Physics-guided Inverse Design of Co-based Superalloys Using Machine Learning and Multi-objective Optimization for Enhanced γ' Solvus TemperatureNew

This paper presents a physics-informed machine learning framework for the inverse design of Co-based superalloys targeting higher γ' solvus temperature while accounting for alloy density. The vast compositional design space and complex interactions among alloying elements governing gamma-prime phase stability present significant challenges in discovering next-generation superalloys. Four descriptors are employed to capture the essential physics of γ' phase stability.