Abstract The unique long-range disordered atomic arrangement inherent in amorphous materials endows them with a range of superior properties, rendering them highly promising for applications in catalysis, medicine, and battery technology, among other fields. Since not all materials can be synthesized into an amorphous structure, the composition design of amorphous materials holds significant importance. Machine learning offers a valuable alternative to traditional “trial-and-error” methods by predicting properties through experimental data, thus providing efficient guidance in material design. In this study, we develop a machine learning workflow to predict the critical casting diameter, glass transition temperature, and Young’s modulus for 45 ternary reported amorphous alloy systems. The predicted results have been organized into a database, enabling direct retrieval of predicted values based on compositional information. Furthermore, the applications of high glass forming ability region screening for specified system, multi-property target system screening and high glass forming ability region search through iteration are also demonstrated. By utilizing machine learning predictions, researchers can effectively narrow the experimental scope and expedite the exploration of compositions.
Read full abstract