Accurate prediction of molten steel temperature in the ladle furnace(LF)refining process has an important influence on the quality of molten steel and the control of steelmaking cost.Extensive research on establishing...Accurate prediction of molten steel temperature in the ladle furnace(LF)refining process has an important influence on the quality of molten steel and the control of steelmaking cost.Extensive research on establishing models to predict molten steel temperature has been conducted.However,most researchers focus solely on improving the accuracy of the model,neglecting its explainability.The present study aims to develop a high-precision and explainable model with improved reliability and transparency.The eXtreme gradient boosting(XGBoost)and light gradient boosting machine(LGBM)were utilized,along with bayesian optimization and grey wolf optimiz-ation(GWO),to establish the prediction model.Different performance evaluation metrics and graphical representations were applied to compare the optimal XGBoost and LGBM models obtained through varying hyperparameter optimization methods with the other models.The findings indicated that the GWO-LGBM model outperformed other methods in predicting molten steel temperature,with a high pre-diction accuracy of 89.35%within the error range of±5°C.The model’s learning/decision process was revealed,and the influence degree of different variables on the molten steel temperature was clarified using the tree structure visualization and SHapley Additive exPlana-tions(SHAP)analysis.Consequently,the explainability of the optimal GWO-LGBM model was enhanced,providing reliable support for prediction results.展开更多
This article discusses and analyzes the law of nitrogen increase in liquid steel and the main factors affect-ing the nitrogen increasing of molten steel,through the way of adding nitrogen to molten steel by bottom blo...This article discusses and analyzes the law of nitrogen increase in liquid steel and the main factors affect-ing the nitrogen increasing of molten steel,through the way of adding nitrogen to molten steel by bottom blowing nitrogen gas in LF refining process.It is considered that the main factors affecting the nitrogen increasing instability of molten steel are the initial temperature of LF refining,nitrogen relative element,surface active elements[O]and[S]of steel liquid,and bottom blowing rate of ladle.The large-scale production practice shows that T[O]not more than 50×10-6 and[S]is not more than 0.020 in LF refining at the initial temperature of not less than 1570.The liquid steel nitrogen enrichment test is carried out by ladle bottom blowing nitrogen gas after 20 min of refining,the flow rate is set as(6.0~7.0)NL/min per ton,and it is turned to 2 NL/min at 6 min before the end of refining,the nitrogen increasing rate of liquid steel is basically stable at(5~6)×10-6 per minute.展开更多
In the prediction of the end-point molten steel temperature of the ladle furnace, the influence of some factors is nonlinear. The prediction accuracy will be affected by directly inputting these nonlinear factors into...In the prediction of the end-point molten steel temperature of the ladle furnace, the influence of some factors is nonlinear. The prediction accuracy will be affected by directly inputting these nonlinear factors into the data-driven model. To solve this problem, an improved case-based reasoning model based on heat transfer calculation(CBR-HTC) was established through the nonlinear processing of these factors with software Ansys. The results showed that the CBR-HTC model improves the prediction accuracy of end-point molten steel temperature by5.33% and 7.00% compared with the original CBR model and 6.66% and 5.33% compared with the back propagation neural network(BPNN)model in the ranges of [-3, 3] and [-7, 7], respectively. It was found that the mean absolute error(MAE) and root-mean-square error(RMSE)values of the CBR-HTC model are also lower. It was verified that the prediction accuracy of the data-driven model can be improved by combining the mechanism model with the data-driven model.展开更多
以我国某钢厂120 t LF精炼炉为研究对象,通过建立由冶炼机理模型和XGBoost模型相结合的混合模型,预测LF精炼过程中的钢水成分并进行实际应用。结果表明,模型预测终点碳、硅、锰、铝等元素均处于内控范围内,并平均减少了每炉钢取样工序0....以我国某钢厂120 t LF精炼炉为研究对象,通过建立由冶炼机理模型和XGBoost模型相结合的混合模型,预测LF精炼过程中的钢水成分并进行实际应用。结果表明,模型预测终点碳、硅、锰、铝等元素均处于内控范围内,并平均减少了每炉钢取样工序0.8次,提高了生产效率。展开更多
The factors restricting the life of the refining furnace cover were introduced,including the airflow erosion of the refining dust removal system,the melting loss caused by the arc radiation of the electrode,the chemic...The factors restricting the life of the refining furnace cover were introduced,including the airflow erosion of the refining dust removal system,the melting loss caused by the arc radiation of the electrode,the chemical erosion and penetration of slag and gas,and the condition of refining slag.The improvement measures are adjusting the material of the small furnace cover from corundum to chrome corundum,using a large shaking table to vibrate,optimizing the size design of the small furnace cover,and appropriately thickening the weak areas in the triangular area.The average service life of the refining furnace cover has been increased from one week to two months,reaching 4 maintenance cycles,which meets the needs of the refining production.展开更多
针对LF精炼炉钢液温度控制过度依赖人工经验的问题,马钢长材事业部以120 t LF精炼炉为研究对象,基于能量平衡原理,计算分析LF精炼过程中输入电能、合金化、炉渣热效应、钢包内衬散热、渣面辐射、吹氩搅拌和烟气热损失等热量对钢液温度...针对LF精炼炉钢液温度控制过度依赖人工经验的问题,马钢长材事业部以120 t LF精炼炉为研究对象,基于能量平衡原理,计算分析LF精炼过程中输入电能、合金化、炉渣热效应、钢包内衬散热、渣面辐射、吹氩搅拌和烟气热损失等热量对钢液温度的影响,建立LF精炼钢液温度的预测模型。经过跟踪实际生产试验、测温校正并优化模型,使模型取得了良好的应用效果。模型预测温度与实际测量值偏差绝对值≤5℃的比例为97.73%,偏差绝对值≤6℃的比例为100%。展开更多
针对LF精炼操作对人工经验过度依赖的问题,马鞍山钢铁有限公司长材事业部基于冶金机理,在120 t LF上开发了温度模型、合金模型、吹氩模型和造渣模型,建立以钢水温度、成分、炉渣三者相互统一的控制模型,利用大数据技术和自学习功能对控...针对LF精炼操作对人工经验过度依赖的问题,马鞍山钢铁有限公司长材事业部基于冶金机理,在120 t LF上开发了温度模型、合金模型、吹氩模型和造渣模型,建立以钢水温度、成分、炉渣三者相互统一的控制模型,利用大数据技术和自学习功能对控制模型进行优化,实现了各模型协同集成和LF智能控制,取得了良好的应用效果,LF自动控制比例达到80%,终点目标温度±5℃命中率达95%以上,终点成分窄范围命中率(w(Si)±0.02%、w(Mn)±0.02%、w(S)±0.001%、w(Al s)±0.005%)达97%以上,降低LF精炼电耗约4 kWh/t、减少精炼处理时间约5 min,提高了生产效率和钢水质量,对炼钢工序降本增效起到了重要作用。展开更多
基金financially supported by the National Natural Science Foundation of China(Nos.51974023 and 52374321)the funding of State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing(No.41621005)the Youth Science and Technology Innovation Fund of Jianlong Group-University of Science and Technology Beijing(No.20231235).
