Prediction of Rolling Force for Hot Strip Rolling Based on RFR

In the hot strip rolling, rolling force is one of the important factors affecting the shape of steel strip. There are some errors in the mechanism model used to predict the secondary rolling force of hot strip rolling in a steel company. In this paper, in order to improve the setting accuracy of the rolling force in production line, the rolling force prediction based on historical production data is studied in this paper. First, in order to reduce the computational complexity of the model and improve the prediction accuracy, correlation analysis and local outlier factor algorithm are used to preprocess the data. Secondly, a rolling force prediction model based on random forest regression algorithm is proposed in this paper, Experimental results based on actual data show that the proposed method has a better predictive effect.