Artificial intelligence techniques have been used to predict basic oxygen furnace(BOF) end-points. However,the main challenge is to effectively reduce the input nodes as too many input nodes in neural network increase...Artificial intelligence techniques have been used to predict basic oxygen furnace(BOF) end-points. However,the main challenge is to effectively reduce the input nodes as too many input nodes in neural network increase complexity,decrease accuracy and slow down the training speed of the network.Simply picking-up variables as input usually influence validity of model.It is quite necessary to develop an effective method to reduce the number of input nodes whereby to simplify the network and improve model performance.In this study,a variable-filtrating technique combining both metallurgical mechanism model and partial least-squares(PLS ) regression method has been proposed by taking the advantages of both of them,i.e.qualitive and quantative relationships between variables respectively.Accordingly,a fuzzy-reasoning neural network(FNN) prediction model for basic oxygen furnace(BOF) end-point carbon content based on this technique has been developed.The prediction results showed that this model can effectively improve the hit rate of end-point carbon content and increase network training speed.The successful hit rate of the model can reach up to 94.12%with about 0.02% error range.展开更多
This paper reports a new method of titration for very weak acids and bases using the appearance of incisions on oscillopolarogram to indicate the end-point.This method has the advantages of rapidity,simplicity,no indi...This paper reports a new method of titration for very weak acids and bases using the appearance of incisions on oscillopolarogram to indicate the end-point.This method has the advantages of rapidity,simplicity,no indicator needed as well as good precision.展开更多
The ^(nat)Mo(γ,xnp)^(95m,g)Nb photonuclear reaction was studied using the electron beam from the NSC KIPT linear accelerator LUE-40.The experiment was performed using the activation and off-line γ-ray spectrometric ...The ^(nat)Mo(γ,xnp)^(95m,g)Nb photonuclear reaction was studied using the electron beam from the NSC KIPT linear accelerator LUE-40.The experiment was performed using the activation and off-line γ-ray spectrometric technique.The experimental isomeric yield ratio(IR) was determined for the reaction products ^(95m,g)Nb at the bremsstrahlung end-point energy E_(γmax) range of 38-93 MeV.The obtained values of IR are in satisfactory agreement with the results of other studies and extend the range of previously known data.The theoretical values of the yields Y_(m,g)(E_(γmax)) and the IR for the isomeric pair ^(95m,g)Nb from the ^(nat)Mo(γ,xnp) reaction were calculated using the partial cross-sections σ(E) from the TALYS1.95 code for six different level density models.For the investigated range of E_(γmax),the theoretical dependence of IR on energy was confirmed-the IR smoothly increases with increasing energy.The comparison showed a noticeable difference(more than 3.85 times) in the experimental IR relative to all theoretical estimates.展开更多
Dephosphorization is essential content in the steelmaking process,and the process after the converter has no dephosphorization function.Therefore,phosphorus must be removed to the required level in the converter proce...Dephosphorization is essential content in the steelmaking process,and the process after the converter has no dephosphorization function.Therefore,phosphorus must be removed to the required level in the converter process.In order to better control the end-point phosphorus content of basic oxygen furnace(BOF),a prediction model of end-point phosphorus content for BOF based on monotone-constrained backpropagation(BP)neural network was established.Through the theoretical analysis of the dephosphorization process,ten factors that affect the end-point phosphorus content were determined as the input variables of the model.The correlations between influencing factors and end-point phosphorus content were determined as the constraint condition of the model.200 sets of data were used to verify the accuracy of the model,and the hit ratios in the range of±0.005%and±0.003%are 94%and 74%,respectively.The fit coefficient of determination of the predicted value and the actual value is 0.8456,and the root-mean-square error is 0.0030;the predictive accuracy is better than that of ordinary BP neural network,and this model has good interpretability.It can provide useful reference for real production and also provide a new approach for metallurgical predictive modeling.展开更多
In order to improve the end-point hit rate of basic oxygen furnace steelmaking,a novel dynamic control model was proposed based on an improved twin support vector regression algorithm.The controlled objects were the e...In order to improve the end-point hit rate of basic oxygen furnace steelmaking,a novel dynamic control model was proposed based on an improved twin support vector regression algorithm.The controlled objects were the end-point carbon content and temperature.The proposed control model was established by using the low carbon steel samples collected from a steel plant,which consists of two prediction models,a preprocess model,two regulation units,a controller and a basic oxygen furnace.The test results of 100 heats show that the prediction models can achieve a double hit rate of 90%within the error bound of 0.005 wt.%C and 15℃.The preprocess model was used to predict an initial end-blow oxygen volume.However,the double hit rate of the carbon con tent and temperature only achieves 65%.Then,the oxygen volume and coolant additi ons were adjusted by the regulation units to improve the hit rate.Finally,the double hit rate after the regulation is reached up to 90%.The results indicate that the proposed dynamic control model is efficient to guide the real production for low carbon steel,and the modeling method is also suitable for the applications of other steel grades.展开更多
文摘Artificial intelligence techniques have been used to predict basic oxygen furnace(BOF) end-points. However,the main challenge is to effectively reduce the input nodes as too many input nodes in neural network increase complexity,decrease accuracy and slow down the training speed of the network.Simply picking-up variables as input usually influence validity of model.It is quite necessary to develop an effective method to reduce the number of input nodes whereby to simplify the network and improve model performance.In this study,a variable-filtrating technique combining both metallurgical mechanism model and partial least-squares(PLS ) regression method has been proposed by taking the advantages of both of them,i.e.qualitive and quantative relationships between variables respectively.Accordingly,a fuzzy-reasoning neural network(FNN) prediction model for basic oxygen furnace(BOF) end-point carbon content based on this technique has been developed.The prediction results showed that this model can effectively improve the hit rate of end-point carbon content and increase network training speed.The successful hit rate of the model can reach up to 94.12%with about 0.02% error range.
