基于灰色神经网络的中低碳铬铁终点硫含量预报模型研究

Research on prediction model of medium-low carbon ferrochrome sulfur end-point content based on gray neural network

针对复吹转炉冶炼中低碳铬铁终点硫含量在线监测困难、取样检测无法实时指导生产的现状,考虑影响终点硫含量的供氧强度、铁水温度等因素,采用以灰色预报模型结合BP神经网络的方法实现中低碳铬铁终点硫含量的预报。仿真实验表明:中低碳铬铁终点硫含量预报绝对误差值在±0.004%以内的命中率为95%,相对误差值在15%以内的命中率达到85%,验证了该预报模型的有效性。

It was difficult to detect sulfur end-point content through on-line measurement in the medium-low carbon ferrochrome combined-blowing converter and hardly to guide production in real time through sampling and inspection.Considering the impaction of the sulfur endpoint content of oxygen intensity,temperature of hot metal and other factors and combining the grey model with BP neural network prediction model,the prediction of medium-low carbon ferrochrome sulfur endpoint content was realized.The simulation results indicated that the prediction hitting rate of the sulfur endpoint content in the low-carbon ferrochrome was 95% when the absolute error was less than 0.004%,and the heating rate was 85% when the relative error was less than 15%.Thus,the validity of the prediction model was proved.