NEURAL NETWORKS IN MANUFACTURING CELL DESIGN

This paper presents a neural network approach in determining the appro priate manufacturing cell configuration that meets the required perfor mance measures. Simulation experiments were conducted with many possib le combinations of design changes to calculate cell performance measur es, and thus generate training pairs for a neural network. Three diffe rent static neural network structures have been trained using the abov e data. Comparison of neural network efficiency and computational effo rt required is made through a case study, for every neural network arc hitecture. (C) 1998 Published by Elsevier Science B.V. All rights rese rved.