Splashing behavior of metal droplets is one of the main phenomena in basic oxygen furnace steelmaking process.The size distribution of metal droplets and the residence time of the metal droplets in the slag have impor...Splashing behavior of metal droplets is one of the main phenomena in basic oxygen furnace steelmaking process.The size distribution of metal droplets and the residence time of the metal droplets in the slag have important effects on the kinetics of the metal–slag reactions.The particle size distribution law,characteristic diameter,splashing velocity and splashing angle of metal droplets were investigated,and an improved prediction model of trajectory and residence time for metal droplets was established based on the combination of expanded droplets theory,decarburization mechanism model and ballistic motion principle.Meanwhile,the trajectory and residence time of metal droplets under different working conditions were analyzed based on this model.The results illustrate that the metal droplets with larger particle size are produced at low lance distance,while the metal droplets with smaller particle size are produced at high lance distance.There is a significant linear relationship between the three diameters(maximum droplet diameter,distribution characteristic diameter,reaction characteristic diameter)and the blowing number.The residence time of decarbonized metal droplets in slag is about 0.2–73 s.Meanwhile,the initial carbon content and diameter of the metal droplets and the FeO content of slag are the main factors affecting the motion state of the metal droplets in the slag,while the splashing velocity,splashing angle and the height of the foam slag have little influence.This model can be used to predict the trajectory and residence time of decarburized metal droplets in a variety of complex multiphase slag conditions,overcoming the limitation that the known model is only applicable to a few specific conditions.展开更多
To predict the endpoint carbon content and temperature in basic oxygen furnace (BOF), the industrial parameters of BOF steelmaking are taken as input values. Firstly, a series of preprocessing works such as the Pauta ...To predict the endpoint carbon content and temperature in basic oxygen furnace (BOF), the industrial parameters of BOF steelmaking are taken as input values. Firstly, a series of preprocessing works such as the Pauta criterion, hierarchical clustering, and principal component analysis on the original data were performed. Secondly, the prediction results of classic machine learning models of ridge regression, support vector machine, gradient boosting regression (GBR), random forest regression, back-propagation (BP) neural network models, and multi-layer perceptron (MLP) were compared before and after data preprocessing. An improved model was established based on the improved sparrow algorithm and BP using tent chaotic mapping (CSSA-BP). The CSSA-BP model showed the best performance for endpoint carbon prediction with the lowest mean absolute error (MAE) and root mean square error (RMSE) values of 0.01124 and 0.01345 mass% among seven models, respectively. And the lowest MAE and RMSE values of 8.9839 and 10.9321 ℃ for endpoint temperature prediction were obtained among seven models, respectively. Furthermore, the CSSA-BP and GBR models have the smallest error fluctuation range in both endpoint carbon content and temperature predictions. Finally, in order to improve the interpretability of the model, SHapley additive interpretation (SHAP) was used to analyze the results.展开更多
A 1∶8 physical water model was constructed to investigate the fluid flow and mixing phenomena in the basic oxygen furnace(BOF)converter.The particle image velocimetry was employed to measure the velocity distribution...A 1∶8 physical water model was constructed to investigate the fluid flow and mixing phenomena in the basic oxygen furnace(BOF)converter.The particle image velocimetry was employed to measure the velocity distribution of the bath and the high-speed camera was applied to capture the cavity shape in the combined blowing BOF converter.The mixing time for varied operating conditions was measured by the stimulus-response approach.The cavity depth increased with the decrease in the lance height and the increase in the top gas flow rate while the bottom blowing gas had little influence on the cavity depth.The minimum cavity depth was obtained under the condition of a 69.8 m^(3)/h top gas flow rate,a 287.5 mm lance height and a 0.93 m^(3)/h bottom blowing gas flow rate,which was 161.2 mm.The mixing time decreased as the lance height decreased and the top blowing gas flow rate increased.The mixing time was first decreased and then increased with the increase in the bottom gas flow rate.With the condition of 69.8 m^(3)/h gas flow rate of top blowing,the 287.5 mm lance height and the 0.93 m^(3)/h gas flow rate of bottom blowing,the mixing time in the converter was 48.65 s.The empirical formula between the stirring power and the mixing time in the converter was calculated.展开更多
