The Research On Sulfur Content Prediction Model For LF

With the development of automation in iron and steel industry, manual operation which is based on experience is not suitable for the renovation of steelmaking process. In order to achieve automatic control of the production process, it makes clear that the research of model building for LF is an indispensable direction in the field of LF research. The predictive model of terminal sulfur content for LF is proposed under this circumstance.In this paper, the desulphurization predictive model is established based on analyzing the principium of desulfurization in LF refining process. The main tasks are as follows:Firstly, the thesis makes a brief introduction about the present situation on desulphurization technology and the characteristics of different desulphurization technology in LF. Then it can be concluded that the selection of refining slag and differences in deoxy process cause different desulphurization technology.Secondly, thermodynamic principium and dynamic principium of desulphurization reaction are introduced. The mechanism model for prediction is established by calculating the values of sulfur capacity and oxygen activity. Besides, the effect of different parameters is summarized based on the mechanism model. Furthermore, the relations between the parameters and the percentage of sulfur removal are showed in the thesis by MATLAB simulating results.Thirdly, aiming at the imperfection of mechanism prediction model, hybrid prediction model which can be modified by actual data is brought forward, including mechanism model and error learning model(ELM). ELM can learn the rule that induces error between mechanism model predictive value and actual data.At last, hybrid prediction model is tested by actual data. It takes conclusion from simulation results that the hybrid prediction model is suitable for the prediction of terminal content of sulfur. Therefore, the research in the thesis is of practical value.