Method for Dynamic Prediction of Oxygen Demand in Steelmaking Process Based on BOF Technology

Oxygen is an important energy medium in the steelmaking process. The accurate dynamic prediction of oxygen demand is needed to guarantee molten steel quality, improve the production rhythm, and promote the collaborative optimization of production and energy. In this work, a analysis of the mechanism and of industrial big data was undertaken, and we found that the characteristic factors of Basic Oxygen Furnace (BOF) oxygen consumption were different in different modes, such as duplex dephosphorization, duplex decarbonization, and the traditional mode. Based on this, a dynamic-prediction modeling method for BOF oxygen demand considering mode classification is proposed. According to the characteristics of BOF production organization, a control module based on dynamic adaptions of the production plan was researched to realize the recalculation of the model predictions. A simulation test on industrial data revealed that the average relative error of the model in each BOF mode was less than 5% and the mean absolute error was about 450 m(3). Moreover, an accurate 30-minute-in-advance prediction of dynamic oxygen demand was realized. This paper provides the method support and basis for the long-term demand planning of the static balance and the short-term real-time scheduling of the dynamic balance of oxygen.

Automated summary

In this study, an analysis of the mechanism and industrial big data was conducted to identify the characteristic factors of Basic Oxygen Furnace (BOF) oxygen consumption in different modes. Based on this, a dynamic-prediction modeling method for BOF oxygen demand considering mode classification was proposed. A control module based on dynamic adaptions of the production plan was researched to achieve the recalculation of model predictions. The simulation test on industrial data demonstrated the accuracy of the model in predicting dynamic oxygen demand and provided a basis for demand planning and real-time scheduling.