ARTIFICIAL NEURAL NETWORKS FOR FLEXIBLE MANUFACTURING SYSTEMS SCHEDULING

Artificial neural networks (ANNs) are information processing systems m otivated by the goals of reproducing the cognitive processes and organ izational models of neurobiological systems. By virtue of their comput ational structure, ANN's feature attractive characteristics such as gr aceful degradation, robust recall with noisy and fragmented data, para llel distributed processing. generalization to patterns outside of the training set, nonlinear modeling capabilities, and learning. These co mputational features could provide enhanced inferencing functionality and real-time capabilities to develop approaches for traditional diffi cult problems such as flexible manufacturing system (FMS) scheduling. In this paper three different schemes of ANN's are applied to the FMS scheduling problem. These include a) relaxation-based networks, b) com petitive-based schemes, and c) adaptive pattern recognition scheduling .