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
The first imported off-gas analysis system on 150 t BOF at Benxi Plates Co.Ltd. is presented and the continuous determination of bath carbon content has been studied. Thecomparison between the whole-course carbon inte...The first imported off-gas analysis system on 150 t BOF at Benxi Plates Co.Ltd. is presented and the continuous determination of bath carbon content has been studied. Thecomparison between the whole-course carbon integral model and the end-point carbon prediction modelhas been made. The results show that the regular change of CO, CO_2 and N_2 content in the off-gasduring blowing plays an important role in judging the smelting end-point of converter; the cubiccurve fitting model has a higher hit rate over 95 percent for the heats whose end-point carboncontent is lower than 0.10 percent with a precision of +-0.02 percent and has a large error for theheats whose end-point carbon content is more than 0.15 percent.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The first imported off-gas analysis system on 150 t BOF at Benxi Plates Co.Ltd. is presented and the continuous determination of bath carbon content has been studied. Thecomparison between the whole-course carbon integral model and the end-point carbon prediction modelhas been made. The results show that the regular change of CO, CO_2 and N_2 content in the off-gasduring blowing plays an important role in judging the smelting end-point of converter; the cubiccurve fitting model has a higher hit rate over 95 percent for the heats whose end-point carboncontent is lower than 0.10 percent with a precision of +-0.02 percent and has a large error for theheats whose end-point carbon content is more than 0.15 percent.
