Application of Principal Component Analysis for Steel Material Components

Abstract

In this research, we made use of the principal component analysis (PCA) technique, which is a multivariate statistical method that transforms a fixed number of correlated variables into a fixed number of orthogonal, uncorrelated axes known as principal components by making use of orthogonal transformation. In other words, the PCA technique converts correlated variables into uncorrelated axes. To minimize the dimensionality of a data set that included a large range of connected variables while yet keeping as much variance within the data set as possible, we employed a method called principal component analysis (PCA). This allowed us to analyze eleven steel components. This is accomplished by reworking the unique variables into a brand new set of uncorrelated variables known as principal components (PC). The principal components are ordered in such a way that they preserve the majority of the variation that is found in all of the unique variables. This is done by reworking the unique variables into a brand new set of uncorrelated variables called principal components (PC). We are able to come to the conclusion that the five principal components that collectively account for approximately sixty-seven percent of the variance in all of the data are the best principal components because this percentage represents the best principal aspect of all of the 11 principal components.

Keywords

• Principal Component Analysis (PCA)
• multivariate
• transformation
• uncorrelated