Mathematical(data-driven)models based on state-of-the-art(SOTA)machine learning and deep learning models and data collected from 12,786 heats were established to predict the values of temperature,sample,and carbon(TSC...Mathematical(data-driven)models based on state-of-the-art(SOTA)machine learning and deep learning models and data collected from 12,786 heats were established to predict the values of temperature,sample,and carbon(TSC)test,including temperature of molten steel(TSC-Temp),carbon content(TSC-C)and phosphorus content(TSC-P),which made prepa-ration for eliminating the TSC test.To maximize the prediction accuracy of the proposed approach,various models with different inputs were implemented and compared,and the best models were applied to the production process of a Hesteel Group steelmaking plant in China in the field.The number of tabular features(hot metal information,scrap,additives,blowing practices,and preset values)was expanded,and time series(off-gas profiles and blowing practice curves)that could reflect the entire steelmaking process were introduced as inputs.First,the latest machine learning models(LightGBM,CatBoost,TabNet,and NODE)were used to make predictions with tabular features,and the best coefficient of determination R^(2)values obtained for TSC-P,TSC-C and TSC-Temp predictions were 0.435(LightGBM),0.857(Cat-Boost)and 0.678(LightGBM),respectively,which were higher than those of classic models(backpropagation and support vector machine).Then,making predictions was performed by using SOTA time series regression models(SCINet,DLinear,Informer,and MLSTM-FCN)with original time series,SOTA image regression models(NesT,CaiT,ResNeXt,and GoogLeNet)with resized time series,and the proposed Concatenate-Model and Parallel-Model with both tabular features and time series.Through optimization and comparisons,it was finally determined that the Concatenate-Model with MLSTM-FCN,SCINet and Informer as feature extractors performed the best,and its R^(2)values for predicting TSC-P,TSC-C and TSC-Temp reached 0.470,0.858 and 0.710,respectively.Its field test accuracies for TSC-P,TSC-C and TSC-Temp were 0.459,0.850 and 0.685,respectively.A related importance analysis was carried out,and dynamic control methods based on prediction values were proposed.展开更多
采用文献计量方法,对2000～2009年Web of ScienceSCIE数据库收录湿地研究的文献进行分析,探讨了湿地研究的年代分布、期刊分布、语种、文献类型、学科分布及排名前10位的国家和机构,以期了解世界各国在这一研究领域的进展情况,并为专业...采用文献计量方法,对2000～2009年Web of ScienceSCIE数据库收录湿地研究的文献进行分析,探讨了湿地研究的年代分布、期刊分布、语种、文献类型、学科分布及排名前10位的国家和机构,以期了解世界各国在这一研究领域的进展情况,并为专业研究人员提供信息参考。展开更多
基金funded by the National Natural Science Foundation of China(Nos.52374321 and 51974023)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Splashing behavior of metal droplets is one of the main phenomena in basic oxygen furnace steelmaking process.The size distribution of metal droplets and the residence time of the metal droplets in the slag have important effects on the kinetics of the metal–slag reactions.The particle size distribution law,characteristic diameter,splashing velocity and splashing angle of metal droplets were investigated,and an improved prediction model of trajectory and residence time for metal droplets was established based on the combination of expanded droplets theory,decarburization mechanism model and ballistic motion principle.Meanwhile,the trajectory and residence time of metal droplets under different working conditions were analyzed based on this model.The results illustrate that the metal droplets with larger particle size are produced at low lance distance,while the metal droplets with smaller particle size are produced at high lance distance.There is a significant linear relationship between the three diameters(maximum droplet diameter,distribution characteristic diameter,reaction characteristic diameter)and the blowing number.The residence time of decarbonized metal droplets in slag is about 0.2–73 s.Meanwhile,the initial carbon content and diameter of the metal droplets and the FeO content of slag are the main factors affecting the motion state of the metal droplets in the slag,while the splashing velocity,splashing angle and the height of the foam slag have little influence.This model can be used to predict the trajectory and residence time of decarburized metal droplets in a variety of complex multiphase slag conditions,overcoming the limitation that the known model is only applicable to a few specific conditions.
基金supported by the National Natural Science Foundation of China(Grant No.U1960202)the Science and Technology Commission of Shanghai Municipality(No.19DZ2270200).
