A transiently chaotic neural network approach to the design of cellular manufacturing

The design of Cellular Manufacturing Systems (CMS) has attained the significant attention of academicians and practitioners over the last three decades. Minimizing intercellular movements while maximizing utilization of machines are the main objectives of interest in designing CMS and are considered in present research. In this paper, the drawbacks of former neural networks-based approaches to cell formation are discussed. The standard version of cell formation problem is formulated and a 'Transiently Chaotic Neural Network' (TCNN) with supplementary procedures is introduced as a powerful rival. A simplified network is constructed. After developing the related equations the approach is tested using the proposed algorithm with 18 problems selected from literature. The results are compared with various other approaches including ART1, Extended-ART1, Ortho-Synapse Hopfield Neural Network (OSHN), etc. The main advantages of our proposed method are: (1) the ability to avoid the local optima trap, (2) the ability to solve problems of different sizes with the same set of values for parameters, and (3) the less computation time. The results also indicate considerable improvement in grouping efficiency through the proposed approach.