Abstract:The thermal state of blast furnace is one of the important factors affecting the blast furnace smelting, and its monitoring and prediction are the focus of the industry. The prediction of blast furnace thermal state is often transformed into the classification problem which focuses on predicting the change trend of silicon content in hot metal, and the regression problem which focuses on predicting the specific value of silicon content in hot metal. A neural network model was proposed combined with long short-term memory(LSTM) and multi-task learning to solve the classification and regression problems of blast furnace thermal state prediction at the same time. The model was trained on two typical blast furnace data sets, and the classification prediction result could reach the accuracy of 0.84, and the regression prediction result could reach the hit rate of 0.76 and the correlation coefficient of 0.819 6. Two single task learning models were trained and compared with multi-task learning models. The experimental results show that the multi-task learning model can simultaneously improve the prediction performance of blast furnace thermal state classification and regression tasks, and the prediction results are better than the single task model.
胡进, 郜传厚. 基于多任务学习的高炉热状态预测[J]. 中国冶金, 2023, 33(7): 81-90.
HU Jin, GAO Chuanhou. Thermal state prediction of blast furnace based on multi-task learning[J]. China Metallurgy, 2023, 33(7): 81-90.
WALLER M,SAXEN H. Time-varying event-internal trends in predictive modeling methods with applications to ladlewise analyses of hot metal silicon content[J]. Industrial and Engineering Chemistry Research,2003,42(1):85.
CHEN S,GAO C. Linear priors mined and integrated for transparency of blast furnace black-box SVM model[J]. IEEE Transactions on Industrial Informatics,2019,16(6):3862.
[7]
JIAN L,GAO C. Binary coding SVMs for the multiclass problem of blast furnace system[J]. IEEE Transactions on Industrial Electronics,2012,60(9):3846.
LI J,HUA C,YANG Y,et al. Fuzzy classifier design for development tendency of hot metal silicon content in blast furnace[J]. IEEE Transactions on Industrial Informatics,2017,14(3):1115.
NURKKALA A,PETTERSSON F,SAXEN H. Nonlinear modeling method applied to prediction of hot metal silicon in the ironmaking blast furnace[J]. Industrial and Engineering Chemistry Research,2011,50(15):9236.
GRAVES A,SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks,2005,18(5/6):602.
GAO C,GE Q,JIAN L. Rule extraction from fuzzy-based blast furnace SVM multiclassifier for decision-making[J]. IEEE Transactions on Fuzzy Systems,2013,22(3):586.
[27]
GAO C,JIAN L,LUO S. Modeling of the thermal state change of blast furnace hearth with support vector machines[J]. IEEE Transactions on Industrial Electronics,2011,59(2):1134.