基于Stacking算法的转炉吹炼终点钢水磷含量预测  

Prediction of phosphorus content in molten steel at the end of converter blowing based on Stacking algorithm

作　　者：于飞 罗辉林 柯凯 张天 YU Fei;LUO Huilin;KE Kai;ZHANG Tian(Steelmaking Plant of Zhongtian Iron&Steel Group Co.,Ltd.,Changzhou 213000,China;Steelmaking Division of Hunan RAMON Technology Co.,Ltd.,Changsha 410000,China)

机构地区：[1]中天钢铁集团有限公司炼钢厂,江苏常州213000 [2]湖南镭目科技有限公司炼钢事业部,长沙湖南410000

出　　处：《炼钢》2024年第4期11-16,共6页Steelmaking

摘　　要：根据中天钢铁集团有限公司120 t转炉的实际生产数据,建立基于Stacking集成学习算法的转炉终点钢水磷含量预测模型。通过脱磷热力学分析确定影响脱磷的主要因素,进而确定模型的输入变量。在数据预处理完成后使用6种机器学习算法(RF、ET、XGBoost、LightGBM、CatBoost、NN)分别建立模型,再将这6种模型的预测结果使用多元线性回归算法进行Stacking集成建模。通过对比这7种模型的预测结果可以得到:Stacking集成模型的预测效果最好,其预测终点钢水磷质量分数误差为±0.004%、±0.005%时的命中率分别为90.59%、97.56%。According to the actual production data of 120 t converter of Zhongtian Iron and Steel Group Co.,Ltd.,a prediction model of phosphorus content in molten steel at the end of converter blowing based on Stacking algorithm was established.The main factors influencing dephosphorization were determined through the thermodynamic analysis of dephosphorization,and then the input variables of the model were determined.After the data preprocessing was completed,six machine learning algorithms(RF,ET,XGBoost,LightGBM,CatBoost,and NN)were used to establish the models,and then the prediction results of these six models were used for Stacking ensemble modeling by multiple linear regression algorithm.By comparing the prediction results of these seven models,it could be concluded that the Stacking ensemble model had the best prediction effect,and the hit rates of the predicted endpoint phosphorus mass fraction were 90.59%and 97.56%when the error interval was±0.004%and±0.005%,respectively.

关 键 词：转炉炼钢 终点磷含量预测 集成学习 Stacking集成 

分 类 号：TF711[冶金工程—钢铁冶金]