High-throughput simulation combined machine learning search for optimum elemental composition in medium entropy alloy

In medium/high entropy alloys, their mechanical properties are strongly dependent on the chemicalelemental composition. Thus, searching for optimum elemental composition remains a critical issue to maximize the mechanical performance. However, this issue solved by traditional optimization process via "trial and error" or experiences of domain experts is extremely difficult. Here we propose an approach based on high-throughput simulation combined machine learning to obtain medium entropy alloys with high strength and low cost. This method not only obtains a large amount of data quickly and accurately,but also helps us to determine the relationship between the composition and mechanical properties.The results reveal a vital importance of high-throughput simulation combined machine learning to find best mechanical properties in a wide range of elemental compositions for development of alloys with expected performance.

Chemical-element-distribution-mediated deformation partitioning and its control mechanical behavior in high-entropy alloys

The chemical element distributions always strongly affect the deformation mechanisms and mechanical properties of alloying materials.However,the detailed atomic origin still remains unknown in highentropy alloys(HEAs)with a stable random solid solution.Here,considering the effect of elemental fluctuation distribution,the deformation behavior and mechanical response of the widely-studied equimolar random Co Cr Fe Mn Ni HEA are investigated by atomic simulations combined with machine learning and micro-pillar compression experiments.The elemental anisotropy factor is proposed,and then used to evaluate the chemical element distribution.The experimental and simulation results show that the local variations of chemical compositions exist and play a critical role in the deformation partitioning and mechanical properties.The high strength and good plasticity of HEAs are obtained via tuning the chemical element distributions,and the optimal elemental anisotropy factor ranges from 2.9 to 3 using machine learning.This trend can be attributed to the cooperative mechanisms depending on the local variational composition:massive partial dislocation multiplication at an initial stage of plastic deformation,and the inhibition of localized shear banding via the nucleation of deformation twinning at a later stage.Using the new insights gained here,it would be possible to create new metallic alloys with superior properties through thermal-mechanical treatment to tailoring the chemical element distribution.