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

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.