Development of a hybrid model for manufacturing cell formation using linguistic theory

This paper presents a new approach for solving cluster formation problems using a linguistic model. The method starts with a hierarchical model in deciding the number of clusters/ machine groups. The solution is further improved by utilizing a genetic algorithm with the objective of decreasing inter-cell move in terms of bottleneck machines. A unique feature of the proposed method is that it recognizes the operations sequence of manufacturing the parts, specified in the process sheets. The concept of null machine is introduced in the linguistic model to calculate the dissimilarity index in the form of Levenshtein´s distance. The model developed by the author can be utilized either for flow type or random job-shop type manufacturing shop, with the emphasis of minimizing the back tracking. Number of machine groups can be predefined in the model. The model has been utilized to partition realistic discrete manufacturing systems for which the machine part incidence matrix shows sparse density.