Machine learning-based phase prediction in high-entropy alloys: further optimization of feature engineering

Journal of Materials Science, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 12, 2025

Language: Английский

Efficient alloy design strategy for fast searching for high-entropy alloys with desired mechanical properties

Materials & Design, Journal Year: 2024, Volume and Issue: 245, P. 113260 - 113260

Published: Aug. 22, 2024

The exponentially large compositional space of high entropy alloys (HEAs) offers more possibilities for designing with desired properties. However, it also poses challenges to using the traditional "trial and error" approach in alloy design. In this work, an XGBoost model predicting elastic properties NbTiVZr family across entire was established by combining density-functional theory (DFT) calculation results as dataset machine learning (ML) algorithms. Furthermore, considerations charge transfer were incorporated into solid solution hardening (SSH) model, further modified. Through comparing plasticity evaluation indices, parameter D (γSurf/γGSFE) determined be suitable alloys. A full yield strength has been constructed based on modified SSH D, respectively. Ultimately, design system models established, achieving good consistency experimental results. And a non-equiatomic exceeding that equiatomic 32.2 % (1409 MPa), while maintaining 29.27 compressive strain discovered. conclusion, work provides efficient strategy

Language: Английский

Machine learning for thermal transport

Journal of Applied Physics, Journal Year: 2024, Volume and Issue: 136(16)

Published: Oct. 24, 2024

Language: Английский