文摘To predict the endpoint carbon content and temperature in basic oxygen furnace (BOF), the industrial parameters of BOF steelmaking are taken as input values. Firstly, a series of preprocessing works such as the Pauta criterion, hierarchical clustering, and principal component analysis on the original data were performed. Secondly, the prediction results of classic machine learning models of ridge regression, support vector machine, gradient boosting regression (GBR), random forest regression, back-propagation (BP) neural network models, and multi-layer perceptron (MLP) were compared before and after data preprocessing. An improved model was established based on the improved sparrow algorithm and BP using tent chaotic mapping (CSSA-BP). The CSSA-BP model showed the best performance for endpoint carbon prediction with the lowest mean absolute error (MAE) and root mean square error (RMSE) values of 0.01124 and 0.01345 mass% among seven models, respectively. And the lowest MAE and RMSE values of 8.9839 and 10.9321 ℃ for endpoint temperature prediction were obtained among seven models, respectively. Furthermore, the CSSA-BP and GBR models have the smallest error fluctuation range in both endpoint carbon content and temperature predictions. Finally, in order to improve the interpretability of the model, SHapley additive interpretation (SHAP) was used to analyze the results.
基金support from the National Natural Science Foundation of China(U22A20171)the High Steel Center(HSC)at North China University of Technology and University of Science and Technology Beijing,China.
文摘A 1∶8 physical water model was constructed to investigate the fluid flow and mixing phenomena in the basic oxygen furnace(BOF)converter.The particle image velocimetry was employed to measure the velocity distribution of the bath and the high-speed camera was applied to capture the cavity shape in the combined blowing BOF converter.The mixing time for varied operating conditions was measured by the stimulus-response approach.The cavity depth increased with the decrease in the lance height and the increase in the top gas flow rate while the bottom blowing gas had little influence on the cavity depth.The minimum cavity depth was obtained under the condition of a 69.8 m^(3)/h top gas flow rate,a 287.5 mm lance height and a 0.93 m^(3)/h bottom blowing gas flow rate,which was 161.2 mm.The mixing time decreased as the lance height decreased and the top blowing gas flow rate increased.The mixing time was first decreased and then increased with the increase in the bottom gas flow rate.With the condition of 69.8 m^(3)/h gas flow rate of top blowing,the 287.5 mm lance height and the 0.93 m^(3)/h gas flow rate of bottom blowing,the mixing time in the converter was 48.65 s.The empirical formula between the stirring power and the mixing time in the converter was calculated.
基金This research has been supported by the Natural Science Foundation of Hebei Province,China(E2022318002).Thanks are given to Tangsteel Co.,Ltd.of Hesteel Group and Digital Co.,Ltd.of Hesteel Group for providing detailed data,hardware and software support for model development and field production test.
文摘Mathematical(data-driven)models based on state-of-the-art(SOTA)machine learning and deep learning models and data collected from 12,786 heats were established to predict the values of temperature,sample,and carbon(TSC)test,including temperature of molten steel(TSC-Temp),carbon content(TSC-C)and phosphorus content(TSC-P),which made prepa-ration for eliminating the TSC test.To maximize the prediction accuracy of the proposed approach,various models with different inputs were implemented and compared,and the best models were applied to the production process of a Hesteel Group steelmaking plant in China in the field.The number of tabular features(hot metal information,scrap,additives,blowing practices,and preset values)was expanded,and time series(off-gas profiles and blowing practice curves)that could reflect the entire steelmaking process were introduced as inputs.First,the latest machine learning models(LightGBM,CatBoost,TabNet,and NODE)were used to make predictions with tabular features,and the best coefficient of determination R^(2)values obtained for TSC-P,TSC-C and TSC-Temp predictions were 0.435(LightGBM),0.857(Cat-Boost)and 0.678(LightGBM),respectively,which were higher than those of classic models(backpropagation and support vector machine).Then,making predictions was performed by using SOTA time series regression models(SCINet,DLinear,Informer,and MLSTM-FCN)with original time series,SOTA image regression models(NesT,CaiT,ResNeXt,and GoogLeNet)with resized time series,and the proposed Concatenate-Model and Parallel-Model with both tabular features and time series.Through optimization and comparisons,it was finally determined that the Concatenate-Model with MLSTM-FCN,SCINet and Informer as feature extractors performed the best,and its R^(2)values for predicting TSC-P,TSC-C and TSC-Temp reached 0.470,0.858 and 0.710,respectively.Its field test accuracies for TSC-P,TSC-C and TSC-Temp were 0.459,0.850 and 0.685,respectively.A related importance analysis was carried out,and dynamic control methods based on prediction values were proposed.
