高炉利用系数提升的鼓风制度自适应调控模型研究  

Research on adaptive control model of blasting system for improvement of blast furnace utilization coefficient

作　　者：王丽敬 胡支滨 韩阳 杨爱民 张玉柱 WANG Lijing;HU Zhibin;HAN Yang;YANG Aimin;ZHANG Yuzhu(Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes,North China University of Science and Technology,Tangshan 063000,China;Hebei Key Laboratory of Data Science and Application,North China University of Science and Technology,Tangshan 063000,China;Tangshan Key Laboratory of Engineering Computing,North China University of Science and Technology,Tangshan 063000,China;Tangshan Intelligent Industry and Image Processing Technology Innovation Center,North China University of Science and Technology,Tangshan 063000,China;College of Metallurgy and Energy,North China University of Science and Technology,Tangshan 063210,China)

机构地区：[1]华北理工大学铁矿石优选与铁前工艺智能化河北省工程研究中心,河北唐山063000 [2]华北理工大学河北省数据科学与应用重点实验室,河北唐山063000 [3]华北理工大学唐山市工程计算重点实验室,河北唐山063000 [4]华北理工大学唐山市智能工业与图像处理技术创新中心,河北唐山063000 [5]华北理工大学冶金与能源学院,河北唐山063210

出　　处：《冶金自动化》2023年第2期57-65,88,共10页Metallurgical Industry Automation

基　　金：国家自然科学基金面上项目(52074126);唐山市科技计划项目(22130201G)。

摘　　要：为确定焦比、煤比、燃料比等经济技术指标调控与高炉利用系数之间的关系,结合贝叶斯优化后的极端梯度提升(extreme gradient boosting,XGBoost)回归高炉利用系数预报模型在多元线性和回归等方面的优势,借助灰狼优化算法(gray wolf optimization,GWO),构建了高炉利用系数提升的鼓风制度预报模型。在经济技术指标可调控区间上,智能推荐技术指标不超过20%的区间内,智能推荐模型利用系数提升达9.1%以上,且系统运行稳健、仿真效果有效,具有在钢铁企业可观的应用前景和推广价值。In order to determine the relationship between the regulation of economic and technical indicators such as coke ratio,coal ratio and fuel ratio and the blast furnace utilization coefficient,combined with the advantages of extreme gradient boosting(XGBoost)regression prediction model of blast furnace utilization coefficient after Bayesian optimization in multiple linearity and regression,and with the help of gray wolf optimization(GWO),the blast system prediction model of blast furnace utilization coefficient improvement was constructed.In the adjustable range of economic and technical indicators,in the range where the technical indicators of intelligent recommendation do not exceed 20%,the utilization coefficient of the intelligent recommendation model increases by more than 9.1%.Moreover,the system runs steadily and the simulation effect is effective,which has considerable application prospects and promotion value in iron and steel enterprises.

关 键 词：高炉利用系数 鼓风制度 灰狼优化算法 自适应调控系统 XGBoost 

分 类 号：TF54[冶金工程—钢铁冶金]