Skip Navigation
Skip to contents

Journal of Powder Materials : Journal of Powder Materials

OPEN ACCESS
SEARCH
Search

Search

Page Path
HOME > Search
2 "Nguyen Hoang Viet"
Filter
Filter
Article category
Keywords
Publication year
Authors
Funded articles
Research Article
Article image
[English]
Thermodynamic and Electronic Descriptor-Driven Machine Learning for Phase Prediction in High-Entropy Alloys: Experimental Validation
Nguyen Lam Khoa, Nguyen Duy Khanh, Hoang Thi Ngoc Quyen, Nguyen Thi Hoang Oanh, , Le Hong Thang, Nguyen Hoa Khiem, Nguyen Hoang Viet
J Powder Mater. 2025;32(3):191-201.   Published online June 30, 2025
DOI: https://doi.org/10.4150/jpm.2025.00143
  • 73 View
  • 5 Download
AbstractAbstract PDF
High-entropy alloys (HEAs) exhibit complex phase formation behavior, challenging conventional predictive methods. This study presents a machine learning (ML) framework for phase prediction in HEAs, using a curated dataset of 648 experimentally characterized compositions and features derived from thermodynamic and electronic descriptors. Three classifiers—random forest, gradient boosting, and CatBoost—were trained and validated through cross-validation and testing. Gradient boosting achieved the highest accuracy, and valence electron concentration (VEC), atomic size mismatch (δ), and enthalpy of mixing (ΔHmix) were identified as the most influential features. The model predictions were experimentally verified using a non-equiatomic Al₃₀Cu₁₇.₅Fe₁₇.₅Cr₁₇.₅Mn₁₇.₅ alloy and the equiatomic Cantor alloy (CoCrFeMnNi), both of which showed strong agreement with predicted phase structures. The results demonstrate that combining physically informed feature engineering with ML enables accurate and generalizable phase prediction, supporting accelerated HEA design.
[English]
The Formation and Crystallization of Amorphous Ti50Cu50Ni20Al10 Powder Prepared by High-Energy Ball Milling
Nguyen Hoang Viet, Jin-Chun Kim, Ji-Soon Kim, Young-Soon Kwon
J Korean Powder Metall Inst. 2009;16(1):9-15.
DOI: https://doi.org/10.4150/KPMI.2009.16.1.009
  • 299 View
  • 0 Download
  • 1 Citations
AbstractAbstract PDF
Amorphization and crystallization behaviors of Ti_50Cu_50Ni_20Al_10 powders during high-energy ball milling and subsequent heat treatment were studied. Full amorphization obtained after milling for 30 h was confirmed by X-ray diffraction and transmission electron microscope. The morphology of powders prepared using different milling times was observed by field-emission scanning electron microscope. The powders developed a fine, layered, homogeneous structure with prolonged milling. The crystallization behavior showed that the glass transition, T_g, onset crystallization, T_x, and super cooled liquid range DeltaT=T_x-T_g were 691,771 and 80 K, respectively. The isothermal transformation kinetics was analyzed by the John-Mehn-Avrami equation. The Avrami exponent was close to 2.5, which corresponds to the transformation process with a diffusion-controlled type at nearly constant nucleation rate. The activation energy of crystallization for the alloy in the isothermal annealing process calculated using an Arrhenius plot was 345 kJ/mol.

Citations

Citations to this article as recorded by  
  • Mechanical Properties of Bulk Amorphous Ti50Cu20Ni20Al10Fabricated by High-energy Ball Milling and Spark-plasma Sintering
    H.V. Nguyen, J.C. Kim, J.S. Kim, Y.J. Kwon, Y.S. Kwon
    Journal of Korean Powder Metallurgy Institute.2009; 16(5): 358.     CrossRef

Journal of Powder Materials : Journal of Powder Materials
TOP