Machine learning for phase selection in multi-principal element alloys

Nusrat Islam, Wenjiang Huang, Houlong Zhuang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Multi-principal element alloys (MPEAs) especially high entropy alloys have attracted significant attention and resulted in a novel concept of designing metal alloys via exploring the wide composition space. Abundant experimental data of MPEAs are available to show connections between elemental properties and the resulting phases such as single-phase solid solution, amorphous, intermetallic compounds. To gain insights of designing MPEAs, here we employ neural network (NN) in the machine learning framework to recognize the underlying data pattern using an experimental dataset to classify the corresponding phase selection in MPEAs. For the full dataset, our trained NN model reaches an accuracy of over 99%, meaning that more than 99% of the phases in the MPEAs are correctly labeled. Furthermore, the trained NN parameters suggest that the valence electron concentration plays the most dominant role in determining the ensuing phases. For the cross-validation training and testing datasets, we obtain an average generalization accuracy of higher than 80%. Our trained NN model can be extended to classify different phases in numerous other MPEAs.

Original languageEnglish (US)
Pages (from-to)230-235
Number of pages6
JournalComputational Materials Science
Volume150
DOIs
StatePublished - Jul 1 2018

Fingerprint

machine learning
Learning systems
Machine Learning
Neural networks
Neural Network Model
Classify
Neural Networks
Intermetallics
Cross-validation
intermetallics
Solid solutions
education
solid solutions
Entropy
Metals
Experimental Data
Electron
entropy
valence
Testing

Keywords

  • High entropy alloys
  • Machine learning
  • Multiprincipal element alloys
  • Phase selection

ASJC Scopus subject areas

  • Computer Science(all)
  • Chemistry(all)
  • Materials Science(all)
  • Mechanics of Materials
  • Physics and Astronomy(all)
  • Computational Mathematics

Cite this

Machine learning for phase selection in multi-principal element alloys. / Islam, Nusrat; Huang, Wenjiang; Zhuang, Houlong.

In: Computational Materials Science, Vol. 150, 01.07.2018, p. 230-235.

Research output: Contribution to journalArticle

@article{517abbd665304886ba5d8469d3178771,
title = "Machine learning for phase selection in multi-principal element alloys",
abstract = "Multi-principal element alloys (MPEAs) especially high entropy alloys have attracted significant attention and resulted in a novel concept of designing metal alloys via exploring the wide composition space. Abundant experimental data of MPEAs are available to show connections between elemental properties and the resulting phases such as single-phase solid solution, amorphous, intermetallic compounds. To gain insights of designing MPEAs, here we employ neural network (NN) in the machine learning framework to recognize the underlying data pattern using an experimental dataset to classify the corresponding phase selection in MPEAs. For the full dataset, our trained NN model reaches an accuracy of over 99{\%}, meaning that more than 99{\%} of the phases in the MPEAs are correctly labeled. Furthermore, the trained NN parameters suggest that the valence electron concentration plays the most dominant role in determining the ensuing phases. For the cross-validation training and testing datasets, we obtain an average generalization accuracy of higher than 80{\%}. Our trained NN model can be extended to classify different phases in numerous other MPEAs.",
keywords = "High entropy alloys, Machine learning, Multiprincipal element alloys, Phase selection",
author = "Nusrat Islam and Wenjiang Huang and Houlong Zhuang",
year = "2018",
month = "7",
day = "1",
doi = "10.1016/j.commatsci.2018.04.003",
language = "English (US)",
volume = "150",
pages = "230--235",
journal = "Computational Materials Science",
issn = "0927-0256",
publisher = "Elsevier",

}

TY - JOUR

T1 - Machine learning for phase selection in multi-principal element alloys

AU - Islam, Nusrat

AU - Huang, Wenjiang

AU - Zhuang, Houlong

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Multi-principal element alloys (MPEAs) especially high entropy alloys have attracted significant attention and resulted in a novel concept of designing metal alloys via exploring the wide composition space. Abundant experimental data of MPEAs are available to show connections between elemental properties and the resulting phases such as single-phase solid solution, amorphous, intermetallic compounds. To gain insights of designing MPEAs, here we employ neural network (NN) in the machine learning framework to recognize the underlying data pattern using an experimental dataset to classify the corresponding phase selection in MPEAs. For the full dataset, our trained NN model reaches an accuracy of over 99%, meaning that more than 99% of the phases in the MPEAs are correctly labeled. Furthermore, the trained NN parameters suggest that the valence electron concentration plays the most dominant role in determining the ensuing phases. For the cross-validation training and testing datasets, we obtain an average generalization accuracy of higher than 80%. Our trained NN model can be extended to classify different phases in numerous other MPEAs.

AB - Multi-principal element alloys (MPEAs) especially high entropy alloys have attracted significant attention and resulted in a novel concept of designing metal alloys via exploring the wide composition space. Abundant experimental data of MPEAs are available to show connections between elemental properties and the resulting phases such as single-phase solid solution, amorphous, intermetallic compounds. To gain insights of designing MPEAs, here we employ neural network (NN) in the machine learning framework to recognize the underlying data pattern using an experimental dataset to classify the corresponding phase selection in MPEAs. For the full dataset, our trained NN model reaches an accuracy of over 99%, meaning that more than 99% of the phases in the MPEAs are correctly labeled. Furthermore, the trained NN parameters suggest that the valence electron concentration plays the most dominant role in determining the ensuing phases. For the cross-validation training and testing datasets, we obtain an average generalization accuracy of higher than 80%. Our trained NN model can be extended to classify different phases in numerous other MPEAs.

KW - High entropy alloys

KW - Machine learning

KW - Multiprincipal element alloys

KW - Phase selection

UR - http://www.scopus.com/inward/record.url?scp=85045282326&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045282326&partnerID=8YFLogxK

U2 - 10.1016/j.commatsci.2018.04.003

DO - 10.1016/j.commatsci.2018.04.003

M3 - Article

AN - SCOPUS:85045282326

VL - 150

SP - 230

EP - 235

JO - Computational Materials Science

JF - Computational Materials Science

SN - 0927-0256

ER -