Prediction of Silicon Content of Molten Iron in Blast Furnace Based on Particle Swarm - Random Forest

The silicon content of blast furnace hot metal is not only the key index in the steel preparation process, but also is often used to characterize the furnace temperature and the running state of blast furnace. Therefore, the prediction method of molten iron silicon content is an important topic in the research of blast furnace smelting. In this paper, the classical stochastic forest model theory is improved and an inter-tree weighted stochastic forest model is proposed. At the same time, particle swarm optimization (PSO) algorithm is used to optimize the model parameters. Finally, through experimental verification, PSOTWB-RF model proposed in this paper has high prediction accuracy and hit ratio.