基于大数据挖掘算法的高炉原料与操作参数优化方法研究
首发时间:2020-10-23
摘要:在高炉生产过程中,由于原料成分、操作手段等的波动,往往会导致生产过程的不稳定。因此,研究原料、高炉操作参数与经济运行指标之间的关系,找到与高炉的高效运行相对应的优化原料和操作参数,对于指导高炉的高效生产,具有重要的意义。本文提出将主成分分析(Principal component analysis,PCA)与聚类分析(Clustering analysis)结合的大数据挖掘方法,使用主成分分析与聚类分析分别对高炉原料和运行参数进行筛选,通过提取结果中的交叉参数;然后,以利用系数和燃料比为决策指标,使用灰色关联分析计算关联度筛选出关键影响参数。通过对高炉经济指标的关键影响参数样本分析,找到了可以使高炉维持在一个最佳经济水平的冶炼参数优化区间,为高炉的高效操作提供指导。
关键词: 数据挖掘 主成分分析 聚类分析 相关性分析 灰色关联分析。
For information in English, please click here
Research on optimization method of parameters for BF raw materials and operating based on big data mining algorithm
Abstract:In the production of blast furnace, the fluctuation of raw materials and operation will lead to the instability of blast furnace production. Therefore, it is of great significance to study the relationship between raw materials, blast furnace operation data and economic operation indexes in order to find the optimal raw materials and operation parameters corresponding to the high-efficiency operation of blast furnace. In this paper, a big data mining method combining principal component analysis (PCA) and clustering analysis was proposed. The principal component analysis and cluster analysis were used to screen the parameters of raw materials and operation of blast furnace production respectively, and the cross parameters in the results were extracted. Then, taking utilization coefficient and fuel ratio as decision-making indexes, grey correlation analysis was used to calculate correlation degree to screen out the key influencing parameters of raw materials and operation of BF. Through the analysis of the key influencing parameters of blast furnace economic indicators, the optimization interval of smelting parameters that can maintain BF at an optimal economic level is found, which provides guidance for the efficient operation of BF.
Keywords: Data mining Principal component analysis Cluster analysis Correlation analysis Grey correlation analysis.
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于大数据挖掘算法的高炉原料与操作参数优化方法研究
评论
全部评论0/1000