Research And Implemation Of Temperature Prediction Model Of Molten Steel In LF And Alloy Model

Steel temperature is an important process index for steel-making. Because of high temperature and strong erosion from steel and slag,steel temperature is measured by point-measurement method with thermal couples ,continuous steel temperature information can not be obtained. It becomes a very urgent problem to establish a reasonable temperature system and accurately control molten steel temperature. It is an important premise to predict accurately the temperature of molten steel in LF for organizing production, improving steel quality, cutting down cost and controlling the steel water temperature. In this paper,back_ propagation neural network combined with Expert system is studied.The temperature model of molten steel in Ladle Furnace (LF) is established according to the production technique.The factors of influencing molten steel temperature of LF were deeply investigated during building up the model of BP network. See the whole steel the system as a system considering of the energy balance. Therefore, the factors used in model were confirmed as follows: the supplying power to heat molten steel, weight of molten steel, temperature of molten steel ,ages of molten steel, depth of slag, argon blowing quantity and stage .In this measurement method ,BP neural network model is used to predict the initial temperature trend,then an expert system is used to compensate the error caused in special conditions. Comparing with previous methods,the adaptation and accuracy of the steel temperature prediction have been improved. The anticipant result of application is that the number of furnace with the prediction error less then±5 degree is 85% of the total number.The alloy process of molten steel is a complex process. It is not only related to the quality of molten steel and the cost of alloy but also to the supplying power . Based on element yield, according to the formula of alloy added, alloy additions are accurately calculated, the quality ofmolten steel can be improved.The program was developed by C#. The software with the complete function and the friendly interface was built up. The software has the functions of data input, the temperature prediction etc.