Application of SVM regression in HAGC system

Abstract

This paper puts forward a design which is presented to estimate relatively accurate HAGC control system and then to predict the rolling gap. Considering many factors that influence the precision of the rolling gap, we can obtain the final formula of the rolling gap according to the theoretical calculation. Besides, A SVM (support vector machine) regression model based on the machine learning is proposed and applied to predict the rolling gap. According to the rolling data collected in the working field, we train SVM Regression model of the rolling gap, then the predicted rolling gap is achieved in the light of the SVM model. Compared with the RBF neural network, a combination of the theory model and SVM forecasting model improves the accuracy of steel strip thickness abundantly.