Research on Prediction of Oxygen Consumption in Converter Steelmaking Based on IGWO-SVM Model

Abstract

Abstract The oxygen supply for converter steelmaking is the main factor affecting the quality of molten steel. To improve the accuracy of the oxygen consumption prediction model for converter steelmaking, an improved gray wolf optimization algorithm is proposed to optimize support vector machines to establish an oxygen consumption prediction model (IGWO-SVM), effectively improving the prediction accuracy of oxygen consumption in converter steelmaking. Firstly, aiming at the problem of slow convergence of the standard gray wolf algorithm and easy to fall into local optimality, Bernoulli chaotic initialization is introduced to enhance the uniformity and ergodicity of the initial population; and an adaptive decreasing convergence factor is introduced to balance the global search of the gray wolf algorithm and local search capability, while adopting adaptive inertia weight strategy to update the population position and speed up the convergence speed. Secondly, the benchmark function is used for testing, and the results show that the improved gray wolf optimization algorithm has improved convergence speed and search accuracy. Finally, based on the measured data of a steel plant to predict the oxygen consumption of converter steelmaking, the simulation results show that the oxygen consumption prediction model of converter steelmaking based on IGWO optimized SVM has high accuracy and strong generalization ability.