| Abstract Scope |
Refractory High-Entropy Alloys (HEAs) are a promising class of materials for ultra-high-temperature applications, including energy generation from gas turbines. In addition to having exceptional mechanical properties at elevated temperatures, these materials can be highly tailored to individual applications by selecting the constituent elements. However, the relationship between elemental composition and function is challenging to understand and even harder to predict because it is nonlinear, high-dimensional, and results from physical phenomena at many scales. While conventional computational materials design has utilized physics-based models to iteratively test hypothesized material compositions in a search for improved ones, machine learning has recently become a standard methodology for rapid empirical, or “data-driven,” design. These methods allow for the exploration of incredibly large design spaces with competing objectives without requiring exhaustive computer simulation. In particular, we have worked on designing HEAs to be fabricated by spark plasma sintering while meeting an extensive list of mechanical property requirements. |