Physics-guided inverse design of Co-based superalloys using machine learning and multi-objective optimization for enhanced gamma-prime solvus temperature

This paper proposes a physics-informed machine learning framework for the inverse design of Co-based superalloys targeting enhanced gamma-prime solvus temperature. The approach incorporates four descriptors including atomic size mismatch (delta-MV) to represent complex interactions among alloying elements. A multi-objective optimization strategy is employed to balance gamma-prime solvus temperature improvements with alloy density constraints. The framework enables efficient exploration of the vast compositional design space for next-generation superalloys with superior high-temperature stability.