Prediction of Vickers hardness of amorphous alloys based on interpretable machine learning

Amorphous alloys are formed by liquid alloys under rapid cooling. Because there is no grain boundary, dislo-cation, and other defects, it shows excellent mechanical properties. Vickers hardness (HV) is one of its excellent properties. In this work, four machine learning models were applied for HV modeling. The input features are atomic fraction, structural features and load, respectively. The determination coefficients R2 of the Light Gradient Boosting Machine (LightGBM) model in the test set are 0.981 and 0.979, respectively, which is far superior to the other three models. The LightGBM model has the best generalization ability. In addition, the shapley additive explanations (SHAP) theory is introduced to improve the interpretability of model. An important discovery of SHAP theory is that XP1 and Tm1 are two most important features, each of which has a critical value. If XP1 and Tm1 of the alloy are in the correct region, which can improve HV.

Automated summary

Amorphous alloys are formed by rapid cooling of liquid alloys, showing excellent mechanical properties due to the absence of grain boundaries, dislocations, and other defects, with Vickers hardness (HV) being one of its outstanding properties. In this study, four machine learning models were applied for HV modeling using atomic fraction, structural features, and load as input features. The Light Gradient Boosting Machine (LightGBM) model achieved higher determination coefficients R2 of 0.981 and 0.979 in the test set compared to the other three models, indicating superior generalization ability. Additionally, the introduction of shapley additive explanations (SHAP) theory improved the interpretability of the model, highlighting XP1 and Tm1 as the two most important features with critical values for improving HV if they fall within the correct range.