文摘This paper reports a new method of titration for very weak acids and bases using the appearance of incisions on oscillopolarogram to indicate the end-point.This method has the advantages of rapidity,simplicity,no indicator needed as well as good precision.
文摘The ^(nat)Mo(γ,xnp)^(95m,g)Nb photonuclear reaction was studied using the electron beam from the NSC KIPT linear accelerator LUE-40.The experiment was performed using the activation and off-line γ-ray spectrometric technique.The experimental isomeric yield ratio(IR) was determined for the reaction products ^(95m,g)Nb at the bremsstrahlung end-point energy E_(γmax) range of 38-93 MeV.The obtained values of IR are in satisfactory agreement with the results of other studies and extend the range of previously known data.The theoretical values of the yields Y_(m,g)(E_(γmax)) and the IR for the isomeric pair ^(95m,g)Nb from the ^(nat)Mo(γ,xnp) reaction were calculated using the partial cross-sections σ(E) from the TALYS1.95 code for six different level density models.For the investigated range of E_(γmax),the theoretical dependence of IR on energy was confirmed-the IR smoothly increases with increasing energy.The comparison showed a noticeable difference(more than 3.85 times) in the experimental IR relative to all theoretical estimates.
基金supported by the National Natural Science Foundation of China(No.51974023)Key R&D Program Projects in Jiangxi Province(20171ACE50020).
文摘Dephosphorization is essential content in the steelmaking process,and the process after the converter has no dephosphorization function.Therefore,phosphorus must be removed to the required level in the converter process.In order to better control the end-point phosphorus content of basic oxygen furnace(BOF),a prediction model of end-point phosphorus content for BOF based on monotone-constrained backpropagation(BP)neural network was established.Through the theoretical analysis of the dephosphorization process,ten factors that affect the end-point phosphorus content were determined as the input variables of the model.The correlations between influencing factors and end-point phosphorus content were determined as the constraint condition of the model.200 sets of data were used to verify the accuracy of the model,and the hit ratios in the range of±0.005%and±0.003%are 94%and 74%,respectively.The fit coefficient of determination of the predicted value and the actual value is 0.8456,and the root-mean-square error is 0.0030;the predictive accuracy is better than that of ordinary BP neural network,and this model has good interpretability.It can provide useful reference for real production and also provide a new approach for metallurgical predictive modeling.
基金This work was supported by Liaoning Province PhD Start-up Fund(No.201601291)Liaoning Province Ministry of Education Scientific Study Project(No.2O17LNQN11).
文摘In order to improve the end-point hit rate of basic oxygen furnace steelmaking,a novel dynamic control model was proposed based on an improved twin support vector regression algorithm.The controlled objects were the end-point carbon content and temperature.The proposed control model was established by using the low carbon steel samples collected from a steel plant,which consists of two prediction models,a preprocess model,two regulation units,a controller and a basic oxygen furnace.The test results of 100 heats show that the prediction models can achieve a double hit rate of 90%within the error bound of 0.005 wt.%C and 15℃.The preprocess model was used to predict an initial end-blow oxygen volume.However,the double hit rate of the carbon con tent and temperature only achieves 65%.Then,the oxygen volume and coolant additi ons were adjusted by the regulation units to improve the hit rate.Finally,the double hit rate after the regulation is reached up to 90%.The results indicate that the proposed dynamic control model is efficient to guide the real production for low carbon steel,and the modeling method is also suitable for the applications of other steel grades.