Interpretable machine learning-based stretch formability prediction of magnesium alloys

This study involved the development of an interpretable prediction framework to access the stretch formability of AZ31 magnesium alloys through the combination of the extreme gradient boosting (XGBoost) model with the sparrow search algorithm (SSA). Eleven features were extracted from the microstructures (e.g., grain size (GS), maximum pole intensity ( I_\mathrmm\mathrma\mathrmx ), degree of texture dispersion (μ), radius of maximum pole position (r), and angle of maximum pole position (A)), mechanical properties (e.g., tensile yield strength (TYS), ultimate tensile strength (UTS), elongation-to-failure (EL), and strength difference (∆S)) and test conditions (e.g., sheet thickness (t) and punch speed (v)) in the data collected from the literature and experiments. Pearson correlation coefficient and exhaustive screening methods identified ten key features (not including UTS) as the final inputs, and they enhanced the prediction accuracy of Index Erichsen (IE), which served as the model’s output. The newly developed SSA-XGBoost model exhibited an improved prediction performance, with a goodness of fit (R²) of 0.91 compared with traditional machine learning models. A new dataset (four samples) was prepared to validate the reliability and generalization capacity of this model, and below 5% errors were observed between predicted and experimental IE values. Based on this result, the quantitative relationship between the key features and IE values was established via Shapley additive explanation method and XGBoost feature importance analysis. I_\mathrmm\mathrma\mathrmx , TYS, EL, r, GS, and ΔS showed a crucial influence on the IE of 10 input features. This work offers a reliable and accurate tool for the prediction of the stretch formability of AZ31 magnesium alloys and provides insights into the development of high-formable magnesium alloys.