Simulating Castable Aluminum Alloy Microstructures with AlloyGAN Deep Learning Model

MaterialMaterials scientists have made progress in controlling alloy performance through microstructureMicrostructure quantification. However, attempts at numerically modeling microstructuresMicrostructure have failed due to the complex nature of the solidificationSolidification processProcess. In this research, we present the AlloyGAN deep learningDeep learning model to generate microstructuresMicrostructure for castable aluminum alloysAluminum alloys. This innovative model demonstrates its capacity to simulate the evolution of aluminum alloyAluminum alloys microstructuresMicrostructure in response to variations in composition and cooling ratesCooling rate. Specifically, it is successful to simulate various effects on castable aluminumAluminum, including: (1) the influence of Si and other elements on microstructuresMicrostructure, (2) the relationship between cooling rateCooling rate and Secondary Dendritic Arm Spacing, and (3) the impact of P/Sr elements on microstructuresMicrostructure. Our model delivers results that match the accuracy and robustness of traditional computational materials scienceComputational Materials Science & Engineering methods, yet significantly reduces computation time.