Prediction model of Bum-through Point based on GA-BP

As one of the important links in the traditional long process steel production process, the sinter yield and quality of the sintering process directly affect the efficiency of ironmaking production. As an important index to detect the sintering production status, the sintering end point is very important for optimizing the production process and improving the product quality. Predicting the sintering end point can help the production planning and scheduling work, and make the production process more orderly and efficient. Accurate endpoint prediction helps to optimize production schedules and ensure the right raw materials and energy inputs to meet the quality requirements of a specific products. A prediction model of BTP based on GA-BP was proposed in this paper. Based on the production data of an iron and steel enterprise, the anomalies in the production data were processed. Then the genetic algorithm (GA) was used to set the initial value and threshold of the neural network (BP), and a GA-BP prediction model was designed. The results show that the prediction accuracy of the GA-BP model for the sintering end point can reach more than 95 %. The sintering prediction ability is further optimized, which effectively suppresses the fluctuation of the sintering end point, improves the calculation accuracy of the sintering end point, assists the field staff to adjust the operating parameters in advance, and stabilizes the sintering production. It has important theoretical significance and practical value in production practice.