Synergy of Artificial Neural Networks and Knowledge-Based Expert Systems for Intelligent FMS Scheduling

Luis Carlos Rabelo, University of Missouri - Rolla
Sema E. Alptekin, University of Missouri - Rolla
Ali S. Kiran, University of Southern California

Article comments

DOI: http://dx.doi.org/10.1109/IJCNN.1990.137594.

© 1990 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

NOTE: At the time of publication, the author Sema Alptekin was affiliated with the University of Missouri - Rolla. Currently, August 2008, she is Professor of Industrial & Manufacturing Engineering and Director of the University Honors Program at California Polytechnic State University - San Luis Obispo .

Abstract

In this paper we describe a hybrid architecture that integrates artificial neural networks and knowledge-based expert systems to generate solutions for the real time scheduling of flexible manufacturing systems. The artificial neural networks perform pattern recognition and, due to their inherent characteristics, support the implementation of automated knowledge acquisition and refinement schemes through a feedback mechanism. The artificial neural network structures enable the system to recognize patterns in the tasks to be solved in order to select the best scheduling rule according to different demands. The knowledge-based expert systems are the higher order elements which drive the inference strategy and interpret the constraints and restrictions imposed by the upper levels of the flexible manufacturing system control hierarchy. The level of self-organization achieved provides a system with a higher probability of success than traditional approaches.