Comprehensive evaluation of the blast furnace status based on data mining and mechanism analysis
Comprehensive evaluation of the blast furnace status based on data mining and mechanism analysis
复制标题
基于数据挖掘和机理分析的高炉现状综合评价
DOI：
10.1515/ijcre-2021-0160
复制
发表时间：
2021-09
影响因子：
1.6
通讯作者：
Shengli Wu
中科院分区：
文献类型：
--
作者：
Yifan Hu;Heng Zhou;Shun Yao;Mingyin Kou;Zongwang Zhang;Li Pang Wang;Shengli Wu
抽象的。钢铁工业作为高能耗、高排放的行业，在带动经济发展的同时，也带来了严重的环境污染问题。为了实现绿色低碳钢铁制造，减少高炉炼铁过程中CO2排放已成为当前主流，其中高炉状态的准确判断是实现这一目标的关键。首先，结合理论与生产经验，建立了高炉的6个评价体系，并通过数理统计从中提取了22个评价参数。借助Python完成数据预处理后，挖掘初始变量中的潜在元素，并通过因子分析建立高炉状态综合评价模型。在此基础上，将高炉状态分为良好、正常、不良、预警四个等级，并通过生产日志对比验证合理性。通过比较不同炉况下的数据分布规律，总结出最佳的运行参数范围。该研究有望为实现高炉节能降耗提供指导。
Abstract. As an industry with high energy consumption and high emission, the iron and steel industry not only drives the economic development, but also brings serious environmental pollution problems. In order to achieve green and low-carbon steel manufacturing, reducing CO2 emissions in the blast furnace ironmaking process has become the current mainstream, of which the accurate judgment of the blast furnace status is a key to achieve it. Firstly, combining theory with production experience, this research established 6 evaluation systems of the blast furnace and extracted 22 evaluation parameters from them through mathematical statistics. After completing the data preprocessing with the help of Python, the potential elements in the initial variables were excavated and a comprehensive evaluation model of the blast furnace status was developed by Factor Analysis. Based on this, the status of the blast furnace were divided into four degrees, i.e. good, normal, poor and warning and the rationality was verified by comparison to the production logs. By means of comparing the law of data distribution under different furnace status, the optimal range of operation parameters was summarized. This study is expected to provide guidance for realizing energy conservation and consumption reduction of the blast furnace.
登录
查看更多内容
DOI：
10.1007/s00170-010-2786-0
发表时间：
2011-02
期刊：
The International Journal of Advanced Manufacturing Technology
影响因子：
--
作者：
Abhijit Ghosh;Sujit K. Majumdar
通讯作者：
Abhijit Ghosh;Sujit K. Majumdar
影响因子：
2.2
作者：
S. Puttinger;H. Stocker
通讯作者：
S. Puttinger;H. Stocker
Hadoop云平台下高炉冶炼过程大数据驱动铁水硅含量动态预测研究
影响因子：
2.3
作者：
Han, Yang;Li, Jie;Zhang, Yu-Zhu
通讯作者：
Zhang, Yu-Zhu
影响因子：
6
作者：
Hana Mandova;S. Leduc;Chuan Wang;Elisabeth Wetterlund;P. Patrizio;W. Gale;F. Kraxner
通讯作者：
Hana Mandova;S. Leduc;Chuan Wang;Elisabeth Wetterlund;P. Patrizio;W. Gale;F. Kraxner
DOI：
10.1007/s11663-014-0156-2
发表时间：
2014-08
期刊：
Metallurgical and Materials Transactions B
影响因子：
--
作者：
T. Mitra;H. Saxén
通讯作者：
T. Mitra;H. Saxén