Cell formation using a fuzzy min–max neural network

This paper proposes the application of a Fuzzy Min–Max neural network for part family formation in a cellular manufacturing environment. Once part families have been formed, a minimum cost flow model is used to form the corresponding machine cells. For simplicity, the input data are in the form of a binary part–machine incidence matrix, although the algorithm can work with an incidence matrix with continuous values. The application of Fuzzy Min–Max is interpreted in physical terms and compared with a related neural network applied previously for cell formation, the Fuzzy ART network. Both neural networks have similarities and differences that are outlined. The algorithms have been programmed and applied to a large set of problems from the literature. Fuzzy Min–Max generally outperforms Fuzzy ART, and the computational times are small and similar in both algorithms.