To predict the endpoint carbon content and temperature in basic oxygen furnace (BOF), the industrial parameters of BOF steelmaking are taken as input values. Firstly, a series of preprocessing works such as the Pauta ...To predict the endpoint carbon content and temperature in basic oxygen furnace (BOF), the industrial parameters of BOF steelmaking are taken as input values. Firstly, a series of preprocessing works such as the Pauta criterion, hierarchical clustering, and principal component analysis on the original data were performed. Secondly, the prediction results of classic machine learning models of ridge regression, support vector machine, gradient boosting regression (GBR), random forest regression, back-propagation (BP) neural network models, and multi-layer perceptron (MLP) were compared before and after data preprocessing. An improved model was established based on the improved sparrow algorithm and BP using tent chaotic mapping (CSSA-BP). The CSSA-BP model showed the best performance for endpoint carbon prediction with the lowest mean absolute error (MAE) and root mean square error (RMSE) values of 0.01124 and 0.01345 mass% among seven models, respectively. And the lowest MAE and RMSE values of 8.9839 and 10.9321 ℃ for endpoint temperature prediction were obtained among seven models, respectively. Furthermore, the CSSA-BP and GBR models have the smallest error fluctuation range in both endpoint carbon content and temperature predictions. Finally, in order to improve the interpretability of the model, SHapley additive interpretation (SHAP) was used to analyze the results.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.U1960202)the Science and Technology Commission of Shanghai Municipality(No.19DZ2270200).
文摘To predict the endpoint carbon content and temperature in basic oxygen furnace (BOF), the industrial parameters of BOF steelmaking are taken as input values. Firstly, a series of preprocessing works such as the Pauta criterion, hierarchical clustering, and principal component analysis on the original data were performed. Secondly, the prediction results of classic machine learning models of ridge regression, support vector machine, gradient boosting regression (GBR), random forest regression, back-propagation (BP) neural network models, and multi-layer perceptron (MLP) were compared before and after data preprocessing. An improved model was established based on the improved sparrow algorithm and BP using tent chaotic mapping (CSSA-BP). The CSSA-BP model showed the best performance for endpoint carbon prediction with the lowest mean absolute error (MAE) and root mean square error (RMSE) values of 0.01124 and 0.01345 mass% among seven models, respectively. And the lowest MAE and RMSE values of 8.9839 and 10.9321 ℃ for endpoint temperature prediction were obtained among seven models, respectively. Furthermore, the CSSA-BP and GBR models have the smallest error fluctuation range in both endpoint carbon content and temperature predictions. Finally, in order to improve the interpretability of the model, SHapley additive interpretation (SHAP) was used to analyze the results.
