Achieving a synergistic optimization of high strength and excellent ductility remains a central challenge in the design of medium-entropy alloys (MEAs). This paper proposes an integrated MD-ML strategy to accelerate the compositional design of NiCoCr MEAs and elucidate their micro-deformation mechanisms. Through efficient ML-based screening in the multi-dimensional compositional space, a non-equiatomic composition, Ni 51.57 Co 43.3 Cr 5.13 , is predicted to possess high yield strength potential. Subsequently, MD simulations validated the mechanical superiority of this composition and systematically elucidated the micro-deformation mechanisms across different alloy compositions. The results indicate that the mechanical responses are primarily governed by stacking fault energy (SFE). Specifically, the low-SFE Ni 40 Co 15 Cr 45 alloy exhibits lower yield strength due to premature phase transformation, whereas the Ni 60 Co 10 Cr 30 alloy, with high transformation propensity, undergoes phase instability after yielding. In contrast, the ML-optimized Ni 51.57 Co 43.3 Cr 5.13 exhibits an ideal dynamic equilibrium mechanism. Its elevated shear modulus significantly enhances yield strength; meanwhile, during plastic deformation, a moderate phase transformation rate facilitates the continuous proliferation of Shockley partial dislocations and the formation of a stable three-dimensional entanglement network, thereby achieving a synergistic improvement in both strength and ductility. This study not only validates the effectiveness of the shear modulus-targeted machine learning strategy for alloy composition design, but also provides clear microscopic mechanistic insights for the rational design of high-performance TRIP medium-entropy alloys.
Gu et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: