Machine learning-based identification method of new strengthening element and the study on Al-Zn-Mg-Cu-Zr-Hf alloy

In this study, we proposed a strengthening element screening method through integrating a machine learning-based property optimization model with strength descriptors of Al-Zn-Mg-Cu alloy. By comparing the predicted properties of alloys with different elements added, we found that the trace element Hf, beyond the dataset, can effectively improve the strength and toughness of Al-Zn-Mg-Cu alloy. According to the alloy optimization result, we fabricated a high-strength Al-Zn-Mg-Cu-Zr-Hf alloy with superior mechanical properties, including 816 MPa for tensile strength, 779 MPa for yield strength, and 9.1 % for elongation.