Based on the temperature situation during the rolling process of 4200 mm/3500 mm medium and thick plates at Baosteel,this article analyzes the influencing factors of temperature changes during the rolling process from...Based on the temperature situation during the rolling process of 4200 mm/3500 mm medium and thick plates at Baosteel,this article analyzes the influencing factors of temperature changes during the rolling process from the perspective of heat transfer theory and the temperature change law during the rolling process.The temperature loss during the four rolling processes is tracked on site,and the temperature drop model parameters during the rolling process of 4200mm/3500mm medium and thick plates at Baosteel are quantitatively provided.It is applied to actual rolling production and has achieved good results.展开更多
This article briefly introduces the weighing device for steel billets in front of the heating furnace of the high-speed wire rod unit,and analyzes and summarizes the problems existing in the original weighing device f...This article briefly introduces the weighing device for steel billets in front of the heating furnace of the high-speed wire rod unit,and analyzes and summarizes the problems existing in the original weighing device for steel billets in production and use.Based on on-site installation conditions,design a new weighing method,match a large range weighing sensor,upgrade the automation control of the weighing device,and remotely transmit the billet weighing data to the MES system of the group.The automatic,stable,reliable,and accurate measurement of steel billet raw materials has been achieved,providing important guarantees for the accurate measurement of production line billet and product yield.展开更多
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
In order to realize the OY Smelting Furnace disposal of solid waste,municipal waste,form a model of steel enterprises and urban integration,through the production practice of smelting furnace,analyzes the mechanism of...In order to realize the OY Smelting Furnace disposal of solid waste,municipal waste,form a model of steel enterprises and urban integration,through the production practice of smelting furnace,analyzes the mechanism of solid waste disposal,and proposed the disposal of solid waste desulfurization agent and disposal method:According to the theory to guide the actual production process,the test ton of iron with 10-15kg of desulfurizer in the production process does not affect the quality of molten iron and slag quality.展开更多
Mathematical simulation was used for trouble-shooting and optimization. By the mathematical simulation, fluid flow and beat transfer of molten-steel in a four-strand tundish of a billet caster under different conditio...Mathematical simulation was used for trouble-shooting and optimization. By the mathematical simulation, fluid flow and beat transfer of molten-steel in a four-strand tundish of a billet caster under different conditions （bare tundish and tundish with flow control device） were analyzed, The results showed that （1） the tundish with flow control device （FCD） has an important effect on the fluid pattern and temperature distribution; （2） the unsteady, solving method was used to model the inclusion motions at different time perthds, and it showed that the FCD is advantageous to separate the nonmetallic inclusions. According to the simulation results, the main problem existing in the industry preduction was found, and some helpful rneasurements were executed. Consequently, the large nonmetallic inclusions were separated, and the content of total oxygen was reduced. The qualily of steel was greatly improved.展开更多
With the increasing demand for energy conservation and emission reduction,more attentions have been paid to the intelligentization,greenization and low carbonization during the transformation and upgrading of steelmak...With the increasing demand for energy conservation and emission reduction,more attentions have been paid to the intelligentization,greenization and low carbonization during the transformation and upgrading of steelmaking plants.Ladle furnace(LF)refining is one of the key procedures in steelmaking process and has been widely used in steelmaking plants for its high equipment matching degree,low equipment investment and outstanding refining performance.According to the main tasks of LF refining process,the modeling methods of temperature prediction model,slag-making model,alloying model,argon blowing model and model of inclusions behavior were systematically reviewed,and the advantages and disadvantages of each modeling method were summarized.In addition,the technical framework for the future has also been proposed based on existing works,including classification of raw materials,graphic representation of knowledge,introduction,upgradation and management of device/equipment,customization of steelmaking,modeling of refining process,synergy of models,intelligentization of decision-making,automation of control,and digitization of processes and operations,aiming to provide a reference for the modeling and intelligent development of LF refining process.展开更多
文摘Based on the temperature situation during the rolling process of 4200 mm/3500 mm medium and thick plates at Baosteel,this article analyzes the influencing factors of temperature changes during the rolling process from the perspective of heat transfer theory and the temperature change law during the rolling process.The temperature loss during the four rolling processes is tracked on site,and the temperature drop model parameters during the rolling process of 4200mm/3500mm medium and thick plates at Baosteel are quantitatively provided.It is applied to actual rolling production and has achieved good results.
文摘This article briefly introduces the weighing device for steel billets in front of the heating furnace of the high-speed wire rod unit,and analyzes and summarizes the problems existing in the original weighing device for steel billets in production and use.Based on on-site installation conditions,design a new weighing method,match a large range weighing sensor,upgrade the automation control of the weighing device,and remotely transmit the billet weighing data to the MES system of the group.The automatic,stable,reliable,and accurate measurement of steel billet raw materials has been achieved,providing important guarantees for the accurate measurement of production line billet and product yield.
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In order to realize the OY Smelting Furnace disposal of solid waste,municipal waste,form a model of steel enterprises and urban integration,through the production practice of smelting furnace,analyzes the mechanism of solid waste disposal,and proposed the disposal of solid waste desulfurization agent and disposal method:According to the theory to guide the actual production process,the test ton of iron with 10-15kg of desulfurizer in the production process does not affect the quality of molten iron and slag quality.
文摘Mathematical simulation was used for trouble-shooting and optimization. By the mathematical simulation, fluid flow and beat transfer of molten-steel in a four-strand tundish of a billet caster under different conditions （bare tundish and tundish with flow control device） were analyzed, The results showed that （1） the tundish with flow control device （FCD） has an important effect on the fluid pattern and temperature distribution; （2） the unsteady, solving method was used to model the inclusion motions at different time perthds, and it showed that the FCD is advantageous to separate the nonmetallic inclusions. According to the simulation results, the main problem existing in the industry preduction was found, and some helpful rneasurements were executed. Consequently, the large nonmetallic inclusions were separated, and the content of total oxygen was reduced. The qualily of steel was greatly improved.
基金funded by the National Natural Science Foundation of China(Grant Nos.50874014,51974023,52374321)the Program for New Century Excellent Talents in University(Grant No.NCET 07-0067)+1 种基金the Fundamental Research Funds for Central Universities(Grant No.FRF-BR-17-029A)the funding of State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing,China(Grant Nos.41620007 and 41621005).
文摘With the increasing demand for energy conservation and emission reduction,more attentions have been paid to the intelligentization,greenization and low carbonization during the transformation and upgrading of steelmaking plants.Ladle furnace(LF)refining is one of the key procedures in steelmaking process and has been widely used in steelmaking plants for its high equipment matching degree,low equipment investment and outstanding refining performance.According to the main tasks of LF refining process,the modeling methods of temperature prediction model,slag-making model,alloying model,argon blowing model and model of inclusions behavior were systematically reviewed,and the advantages and disadvantages of each modeling method were summarized.In addition,the technical framework for the future has also been proposed based on existing works,including classification of raw materials,graphic representation of knowledge,introduction,upgradation and management of device/equipment,customization of steelmaking,modeling of refining process,synergy of models,intelligentization of decision-making,automation of control,and digitization of processes and operations,aiming to provide a reference for the modeling and intelligent development of LF refining process.
