USING EVOLUTIONARY COMPUTATION APPROACH TO IMPROVE THE PERFORMANCE OF THE FUZZY-ART FOR GROUPING PARTS

Abstract

ABSTRACT In this research, a hybrid intelligent approach has been proposed to the group technology purpose based on the part geometrical shapes and manufacturing attributes to improve productivity in manufacturing. In literature, artificial neural networks (ANN) have been widely applied for the part grouping applications. However, when the number of part data becomes larger, it will be more difficult to find the most appropriate ANN parameters to get the most desired grouping results. Currently, the parameter-selection process in ANN has mostly been done manually by the way of trial and error. It is time-consuming and does not guarantee an optimum result. Evolutionary computation approach (EC) is an optimal mathematical search technique based on the principles of natural selection and genetic recombination. Therefore, a hybrid approach (EC based Fuzzy Adaptive Resonance Theory; ECFART) incorporating an EC and a Fuzzy-ART neural network has been proposed to automate the Fuzzy-ART parameters selection process so that the best part-grouping can be obtained. A set of twenty-five hypothetical part data has been tested in order to validate the proposed approach. The results show that the proposed hybrid approach could generate the most appropriate parameters of Fuzzy-ART consistently and efficiently.