高炉-转炉铁钢界面铁水温降预测建模和分析

Modeling and analysis of temperature drop prediction on techno-interface of BF-BOF route

针对高炉-转炉铁钢界面间铁水在受铁、运输及预脱硫过程中的散热问题,以铁水温降为研究对象,分析铁钢界面铁水在运输过程温降的影响因素,建立基于极限学习机的铁水温降预测模型。实例研究结果表明,建立的预测模型能够很好地预测铁钢界面铁水运输过程温降,连续预测100罐铁水温降,当绝对误差小于10℃时,铁水温降命中率为87%,预测均方根误差为6.932。对铁水温降的各主要影响因素定量分析表明,铁水温降对受铁温度最为敏感。

For the problems of heat transfer of hot metal in the process of transporting, pre-desulfurization of ironmaking and steelmaking interface, the present work takes the temperature drop of hot metal as research object, and the factors influencing temperature drop of hot metal in the process of transportation at the interface of ironmaking and steelmaking were analyzed. A prediction model of molten iron temperature drop based on extreme learning machine was established. The results show that the prediction model can predict the temperature drop of the hot metal in the transportation process of the ironmaking and steelmaking interface. When the absolute error is less than 10 ℃, the hit rate of the proposed model is 87%, and the root mean square error is 6.932. Quantitative analysis of the main factors affecting the temperature drop of hot metal shows that the temperature drop of hot metal is most sensitive to the initial temperature of hot metal.