Development of an improved CBR model for predicting steel temperature in ladle furnace refining

In the prediction of the end-point molten steel temperature of the ladle furnace, the influence of some factors is nonlinear. The prediction accuracy will be affected by directly inputting these nonlinear factors into the data-driven model. To solve this problem, an improved case-based reasoning model based on heat transfer calculation (CBR-HTC) was established through the nonlinear processing of these factors with software Ansys. The results showed that the CBR-HTC model improves the prediction accuracy of end-point molten steel temperature by 5.33% and 7.00% compared with the original CBR model and 6.66% and 5.33% compared with the back propagation neural network (BPNN) model in the ranges of −3, 3 and −7, 7, respectively. It was found that the mean absolute error (MAE) and root-mean-square error (RMSE) values of the CBR-HTC model are also lower. It was verified that the prediction accuracy of the data-driven model can be improved by combining the mechanism model with the data-driven model.