Wear prediction model of hot rolling backup roll based on FEM + ML algorithm

The wear of backup rolls will have a great impact on the quality of the shape of hot rolled strip sheet. In order to overcome the limitations of the finite element method (FEM) in calculating backup roll wear in terms of efficiency and accuracy, this paper proposes a tandem FEM + ML hybrid model to optimise the predictive effect of the finite element method (FEM) on backup roll wear. Firstly, a backup roll wear model based on FEM is established. Secondly, in order to select the optimal machine learning (ML) algorithm as the finite element error compensation model, three types of finite element error compensation models were established based on the random forest (RF) algorithm, the radial basis function (RBF) neural network algorithm, and the particle swarm optimisation support vector machine (PSO-SVM) algorithm. Finally, the three types of finite element error compensation models were connected in series with the FEM model to compare the prediction performance of the three types of FEM + ML models on backup roll wear. The numerical experimental results show that the FEM + PSO-SVM model can better predict the wear of the backup roll, and the PSO-SVM algorithm is the most suitable for building the finite element error compensation model. It is proved that the FEM + ML model proposed in this paper can effectively improve the accuracy and computational efficiency of the FEM model for predicting backup roll wear without adding microelements. In addition, among the hot rolling parameters, the rolling force has the greatest influence on the backup roll wear, and excessive rolling force for a single pass should be avoided to slow down the backup roll wear.