Correlations between Thermal Parameters and Glass Forming Abilities of Bulk Metallic Glasses Unveiled by Datamining

Abstract

Datamining informatics techniques such as principal component analysis and partial least squares were applied to identify the composition characteristics of bulk metallic glasses with high glass forming abilities. It was pointed out that the reduced glass transition temperature Tg/Tl was comparatively the best indicator but no single indicator can reflect all the glass forming abilities of different alloy systems.

DFT Investigation of Electronic and Mechanical Properties of Binary Magnesium-Rare Earth Alloys Examined with Data Mining Approach

“…It is important to note that the eigenvectors of the covariance matrix are orthogonal in Principal Component Analysis. [49][50][51][52][53] The final stage of Principal Component Analysis involves evaluating the scores, which represent the projections of the variables onto a given principal component (PC), and the loads, which represent the eigenvectors of the diagonalized covariance matrix. The scores correspond to the eigenvalues of the diagonalized covariance matrix, while the loads correspond to its eigenvectors.…”