Olson challenged students to develop a printable aluminum alloy stronger than any that existed at the time. Aluminum's strength depends heavily on its microstructure, particularly the size and density of tiny internal features called "precipitates." Smaller, more closely packed precipitates generally result in a stronger metal.
Students used simulations to test different combinations of elements and concentrations, attempting to predict which mixtures would produce the strongest alloy. Despite extensive modeling, the effort did not outperform existing printable aluminum designs. That outcome prompted Taheri-Mousavi to consider a different approach.
"At some point, there are a lot of things that contribute nonlinearly to a material's properties, and you are lost," Taheri-Mousavi says. "With machine-learning tools, they can point you to where you need to focus, and tell you for example, these two elements are controlling this feature. It lets you explore the design space more efficiently."
Cool, thanks!