Similarity-based cluster analysis for the cell formation problem

This chapter illustrates the cell formation problem (CFP) as supported by the similarity based manufacturing clustering approach. A literature review on existing problem oriented models and tools is reported. In particular the role of generic similarity index (SI) is presented both as general purpose and problem oriented index. In problem oriented indices there are several factors which play an important role in the determination of the value of similarity between two generic machines, e.g. the number of machines visited by each part, the sequence of manufacturing operations, the production quantity for each part, the manufacturing unit time, etc. A significant numerical example is illustrated in order to clearly define the basic steps for the implementation of an effective procedure of clustering machines into manufacturing cells and parts/products into families of parts: data collection, similarity index evaluation, clustering algorithm development and application, dendrogram construction, threshold value of group similarity definition, part assignment, and performance evaluation. An experimental analysis conducted on a literature problem oriented instance is also illustrated to compare the performance of different problem settings and define best practices and guidelines for professional and practitioners of industry. A problem setting is a combination of multiple decisions corresponding to the adoption of a set of attributes, e.g. the similarity index, the clustering rule, the threshold value of group similarity, and the part family formation rule. Literature presents many indices but a few significant case studies and instances not useful to properly compare them and support the best choice given an operating context, i.e. a specific production problem.