Creating win-wins from strength–ductility trade-off in multi-principal element alloys by machine learning

Leilei Wu, Guanying Wei, Gang Wang, Haiyan Wang, Jingli Ren

Research output: Contribution to journalReview articlepeer-review

12 Scopus citations

Abstract

Trading-off the contradicting mechanical properties of metals and alloys, such as strength–ductility, is usually difficult through conventional strengthening mechanisms. Here, we propose a novel method to accurately classify multi-principal element alloys (MPEAs) with excellent strength–ductility, possessing a yield strength more than 1 GPa and a ductility over 20%. We find that lower valence electron concentration (VEC), higher melting points, and near-zero mixing entropy exert the strongest contributions to the strength-ductility trade-off. Furthermore, we use polynomials to fit the characteristic contributions of yield strength and reveal the effect of VEC on mechanical properties at different phase. The present work demonstrates that properties fitting can be accomplished effectively by machine learning, which provides a simple and fast evaluation method for the design of a new generation of high-strength-ductility MPEAs.

Original languageEnglish (US)
Article number104010
JournalMaterials Today Communications
Volume32
DOIs
StatePublished - Aug 2022

Keywords

  • Alloys design
  • Feature analysis
  • Machine learning
  • Multi-principal element alloys
  • Strength–ductility trade-off

ASJC Scopus subject areas

  • General Materials Science
  • Mechanics of Materials
  • Materials Chemistry

Fingerprint

Dive into the research topics of 'Creating win-wins from strength–ductility trade-off in multi-principal element alloys by machine learning'. Together they form a unique fingerprint.

Cite this