Online Thickness Prediction of Hot Rolling Strip Based on ARO-XGBoost

An online thickness prediction algorithm for strip steel based on machine learning is proposed to address issues of strong coupling and low accuracy in the thickness mathematical model. Firstly, the rolling data is used to establish an online thickness prediction model by optimizing the eXtreme Gradient Boosting (XGBoost) algorithm parameters based on the Artificial Rabbits Optimization (ARO) algorithm. Then, a self-learning system is deployed to optimize the results. Finally, the predicted outcomes will be compared with the actual thickness to verify the accuracy of the thickness prediction model. The experimental results show that the online thickness prediction algorithm can quickly and accurately predict the strip thickness. When the ARO-XGBoost model was used to predict the 3 mm, 4 mm, and 5.65 mm strips, Root Mean Square Error (RMSE) can be controlled within 11.5 μm, 12 μm, and 16.6 μm. The results can improve the accuracy of the thickness mathematical model for hot strip rolling and enhance the level of the thickness control system.