基于自回归分布滞后模型的高炉铁水硅含量的预报  

Prediction of Hot Metal Silicon Content in Blast Furnaces Based on the Autoregressive Distributed Lag Model

作　　者：李江鹏[1] 石琳[1] 于涛[1] 曹富军[1] 袁冬芳[1] 

机构地区：[1]内蒙古科技大学数理与生物工程学院,内蒙古包头014010

出　　处：《内蒙古大学学报（自然科学版）》2013年第4期419-423,共5页Journal of Inner Mongolia University：Natural Science Edition

基　　金：国家自然科学基金资助项目(51064019;61263015);内蒙古科技大学创新基金资助项目(2011NCL031);内蒙古科技大学创新基金资助项目(2011NCL019)

摘　　要：高炉冶炼过程中,铁水硅含量是评定高炉炉况稳定性和生铁质量的重要指标,其预测和控制对高炉的稳定顺行有重要意义.基于包钢6号高炉的生产数据,建立差分时间序列的自回归分布滞后模型对高炉铁水硅含量进行预测.结果表明:在炉况波动较小的情况下,该模型的预测命中率能达到87.5%,对实际的生产操作过程有一定的指导意义.In the iron-making process,hot metal silicon content is an important index to evaluate the stability of iron-making process and quality of hot metal,the prediction and control play an important role in the stable operation of blast furnaces.Based on the data collected from No.6 blast furnace of Baotou Iron and Steel Corporation,an autoregressive distributed lag model is proposed to predict the hot metal silicon content in blast furnaces.The result has been achieved that the hit rate of the model is 87.5% in the less fluctuation,which is of certain guiding significance for the production operation of blast furnaces.

关 键 词：铁水硅含量 差分变换 自回归分布滞后模型 时滞 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TF533[自动化与计算机技术—控制科学与工程]