文摘Accurate prediction of molten steel temperature in the ladle furnace(LF)refining process has an important influence on the quality of molten steel and the control of steelmaking cost.Extensive research on establishing models to predict molten steel temperature has been conducted.However,most researchers focus solely on improving the accuracy of the model,neglecting its explainability.The present study aims to develop a high-precision and explainable model with improved reliability and transparency.The eXtreme gradient boosting(XGBoost)and light gradient boosting machine(LGBM)were utilized,along with bayesian optimization and grey wolf optimiz-ation(GWO),to establish the prediction model.Different performance evaluation metrics and graphical representations were applied to compare the optimal XGBoost and LGBM models obtained through varying hyperparameter optimization methods with the other models.The findings indicated that the GWO-LGBM model outperformed other methods in predicting molten steel temperature,with a high pre-diction accuracy of 89.35%within the error range of±5°C.The model’s learning/decision process was revealed,and the influence degree of different variables on the molten steel temperature was clarified using the tree structure visualization and SHapley Additive exPlana-tions(SHAP)analysis.Consequently,the explainability of the optimal GWO-LGBM model was enhanced,providing reliable support for prediction results.
文摘This article discusses and analyzes the law of nitrogen increase in liquid steel and the main factors affect-ing the nitrogen increasing of molten steel,through the way of adding nitrogen to molten steel by bottom blowing nitrogen gas in LF refining process.It is considered that the main factors affecting the nitrogen increasing instability of molten steel are the initial temperature of LF refining,nitrogen relative element,surface active elements[O]and[S]of steel liquid,and bottom blowing rate of ladle.The large-scale production practice shows that T[O]not more than 50×10-6 and[S]is not more than 0.020 in LF refining at the initial temperature of not less than 1570.The liquid steel nitrogen enrichment test is carried out by ladle bottom blowing nitrogen gas after 20 min of refining,the flow rate is set as(6.0~7.0)NL/min per ton,and it is turned to 2 NL/min at 6 min before the end of refining,the nitrogen increasing rate of liquid steel is basically stable at(5~6)×10-6 per minute.
基金financially supported by the National Natural Science Foundation of China (No.51674030)the Fundamental Research Funds for the Central Universities (Nos.FRF-TP-18-097A1 and FRF-BD-19-022A)。
文摘In the prediction of the end-point molten steel temperature of the ladle furnace, the influence of some factors is nonlinear. The prediction accuracy will be affected by directly inputting these nonlinear factors into the data-driven model. To solve this problem, an improved case-based reasoning model based on heat transfer calculation(CBR-HTC) was established through the nonlinear processing of these factors with software Ansys. The results showed that the CBR-HTC model improves the prediction accuracy of end-point molten steel temperature by5.33% and 7.00% compared with the original CBR model and 6.66% and 5.33% compared with the back propagation neural network(BPNN)model in the ranges of [-3, 3] and [-7, 7], respectively. It was found that the mean absolute error(MAE) and root-mean-square error(RMSE)values of the CBR-HTC model are also lower. It was verified that the prediction accuracy of the data-driven model can be improved by combining the mechanism model with the data-driven model.
文摘The factors restricting the life of the refining furnace cover were introduced,including the airflow erosion of the refining dust removal system,the melting loss caused by the arc radiation of the electrode,the chemical erosion and penetration of slag and gas,and the condition of refining slag.The improvement measures are adjusting the material of the small furnace cover from corundum to chrome corundum,using a large shaking table to vibrate,optimizing the size design of the small furnace cover,and appropriately thickening the weak areas in the triangular area.The average service life of the refining furnace cover has been increased from one week to two months,reaching 4 maintenance cycles,which meets the needs of the refining production.
文摘针对LF精炼炉钢液温度控制过度依赖人工经验的问题,马钢长材事业部以120 t LF精炼炉为研究对象,基于能量平衡原理,计算分析LF精炼过程中输入电能、合金化、炉渣热效应、钢包内衬散热、渣面辐射、吹氩搅拌和烟气热损失等热量对钢液温度的影响,建立LF精炼钢液温度的预测模型。经过跟踪实际生产试验、测温校正并优化模型,使模型取得了良好的应用效果。模型预测温度与实际测量值偏差绝对值≤5℃的比例为97.73%,偏差绝对值≤6℃的比例为100%。
