A real-time expert system with GPC for cold strip mill

In this paper, a real-time expert system for cold strip mill is developed using a generalized predictive control (GPC) approach. A simple model of the cold strip mill for gauge and shape regulation is derived. The expert system captures such an engineer's knowledge for gauge and shape regulation and builds a knowledge base which contains both structural and behavioral knowledge. For the purpose of real time control, a rule-based regulator is proposed. Simulation results are given in the paper to show the good performance of the system designed by the proposed method.