Study on Productive Process Model Basic Oxygen Furnace Steelmaking Based on RBF Neural Network

The endpoint temperature and carbon content of basic oxygen furnace (BOF) are the control of the BOF steelmaking process. There exists a complex relationship among them and each control variable. While the multiple linear model is limited to predict the endpoint temperature and carbon content through each control variable, and the online continue measurement can’t be made. So the predictive model of some control variables of the BOF steelmaking based on RBF neural network was put forward, and the study of verifying model was made by comparing the predictive value with the practical data of 89 converters in a factory. It turned out that the method has high accurate prediction, and it can be used in the process of prediction in steel enterprises.