HUMAN COGNITION INSPIRED PROCEDURES FOR PART FAMILY FORMATION BASED ON NOVEL INSPECTION BASED CLUSTERING APPROACH

Human cognition based procedures are promising approaches for solving different kind of problems, and this paper addresses the part family formation problem inspired by a human cognition procedure through a graph-based approach, drawing on pattern recognition. There are many algorithms which consider nature inspired models for solving a broad range of problem types. However, there is a noticeable existence of a gap in implementing models based on human cognition, which are generally characterized by “visual thinking”, rather than complex mathematical models. Hence, the natural power of reasoning - by detecting the patterns that mimic the natural human cognition - is used in this study as this paper is based on the partial implementation of graph theory in modelling and solving issues related to part machine grouping, regardless of their size. The obtained results have shown that most of the problems solved by using the proposed approach have provided interesting benchmark results when compared with previous results given by GRASP (Greedy Randomized Adaptive Search Procedure) heuristics. Keywords: Cellular manufacturing systems; part family formation; human cognition; inspection-based clustering.

Part Family Formation Based on Clustering Algorithm and BP Network

To solve the problem of design and manufacturing on the production of many varieties of small batch, the parts grouping method that based on clustering algorithm, clustering validity index and BP neural network method for new parts is proposed. At first, mathematical model of part clustering is built, and parts grouping is based on the similarity of data and cluster centers which is calculated by Euclidean distance, then the effectiveness of parts group is tested by Function Index and optimal number of clusters group can be found. The algorithm is achieved by Matlab clustering toolbox, so the best part family structure is built. Furthermore, the grouped parts are used to train the BP neural network toolbox in Matlab, then simulate new parts on network to find the match group. At last, a case study was also presented to verify the feasibility of this method．