Research On BOF Steelmaking Endpoint Prediction And Control Model

With the development of our country socialist market economy,the iron and steel enterprises in the development of the national economy plays a more and more important position.BOF is a key process to steel production,whose task is smelting steel that meets the desired requirements about the temperature and various components.Because the temperature of molten steel can be measured continuously,and the boundary condition of smelting process is very complex,the terminal control of smelting process is difficult to achieve.In the actual production process,it is hard to control the carbon and temperature precisely,it is very necessary to improve the terminal control efficiency of BOF.In the meantime,because the process of BOF is a very complex physical and chemical processes with multi-component multi-phase and high temperature,whose mechanism about the input and output is nonlinear seriously and not very clear,the conventional modeling methods are difficult to meet the production requirements.Therefore,it is necessary to study the model and control for the BOF based on the neural network.The thesis first introduces the principle and equipment and the overview and status about terminal control technology of BOF briefly.Secondly,the neural network and several predicting methods of terminal model of BOF by using the neural network are introduced briefly.Thirdly,the result that the Levenberg-Marquardt(LM)method has fast convergence and good learning performance is got by summarizing and comparing features between several BP algorithms.Finally,Establish the neural network forecast and control model based on LM for BOF.In this thesis the modeling method is mainly based on neural network theory.The actual data of continuous 100 batches from Shouqin Company steel departmental are chosen as example,input parameter including the carbon content and terminal temperature.Establish three-layers BP prediction neural networks,endpoint various and steel temperature content.The model of endpoint various and steel temperature prediction have established.On the basis of this,the method based on BP neural network is proposed so as to determine the blown oxygen and auxiliary raw materials.The modeling study showed the method is effective and can be used in practical process for steel production.