Model of Hot Metal Silicon Content in Blast Furnace Based on Principal Component Analysis Application and Partial Least Square

Abstract

In blast furnace (BF) iron-making process, the hot metal silicon content was usually used to measure the quality of hot metal and to reflect the thermal state of BF. Principal component analysis (PCA) and partial least-square (PLS) regression methods were used to predict the hot metal silicon content. Under the conditions of BF relatively stable situation, PCA and PLS regression models of hot metal silicon content utilizing data from Baotou Steel No. 6 BF were established, which provided the accuracy of 88.4% and 89.2%. PLS model used less variables and time than principal component analysis model, and it was simple to calculate. It is shown that the model gives good results and is helpful for practical production.