NEURAL NETWORK BASED REAL-TIME PRODUCTION SCHEDULING FOR INDUSTRIAL PROCESSES

Abstract

This paper presents an artificial neural network (ANN) based real-time production scheduling expert system existing in a hierarchical integrated computer control/production management system for some industrial processes with multi-production-stages and discreat event operations. A hierarchical neural network model has been developed to build an expert system to solve the problem under study. According to the real-time information both of status of production facilities and mass/energy flow as well as the long term production scheduling, the expert system makes the real-time production scheduling strategy, supervises the production process, and operats the production process both in normal and abnormal operating conditions. Introducing this real-time production scheduling, a computer simulation for the real-time production scheduling of a steel plate mill shows the satisfactory result.