工程科学学报.第43卷，第4期：569-576.2021年4月 Chinese Journal of Engineering,Vol.43,No.4:569-576,April 2021 https://doi.org/10.13374/j.issn2095-9389.2020.05.28.001;http://cje.ustb.edu.cn 基于支持向量回归与极限学习机的高炉铁水温度预测 王振阳)区，江德文)，王新东)，张建良1,3)，刘征建)，赵宝军) 1)北京科技大学治金与生态工程学院，北京1000832)河钢集团有限公司钢铁技术研究总院，石家庄0500233)昆士兰大学化学工程学 院，圣卢西亚QLD4072 ☒通信作者.E-mail:wangzhenyang(@ustb.edu.cn 摘要选取某4000m3级别高炉2014年至2019年时间范围内的日平均数据，以铁水温度为目标函数.首先对铁水温度的 特征参量进行线性与非线性相关性分析、特征选择与规范化处理，获取了显著影响铁水温度的正负相关性特征参量.在此基 础上，基于支持向量回归与极限学习机两种算法对铁水温度构建预测模型，模型均可对铁水温度实现有效预测，基于支持向 量回归算法构建的预测模型较优，预测平均绝对误差为4.33℃，±10℃误差范围内的命中率为94.0%. 关键词大数据：机器学习：支持向量回归：极限学习机：铁水温度 分类号TF543.1 Prediction of blast furnace hot metal temperature based on support vector regression and extreme learning machine WANG Zhen-yang JIANG De-wen.WANG Xin-dong.ZHANG Jian-liang LIU Zheng-jian,ZHAO Bao-jun 1)School of Metallurgical and Ecological Engineering,University of Science and Technology Beijing,Beijing 100083,China 2)Iron and Steel Technology Research Institute,Hegang Group Co.Ltd.,Shijiazhuang 050023,China 3)School of Chemical Engineering,The University of Queensland,St Lucia QLD 4072,Australia Corresponding author,E-mail:wangzhenyang@ustb.edu.cn ABSTRACT The hot metal temperature is a key process parameter for blast furnace(BF)ironmaking that reflects the quality of hot metal,the thermal state of BF hearth,the energy utilization efficiency of BF,and many other information.Prediction of the hot metal temperature in the next smelting cycle will be helpful in gaining a better understanding of the change trend of hot metal quality and BF smelting status in time.With this,corresponding operational measures can be conducted to maintain the BF stable and smooth state,high production,and low consumption.Nowadays,big data technology has made considerable progress toward a more accurate and faster collection,storage,transmission,query,analysis,and integration of mass data,providing a good data foundation for data-driven machine learning models.In addition,with the substantial increase in computer calculation speed and the significant development of algorithms, the prediction accuracy of deep machine learning models has noticeably improved.The development of these technologies provides feasibility for the prediction of important indicators under complex industrial conditions.Based on the data produced from a 4000-mBF in a large span time range(2014-2019)and daily time dimension,this paper considered hot metal temperature as the objective function. First,the characteristic parameters of hot metal temperature were processed by linear and nonlinear correlation analysis,feature selection,and normalization methods.Then,the positive and negative correlation characteristic parameters that have a significant influence on the temperature of the hot metal were obtained.Finally,prediction models of hot metal temperature were established based on two algorithms of support vector regression and extreme learning machine.Although both the algorithms can achieve effective 收稿日期：202005-28 基金项目：中国博士后科学基金面上资助项目(2019M650490)基于支持向量回归与极限学习机的高炉铁水温度预测 王振阳1) 苣，江德文1)，王新东2)，张建良1,3)，刘征建1)，赵宝军3) 1) 北京科技大学冶金与生态工程学院，北京 100083    2) 河钢集团有限公司钢铁技术研究总院，石家庄 050023    3) 昆士兰大学化学工程学 院，圣卢西亚 QLD 4072 苣通信作者，E-mail: wangzhenyang@ustb.edu.cn 摘    要    选取某 4000 m 3 级别高炉 2014 年至 2019 年时间范围内的日平均数据，以铁水温度为目标函数，首先对铁水温度的 特征参量进行线性与非线性相关性分析、特征选择与规范化处理，获取了显著影响铁水温度的正负相关性特征参量. 在此基 础上，基于支持向量回归与极限学习机两种算法对铁水温度构建预测模型，模型均可对铁水温度实现有效预测，基于支持向 量回归算法构建的预测模型较优，预测平均绝对误差为 4.33 ℃，±10 ℃ 误差范围内的命中率为 94.0%. 关键词    大数据；机器学习；支持向量回归；极限学习机；铁水温度 分类号    TF543.1 Prediction  of  blast  furnace  hot  metal  temperature  based  on  support  vector  regression and extreme learning machine WANG Zhen-yang1) 苣 ，JIANG De-wen1) ，WANG Xin-dong2) ，ZHANG Jian-liang1,3) ，LIU Zheng-jian1) ，ZHAO Bao-jun3) 1) School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China 2) Iron and Steel Technology Research Institute, Hegang Group Co. Ltd., Shijiazhuang 050023, China 3) School of Chemical Engineering, The University of Queensland, St Lucia QLD 4072, Australia 苣 Corresponding author, E-mail: wangzhenyang@ustb.edu.cn ABSTRACT    The hot metal temperature is a key process parameter for blast furnace (BF) ironmaking that reflects the quality of hot metal, the thermal state of BF hearth, the energy utilization efficiency of BF, and many other information. Prediction of the hot metal temperature in the next smelting cycle will be helpful in gaining a better understanding of the change trend of hot metal quality and BF smelting status in time. With this, corresponding operational measures can be conducted to maintain the BF stable and smooth state, high production, and low consumption. Nowadays, big data technology has made considerable progress toward a more accurate and faster collection, storage, transmission, query, analysis, and integration of mass data, providing a good data foundation for data-driven machine learning models. In addition, with the substantial increase in computer calculation speed and the significant development of algorithms, the  prediction  accuracy  of  deep  machine  learning  models  has  noticeably  improved.  The  development  of  these  technologies  provides feasibility for the prediction of important indicators under complex industrial conditions. Based on the data produced from a 4000-m3 BF in a large span time range (2014–2019) and daily time dimension, this paper considered hot metal temperature as the objective function. First,  the  characteristic  parameters  of  hot  metal  temperature  were  processed  by  linear  and  nonlinear  correlation  analysis,  feature selection,  and  normalization  methods.  Then,  the  positive  and  negative  correlation  characteristic  parameters  that  have  a  significant influence on the temperature of the hot metal were obtained. Finally, prediction models of hot metal temperature were established based on  two  algorithms  of  support  vector  regression  and  extreme  learning  machine.  Although  both  the  algorithms  can  achieve  effective 收稿日期: 2020−05−28 基金项目: 中国博士后科学基金面上资助项目（2019M650490） 工程科学学报，第 43 卷，第 4 期：569−576，2021 年 4 月 Chinese Journal of Engineering, Vol. 43, No. 4: 569−576, April 2021 https://doi.org/10.13374/j.issn2095-9389.2020.05.28.001; http://cje.ustb.edu.cn