Optimizing FeNiCrAlCu high entropy superalloy design: Integrating thermodynamic calculations, first-principles, and machine learning for enhanced stacking fault energy modeling

High-entropy superalloys (HESA) are promising alternatives to traditional superalloys, offering enhanced performance, greater sustainability, and increased cost-effectiveness for applications involving elevated temperatures. This research centers on Fe-based HESA, emphasizing the critical role of stacking fault energy (SFE) on the mechanisms of deformation and creep. By using Fe as the base alloy instead of Ni, the development becomes more economical. We introduce an innovative approach for predicting SFE through a combination of machine learning and computational thermodynamics. Additionally, first-principles calculations are employed to examine the effects of reducing Ni while incorporating Cu and Zr, which affect the elasticity, SFE, and electronic configuration. The results indicate that adding Cu increases ductility and reduces the ratio of stable and unstable SFE from 0.15 to 0.14. whereas reduced Ni content and enhanced Zr addition decrease the ratio of stable to unstable SFE from 0.18 to 0.17, thereby enhancing mechanical robustness at a small trade-off in ductility. Electronic configuration study reveals that Cu addition improves electron accumulation by 1.4%, reduces the available electronic states at the Fermi energy by 2 states/eV, weakens interatomic bonding, increases interlayer distance by 0.06 Å, and reduces SFE. Optimization of the Fe-based HESA configuration is feasible by adjusting Cr and Ni concentrations to achieve the desired SFE, substantially improving strength, hardness, and ductility under elevated temperatures. The calculated SFE data serves as the basis for a machine learning framework, with the neural network model achieving a Root Mean Squared Error (RMSE) of 1.75 and an accuracy of 0.99 in predicting SFE values and classifications. Synergizing data-driven models and computational thermodynamics provides a robust predictive model for SFE, enabling more accurate and efficient alloy design. The development of Fe-based HESA contributes to resource sustainability by reducing reliance on expensive and limited elements like Ni.