中南大学学报（自然科学版）2025，Vol.56Issue(9)：3627-3639,13.DOI:10.11817/j.issn.1672-7207.2025.09.005
基于数据挖掘的电弧炉炼钢终点温度预测研究
Research on molten steel end-point temperature prediction model in electric arc furnace steelmaking process using data mining methods
摘要
Abstract
A data mining strategy for accurately predicting the end-point temperature of molten steel(EPT-MS)in electric arc furnace(EAF)steelmaking based on anomaly detection,feature selection and machine learning algorithm was proposed.Real EAF steelmaking process data of 1 235 heats with 31-1 input-output pair were used to verify the effectiveness of this strategy.Four supervised learning prediction algorithms including logistic regression(LR),k-nearest neighbors(kNN),decision tree(DT)and extreme gradient boosting(XGBoost)were used for prediction model development.The prediction performance was evaluated considering influencing factors including the data volume,unsupervised learning anomaly detection algorithms,feature selection methods,and supervised learning algorithms.The results show that XGBoost outperforms the other three algorithms and shows hit rates over 40%,80%and 95%within temperature error bounds of±5,±10 and±15℃.Both data quality and volumes affect the supervised learning prediction algorithm models.The unsupervised anomaly deletion algorithm AE enhances data quality affecting prediction accuracy greatly.The permutation importance feature selection can simplify the model structure.The EPT-MS prediction problem should be analyzed more comprehensively from multiple perspectives of data,features and algorithms.关键词
电弧炉炼钢/终点温度/预测模型/数据挖掘/机器学习/异常检测Key words
electric arc furnace steelmaking/end-point temperature/prediction model/data mining/machine learning/anomaly detection分类
矿业与冶金引用本文复制引用
胡航,邹雨池,魏光升,李冠男,郭宇峰,杨凌志..基于数据挖掘的电弧炉炼钢终点温度预测研究[J].中南大学学报（自然科学版）,2025,56(9):3627-3639,13.基金项目
国家自然科学基金资助项目(52474368,52174328) （52474368,52174328）
中南大学研究生自主探索创新项目(2024ZZTS0062)(Projects(52474368,52174328)supported by the National Natural Science Foundation of China （2024ZZTS0062）
Project(2024ZZTS0062)supported by the Fundamental Research Funds for the Central Universities of Central South University) （2024ZZTS0062）
