Four kinds of 7xxx series aluminum alloys with different Y contents were obtained by ordinary gravity casting. The effect of Y content on the microstructure and mechanical properties of as-cast and as-solutionized Al-7.9Zn-3Mg-2.4Cu-0.13Zr (wt.%) alloys were investigated by means of X-ray diffraction (XRD), electron backscattering diffraction (EBSD), scanning electron microscopy (SEM), energy dispersive spectrometer (EDS) and room-temperature tensile tests. The results shows that, in as-cast condition, Y element can refine the grain and reduce the content of Mg(Zn, Cu, Al)2 lamellar phases at the interdendritic. (Al, Zn)8Cu4Y block-shaped phases form in interdendritic regions. After solution treatment, the undissolved Mg(Zn, Cu, Al)2 phases evolved from lamellar to bulk-like which distribution in interdendritic, but no obvious change in (Al, Zn)8Cu4Y phase. The tensile testing results shows that the optimal Y content is 0.45 wt.%. At 0.45 wt.% Y, the ultimate tensile strength and elongation are 267 MPa and 2.4% in as-cast condition and 420 MPa and 3.6% in as-solutionized condition.

High-strength 2xxx series aluminum alloys (Al-Cu system) have been favored by the aerospace and railway transportation industries. Traditionally, developing new materials with targeted properties is guided by extensive experiments and expert experience, causing the development process to be dismayingly slow and expensive. Here, a Kriging model-based efficient global optimization(EGO) lgorithm is applied to search for new 2xxx series aluminum alloys with high tensile strength in a huge search space. After four iterations, the alloy's ultimate tensile strength increased by 60 MPa, which is higher than that of the best alloy in the initial data set. This study demonstrates the feasibility of using machine-learning to search for 2xxx alloys with good mechanical performance.