Determination of glass forming ability of bulk metallic glasses based on machine learning

Nowadays, the development of new bulk metallic glasses (BMGs) is still subject to repeated testing. To address this challenging problem, this paper proposes the random forest (RF) regression model for predicting glass forming ability (GFA) based on the 810 datapoints of the metal alloy composition dataset (including Tg, Tx, Tl, and Dmax, where Tg is the glass transition temperature, Tx the onset crystallization temperature, Tl the liquidus temperature or the offset temperature of melting, Dmax is the critical diameter). Various types of feature parameters related to GFA were first screened to identify the optimal features. Grid search was then used to optimize hyperparameters of the machine-learning (ML). The research suggests that the random forest (RF) regression model's accuracy has been improved, and our proposed approach has great potential in predicting the formation of the BMGs. Furthermore, this study also suggests that both characteristic temperature (Tg, Tx, and Tl) and topological structure parameters play an important role in describing the glass formation of alloys.

Automated summary

This study proposes a random forest regression model based on the metal alloy composition dataset to predict the glass forming ability of bulk metallic glasses. By screening feature parameters and optimizing hyperparameters, the accuracy of the model has been improved, revealing the importance of characteristic temperatures and topological structure parameters in describing the formation of alloy glasses.