Explainable machine learning-enabled dual-objective design of γ' phase characteristic parameters in γ'-strengthened Co-based superalloys

The high-temperature performance of Co-based superalloys is primarily dictated by the coarsening kinetics and volume fraction of the γ′ phase. To simultaneously optimize these two interrelated microstructural parameters, we propose a dual-objective design framework that integrates explainable machine learning (XML), multi-fidelity data augmentation, and SHapley Additive exPlanations (SHAP)-based interpretability. For γ′ phase coarsening rate constant (Kr), a small experimental dataset was expanded using medium-fidelity simulations and further balanced with low-fidelity synthetic samples. For γ′ volume fraction (Vγ′), synthetic oversampling was applied to a larger dataset to mitigate distribution imbalance. ML models trained on these augmented datasets achieved high predictive accuracy, with SHAP analysis providing interpretable insights. Guided by these insights, several new compositions were proposed and validated. The optimal composition, Co-30Ni-10Al-3Ti-4Ta-5Cr-2Mo-1V (at.%), achieves a low Kr of 0.756 ± 0.06 nm2·s-1 and a high Vγ′ of exceeding 70% at 1000 °C, while also fulfills multiple other critical design criteria, offering a promising route for next-generation Co-based superalloys.