Temperature Distribution Prediction in Control Cooling Process with Recurrent Neural Network for Variable-Velocity Hot Rolling Strips

Abstract

Control cooling is essential method for microstructure and mechanical properties control in hot rolling strip making. It is vital to realize high precises temperature distribution prediction and control in cooling process to ensure the industrial production. In this paper, a traditional mechanism model based on finite-difference method and combining with online cycle velocity calculation strategy was introduced as one of estimating temperature distribution baseline method. However, considering calculation time, variable-velocity rolling makes it difficult to rapidly realize temperature and water distribution modifying of each segment in cooling zone. Herein, a temperature distribution prediction method based on recurrent neural network was proposed, instead of only final cooling temperature prediction. And temperature distribution prediction performance of model with different recurrent cell and time steps were evaluated. The results indicated that the proposed model could realize temperature distribution prediction and the model based on bi-LSTM and 48 timesteps has the highest determination coefficient value of 0.976 and lowest root mean square error of 8.03 and mean absolute error of 5.7. Furthermore, compared with baseline model, the proposed model retained lower computational cost, making it applicable in industrial application by providing real-time temperature distribution prediction.