%A Hai Chau Nguyen
%A Masatoshi Kubo
%A Viet Hai Le
%A Tomoyuki Yamamoto
%T Phase Prediction of Multi-principal Element Alloys Using Machine Learning Methods
%X Designing new materials with desired properties is a complex and time consuming process. One of the challenging factors of the design process is the huge search space of possible materials. Machine learning methods such as k-nearest neighbours, support vector machine (SVM) and artificial neural network (ANN) can contribute to this process by accurately predicting materials properties. Properties of multi-principal element alloys (MPEAs) highly depend on alloys’ phases. Thus accurate prediction of alloy’s phase is important to eliminate the search space. In this paper we propose a solution of employing support vector machine method with hyperparameters tuning and the use of weights values for alloy’s phase prediction. Comparative experiments show that on a 118 MPEAs dataset, our solution achieves cross-validation accuracy of 90%. It is 6.7% higher than that of ANN. On another 401 MPEAs dataset, our solution is comparable to ANN and obtains 70.7% cross-validation accuracy.
%C Phuket, Thailand
%D 2021
%L SisLab4236