基于参数优化SVR方法预测高炉煤气利用率  

Prediction of utilization ratio of blast furnace gas based on parameter optimized by SVR method

作　　者：党晓晶 石琳[2] 赵娜 袁冬芳 李江鹏 DANG Xiaojing;SHI Lin;ZHAO Na;YUAN Dongfang;LI Jiangpeng(School of Mining and Coal,Inner Mongolia University of Science and Technology,Baotou 014010,Nei Mongol,China;School of Science,Inner Mongolia University of Science and Technology,Baotou 014010,Nei Mongol,China)

机构地区：[1]内蒙古科技大学矿业与煤炭学院,内蒙古包头014010 [2]内蒙古科技大学理学院,内蒙古包头014010

出　　处：《钢铁研究学报》2021年第4期279-283,共5页Journal of Iron and Steel Research

基　　金：内蒙古自然科学基金资助项目(2020MS06010,2018LH01008);内蒙古科技大学创新基金资助项目(2015XYPYL11)。

摘　　要：高炉煤气利用率是反映高炉能耗的重要指标,其预测控制对炼铁过程的节能降耗具有重要意义。利用某高炉在线采集的数据对煤气流温度分布和高炉煤气利用率的关系进行研究。首先,对高炉煤气利用率数据和能够实时反映煤气流分布的炉喉十字测温数据中的缺失值进行多重插补填充,并利用分位点计算煤气流分布的经验分布函数,得到测温数据的小时分布概率。再运用灰狼算法优化支持向量回归(Support Vector Regression, SVR)模型的样本量和核参数,建立高炉煤气利用率预测模型。结果表明,在优化建模样本量和模型核参数的情况下,支持向量回归模型的预测精度更高,能够为高炉的优化控制和节能降耗提供有力支持。In iron smelting process, the predictive control of blast furnace gas utilization ratio which is an important index to reflect its energy consumption is of great significance for energy-saving and consumption-reducing. The relationship between gas temperature distribution in blast furnace and gas utilization efficiency was studied by analyzing blast furnace operation data. Firstly, the multiple imputation method was used to deal with the problem of missing data existing in gas utilization efficiency data and cross temperature data which can represent gas distribution in blast furnace on real time, then the empirical distribution function of gas distribution was acquired by quantile, the hourly probability distribution of temperature data was obtained. Secondly, the best amount of the samples size and optimal parameter values of kernel function of Support Vector Regression model is determined by the grey wolf algorithm, and a model is built to predict gas utilization ratio of blast furnace. The results demonstrate that the model proposed achieves more accurate prediction when the best sample size and optimal parameter values is determined, which serves as a effective support for optimal control of blast furnace operation as well as energy-saving and consumption-reducing.

关 键 词：高炉 经验分布函数 支持向量回归 灰狼算法 煤气利用率 

分 类 号：TF537[冶金工程—钢铁冶金]