【摘要】 基于260 t转炉实际生产数据，通过机器学习算法XGBoost（eXtreme Gradient Boosting,极限梯度提升树）、弹性回归、线性回归、AdaBoost（Adaptive Boosting,自适应提升树）四种算法建立了终渣主要成分CaO、SiO₂、TFe和MgO的预测模型。通过优化调参，XGBoost终渣成分预测模型的决定系数R²均在0.8以上。溅渣时间模型采用SVR（Support Vector Regression,支持向量机回归）、LGBM （Light Gradient Boosting Machine,轻量梯度提升机回归）、GBDT（Gradient Boosting Decision Tree,梯度提升树回归）、RF（Random Forest,随机森林）和XGBoost五种算法进行建模。通过探究，将SVR、XGBoost、GBDT算法使用集成方法得到Stacking集成溅渣时间预测模型，Stacking集成溅渣时间预测模型提升了单个模型的预测效果，偏差为±20 s的预测命中率达89.95%。更多还原

【Abstract】 Based on the actual production data of 260 t converter, prediction models of the main components of endpoint slag, CaO, SiO₂, TFe and MgO, were established through four algorithms of machine learning algorithm, XGBoost（eXtreme Gradient Boosting）, elastic regression, linear regression and AdaBoost（Adaptive Boosting）. By optimizing the parameters, the determination coefficients R² of XGBoost endpoint slag composition prediction model is all above 0.8.The slag splashing time model was modeled using five algorithms: SVR（Support Vector Regression）, LGBM（Light Gradient Boosting Machine）, GBDT（Gradient Boosting Decision Tree）, RF（Random Forest） and XGBoost, respectively. Then, the integrated slag splashing time model was obtained by integrating SVR, XGBoost and GBDT. Stacking integrated slag splashing time model improves the prediction effect of each single model, and the prediction hit rate is 89.95 % in the error range of ±20 s.更多还原