Predicting the Average Composition of an AlFeNiTiVZr-Cr Alloy with Machine Learning and X-ray Spectroscopy

A multi-principal element alloy (MPEA) is a type of metallic that composed multiple elements, with each making up significant portion the alloy. In this study, initial atomic percentage elements in an (AlFeNiTiVZr)1-xCrx MPEA as function position on surface was investigated using machine learning algorithms. Given absence linear relationship between and their location surface, it not possible to discern any clear association from dataset. To overcome non-linear relationship, prediction accomplished both decision tree (DT) random forest (RF) regression models. The models were compared, results found be consistent experimental findings (a coefficient determination R2 0.98 obtained DT algorithm 0.99 RF one). This research demonstrates potential algorithms analysis wavelength-dispersive X-ray spectroscopy (WDS) datasets.