machine capacity and product demand have been considered for machine cell formation. The performance of the proposed methodology is tested using group technology efficiency (GTE) and exceptional elements (EE) for 15 cases of different size problems from open literature and compared with the best available results in the literature. It is observed from the results that the proposed method of cell formation performs better than the existing methods in many instances and is capable of solving varied sizes of cases.