引用本文:周平,李瑞峰,郭东伟,王宏,柴天佑.高炉炼铁过程多元铁水质量指标多输出支持向量回归建模[J].控制理论与应用,2016,33(6):727~734.[点击复制]
Ping Zhou,LI Rui-feng,GUO Dong-wei,Wang Hong,CHAI Tianyou.Multi-output support vector regression modeling for multivariate molten iron quality indices in blast furnace ironmaking process[J].Control Theory and Technology,2016,33(6):727~734.[点击复制]
高炉炼铁过程多元铁水质量指标多输出支持向量回归建模
Multi-output support vector regression modeling for multivariate molten iron quality indices in blast furnace ironmaking process
摘要点击 4590  全文点击 2834  投稿时间：2015-10-29  修订日期：2016-02-23
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2016.50857
  2016,33(6):727-734
中文关键词  高炉炼铁  铁水质量  多输出支持向量回归(M–SVR)  模型精度综合评价  遗传优化  数据驱动建模
英文关键词  blast furnace ironmaking  molten iron quality (MIQ)  multi-output support vector regression (M–SVR)  comprehensive evaluation of modeling accuracy  genetic optimization  data-driven modeling
基金项目  国家自然科学基金项目(61473064, 61290323, 61333007), 中央高校基本科研业务费项目(N130108001), 国家“863”计划项目(2015AA043802), 辽宁省教育厅科技项目(L20150186)资助.
作者单位E-mail
周平* 东北大学流程工业综合自动化国家重点实验室 zhouping@mail.neu.edu.cn 
李瑞峰 东北大学流程工业综合自动化国家重点实验室  
郭东伟 东北大学流程工业综合自动化国家重点实验室  
王宏 英国曼切斯特大学控制系统中心  
柴天佑 东北大学流程工业综合自动化国家重点实验室  
中文摘要
      针对高炉炼铁过程铁水温度、Si含量、S含量、P含量等关键质量指标难以直接在线检测, 且离线化验过程 滞后严重的难题, 建立基于建模精度综合评价与遗传参数优化的铁水质量(molten iron quality, MIQ)多输出支持向 量回归(multi-output support vector regression, M–SVR)动态模型, 用于对高炉铁水质量指标进行在线估计. 与常规单 输出SVR建模不同, M–SVR可一次确定多个分类超平面, 从而可实现多元铁水质量指标的多输出建模: 建模精度综 合评价指标从模型估计趋势以及估计误差等方面综合评价建模性能; 以建模精度综合评价指标为适应度函数, 采 用遗传算法对M–SVR的伸缩向量和惩罚因子参数进行全局寻优, 从而获得具有最优参数的GA–M–SVR动态模型. 在某钢铁厂2#高炉的工业实验表明: 所提GA–M–SVR模型能够根据实时输入数据的变化对多元铁水质量参数进行 准确估计.
英文摘要
      Molten iron temperature as well as Si, P, and S contents are the most essential molten iron quality (MIQ) indices in the blast furnace (BF) ironmaking, while difficult to be directly measured online, and large-time delay exists in offline analysis through laboratory sampling. Focusing on this practical challenge, a data-driven multi-output support vector regression (M–SVR) dynamic model is established to estimate the MIQ indices online, with the help of the proposed comprehensive evaluation on modeling accuracy and genetic optimization on model parameters. Different from the conventional single output SVR, the M–SVR can calculate multiple classification by one training process, so as to realize multi-output regression modeling of multivariate MIQ indices. With the proposed comprehensive evaluation index on modeling accuracy, the modeling performance can be evaluated from the aspects of model estimation trend as well as estimation error. By taking this comprehensive evaluation index as the fitness function, the genetic algorithm (GA) is to find the optimal values of the telescopic vector and the penalty factor for the M–SVR model, so that the GA–M–SVR dynamic model with optimal parameters can be obtained. Finally, industrial experiments have been carried out on the 2# blast furnace in an Iron & Steel Group Co. of China, where it has been demonstrated that the GA–M–SVR model produces satisfied modeling and estimating accuracy.