Welding repair of cracks in FSX-414 cobalt-based alloy, used in high-temperature components, poses significant challenges due to the presence of surface oxide films within the cracks. By comparing the formation of oxide films on the external surface and inside the narrow crevice of FSX-414 alloys preserved at 900 °C for up to 1000 h, we found that the oxide film growth rate on the external surface was slightly larger than that inside the narrow crevice, and the latter slowed down after 672 h. Additionally, the oxide films on both surfaces were mainly composed of O and Cr elements, providing excellent protection to the underlying metal and resulting in minimal internal oxidation. A compositional transition region formed between the oxide film and the base metal. The width of the transition region decreased with heating duration and was narrower in the external surface sample, leading to a steeper composition gradient between the oxide film and the inner metal. With prolonged exposure, increasing numbers of “pores” rich in W and O appeared near the oxide films, creating channels that connect the oxide layer with the internal metal and accelerate material degradation. “Pores” extended deeper into the metal within the narrow crevice compared to those on the surface. Prior to welding repair, channels composed of W and O near the oxide films must be cleaned along with the oxide layer itself, and the removal of oxide from narrow cracks poses greater difficulty.

The multi-objective optimization of multicomponent superalloys has long been impeded by not only the complex interactions among multiple elements but also the low efficiency and high cost of traditional trial-and-error methods. To address this issue, this study proposed a thermodynamic calculation data-driven optimization framework that integrates machine learning (ML) and multi-objective screening based on domain knowledge. The core of this methodology involves introducing a commercial reference alloy and rapidly generating a large-scale thermodynamic dataset through ML models. After training, the ML models were verified to be more efficient at predicting phase transition temperatures and γ′ volume fractions than the CALPHAD methods. Focusing on the mechanical properties, critical strength indices, including solid solution strengthening, precipitation strengthening, and creep resistance based on the calculated γ/γ′ two-phase compositions, were compared with the reference alloy and set as the critical screen criteria. Optimal alloys were selected from the 388,000 candidates. Compared with the reference alloy, two new alloys were experimentally verified to have superior or comparable compressive yield strength and creep resistance at 900 °C at the expense of oxidation resistance and density, while maintaining comparable cost. This work demonstrates the significant potential of combining high-throughput thermodynamic data with intelligent multi-objective optimization to accelerate the development of new alloys with tailored property profiles.