Application of Machine Learning in Amorphous Alloys

Abstract

In the past few decades, traditional methods for developing amorphous alloys, such as empirical trial-and-error approaches and density functional theory (DFT)-based calculations, have enabled researchers to explore numerous amorphous alloy systems and investigate their properties. However, these methods are increasingly unable to meet the demands of modern research due to their long development cycles and low efficiency. In contrast, machine learning (ML) has gained widespread adoption in the design, analysis, and property prediction of amorphous alloys due to its advantages of low experimental cost, powerful performance, and short development cycles. This review focuses on four key applications of ML in amorphous alloys: (1) prediction of amorphous alloy phases, (2) prediction of amorphous composite phases, (3) prediction of glass-forming ability (GFA), and (4) prediction of material properties. Finally, we outline future directions for ML in materials science, including the development of more sophisticated models, integration with high-throughput experimentation, and the creation of standardized data-sharing platforms. These insights provide potential research directions and frameworks for subsequent studies in this field.

Keywords: amorphous alloys; glass-forming ability; machine learning; properties.

Figure 1

Number of published works on “machine learning” and “machine learning” + “material” (from January 1999 to September 2018) [7]. Copyright © 2019, Elsevier Ltd.

Figure 2

The relationship between the experimental Young’s modulus and the predicted values of the optimal model: (a) XGBoost; (b) RF; (c) SVR [90]. Copyright © 2020, Springer Nature.