Machine learning-driven insights into the microstructure and properties of high-entropy alloys

Xiaoyi Zhang, Wenhan Zhou, Xiang Li, Tong Xu, Yongzhen Yu, Lei Zheng, Guanhua Jin, Shengli Zhang,
Machine learning-driven insights into the microstructure and properties of high-entropy alloys,
Advanced Powder Materials,
Volume 4, Issue 5,
2025,
100331,
ISSN 2772-834X,
https://doi.org/10.1016/j.apmate.2025.100331.
(https://www.sciencedirect.com/science/article/pii/S2772834X25000673)
Abstract: High entropy alloys (HEAs) have recently become a popular category of alloys, composed of five or more elements. These alloys are of particular interest in the field of materials due to their unique structure and excellent properties. However, the multi-component nature of these alloys poses challenges to traditional calculation methods, necessitating the development of alternative approaches for their analysis. Machine learning, a branch of artificial intelligence, has emerged as a promising solution to address the complexity inherent in the composition and structure of HEAs. The present review focuses on the fundamental definition and process of machine learning and its application in the research field of HEAs. The primary focus of this research field is the prediction of phase structure, hardness, strength, thermodynamic properties, and catalytic properties. In addition, future perspectives on the challenges in this research area are also presented.
Keywords: High entropy alloys; Machine learning; Materials computation; Structural design; Physical property prediction