Machine learning-assisted composition design of W-free Co-based superalloys with high γ′-solvus temperature and low density

Abstract

Developing materials with multiple desired characteristics is a tremendous challenge, particularly in an elaborate material system. Herein, a machine learning assisted material design strategy was applied to simultaneously optimize dual target attributes by considering γ′ solvus temperature and alloy density of multi-component Co-based superalloys. To verify the soundness of our strategy, four alloys were selected and experimentally synthesized from >510,000 candidates, each of them possessing γ′ solvus temperature exceeding 1200 °C and alloy density below 8.3 g/cm3. Of those, Co–35Ni–12Al–5Ti–3V–3Cr–2Ta–2Mo (at.%) possesses the highest γ′ solvus temperature of 1250 °C and lower density of 8.2 g/cm3. This article validates a straightforward strategy to guide rapid discovery and fabrication of multi-component materials with desired dual-performance characteristics.