唐钢二炼铁厂3号高炉铁水硅含量神经网络预报模型

A nueral network model for predicting the silicon content of the hot metal at No.3 blast furnace in Tangshan iron and steel Co.

根据唐钢二炼铁厂 3# 高炉的生产情况和技术水平 ,建立了高炉铁水硅含量神经网络预报模型。模型采用BP网络 ,仿真试验结果表明 ,该模型具有较好的命中效果。同时 ,基于预报的铁水硅含量 ,结合部分专家知识 ,指导操作决策。

In this paper,a neural network model for prediction of silicon content of hot metal is set up according to the actual operational condiction and technology of 3 # blast furnace in No.2 Iron works,Tangshan Iron and Steel Co.Back Propagation (BP) network is used in the model.The off line prediction shows the model results have good effect.According to silicon content of hot metal of prediction,expert knowledge is used.Then it can guide operational direction making.So it is highly practical.