English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Multivariate modeling has gained popularity in several process industries, especially in the petrochemical sector. The Partial Least Square (PLS) is one of the various multivariate techniques where the relationship between multiple Y (responses) and large number of X variables (predictors) are modelled. Recently, the technique has been used in the steel industry. 1‐4) The PLS is emerging as the most robust 4,5) and reliable prediction tool when huge amounts of collinear data are to be handled. Collinear data means any two columns in the data set are linearly dependent and the inverse of the matrix is non-existent since the determinant is zero. The other multivariate techniques like multiple linear regression (MLR) fails to handle collinear data as it involves inversion of matrix to estimate the regression coefficients. The present work deals with the application of PLS to predict the silicon content of hot metal. This is a novel application of PLS in ironmaking since PLS has traditionally been used in many other scientific fields like chemometrics, chemistry, biology etc. to name a few. 5,6) Use of PLS in hot metal silicon prediction is a novel application since most of the reported Si prediction models have employed ANN 7‐10) and nonlinear time series methods. 11‐13)

Prediction of Silicon Content in Blast Furnace Hot Metal Using Partial Least Squares (PLS)