Research on Prediction Model of End-Point Phosphorus Content for AOD Furnace Smelting Ferrochrome Based on RBF Neural Network

Abstract

AOD furnace Smelting Ferrochrome is a complex process. The discretion of the impurity content of phosphorus is one of the important factors affecting the quality of ferrochrome products. If ferrochrome phosphorus excesses, the product is easy to break. At present, the most detection methods of determination the end phosphorus content are artificial experiments, so efficiency is lagging behind. It is necessary to establish a model to predict end-point phosphorus content for improving production efficiency, reducing costs, saving energy consumption. The important influence factors of AOD furnace smelting ferrochrome end-point phosphorus content were determined based on analyzing response characteristics of hot metal dephosphorization pretreatment and thermodynamic condition, the control variables of the end phosphorus content were fixed. According to Sinosteel Jilin Ferroalloys Co., Ltd 5t AOD furnace smelting medium-low carbon ferrochrome technology and production data, a prediction model for AOD furnace smelting ferrochrome end-point phosphorus content has been established based on RBF artificial neural network in accordance with the ferrochrome smelting process for online prediction of end-point phosphorus content. Results showed that the prediction precision of target shooting is 85.7% within the error 0.003%, which has provided important theoretical basis on improving the smelting process and product quality.