A New Method to Characterize Limited Material Datasets of High-Entropy Alloys Based on the Feature Engineering and Machine Learning

18 Pages Posted: 27 Aug 2019

See all articles by Dongbo Dai

Dongbo Dai

Shanghai University - School of Computer Engineering and Science

Tao Xu

Shanghai University - School of Computer Engineering and Science

Hongqing Hu

Shanghai University - School of Computer Engineering and Science

Zhiting Guo

Shanghai University - School of Computer Engineering and Science

Qing Liu

Shanghai University - School of Computer Engineering and Science

Shengzhou Li

Shanghai University - School of Computer Engineering and Science

Quan Qian

Shanghai University - School of Computer Engineering and Science; Shanghai University - Materials Genome Institute

Yan Xu

Shanghai University of Electric Power - College of Mathematics and Physics

Huiran Zhang

Shanghai University - School of Computer Engineering and Science; Shanghai University - Materials Genome Institute; Shanghai Institute for Advanced Communication and Data Science

Abstract

This paper proposed a new method for characterizing limited material data of high-entropy alloys (HEAs) based on the feature engineering and machine learning (ML). The descriptor dimensionality is augmented from original small dimension to a high dimension by non-linear combination based on feature engineering to characterize this kind material. To avoid overfitting, we carried out 5-fold cross-validation to evaluate the generalization performance of the model. The results showed that this method could achieve higher accuracy in predicting the phase formation of HEAs. Except the prediction of HEAs, this method also can be applied to other materials with limited data.

Keywords: High-entropy alloy, Phase transformations, Machine learning, Feature engineering

Suggested Citation

Dai, Dongbo and Xu, Tao and Hu, Hongqing and Guo, Zhiting and Liu, Qing and Li, Shengzhou and Qian, Quan and Xu, Yan and Zhang, Huiran, A New Method to Characterize Limited Material Datasets of High-Entropy Alloys Based on the Feature Engineering and Machine Learning. Available at SSRN: https://ssrn.com/abstract=3442010 or http://dx.doi.org/10.2139/ssrn.3442010

Dongbo Dai (Contact Author)

Shanghai University - School of Computer Engineering and Science

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Tao Xu

Shanghai University - School of Computer Engineering and Science

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Hongqing Hu

Shanghai University - School of Computer Engineering and Science

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Zhiting Guo

Shanghai University - School of Computer Engineering and Science

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Qing Liu

Shanghai University - School of Computer Engineering and Science

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Shengzhou Li

Shanghai University - School of Computer Engineering and Science

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Quan Qian

Shanghai University - School of Computer Engineering and Science

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Shanghai University - Materials Genome Institute

China

Yan Xu

Shanghai University of Electric Power - College of Mathematics and Physics

China

Huiran Zhang

Shanghai University - School of Computer Engineering and Science ( email )

149 Yanchang Road
Shangda Road 99
Shanghai 200072, Shanghai 200444
China

Shanghai University - Materials Genome Institute ( email )

China

Shanghai Institute for Advanced Communication and Data Science ( email )

China

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
62
Abstract Views
321
rank
405,073
PlumX Metrics