Model Adaptive Learning for Steel Rolling Mill Control

Abstract

Steel rolling process exhibits multi-variables, multi-models, nonlinear, time-varying. This paper describes a model adaptive learning method for steel rolling process control. Optimize mechanism of long self-learning and short self-learning based on model adaptive learning are proposed. Moreover, model adaptive technology based on model classification and information system classification are used. The rolling mill strategy optimize method are founded. The fitness of multi-varieties and multi-standards is solved greatly. The application results show that the proposed controller can optimize the steel enterprise yield process control system, have practical significances and promotional value.