Prediction of silicon content in hot molten of blast furnace based on big data technology
LIU Xiao-jie1, DENG Yong1, LI Xin1, HAO Liang-yuan2, LIU Er-hao3, LÜ Qing1
1. College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, Hebei, China; 2. Steel Research Institute, HBIS Group Co., Ltd., Shijiazhuang 050000, Hebei, China; 3. Chengde Branch, HBIS Group Co., Ltd., Chengde 067000, Hebei, China
Abstract:The silicon content in hot metal is not only the chemical heat representation of the hearth heat system, but also an important parameter to characterize the furnace temperature and hot metal quality. 30 input parameters of real-time database and laboratory database of No.4 blast furnace of a certain steel plant in 2019 were selected. Through data processing and feature extraction, 17 parameters were finally selected for model prediction, with a total of 8 760 groups. The Adaboost model, decision tree model and random forest model were constructed to predict the silicon content in hot metal after 2 hours. It was found that the accuracy of Adaboost model was higher than that of decision tree model and random forest model. In terms of learning effect, the Adaboost model was superior, which can better capture and predict the silicon content in hot metal.
刘小杰, 邓勇, 李欣, 郝良元, 刘二浩, 吕庆. 基于大数据技术的高炉铁水硅含量预测[J]. 中国冶金, 2021, 31(2): 10-16.
LIU Xiao-jie, DENG Yong, LI Xin, HAO Liang-yuan, LIU Er-hao, LÜ Qing. Prediction of silicon content in hot molten of blast furnace based on big data technology[J]. China Metallurgy, 2021, 31(2): 10-16.
CHANG C J, LI D C, HUANG Y H, et al. A novel gray forecasting model based on the box plot for small manufacturing data sets[J]. Applied Mathematics and Computation, 2015, 265: 400.
LIU Song, LYU Qing, LIU Xiao-jie, et al. Synthetically predicting the quality index of sinter using machine learning model[J]. Ironmaking and Steelmaking, 2020, 47(7): 828.
[12]
Camilon P R, Levi J R, Carrion R A, et al. Physician impact on the patient and family experience in a pediatric otolaryngology practice[J]. Laryngoscope, 2019, 129(11): 2610.