About this Abstract |
Meeting |
MS&T21: Materials Science & Technology
|
Symposium
|
High Entropy Materials: Concentrated Solid Solutions, Intermetallics, Ceramics, Functional Materials and Beyond II
|
Presentation Title |
Now On-Demand Only - Computationally Guided High Entropy Alloy Discovery |
Author(s) |
Kenneth D. Smith, John A Sharon, Ryan Deacon, Soumalya Sarkar |
On-Site Speaker (Planned) |
Kenneth D. Smith |
Abstract Scope |
High Entropy Alloys (HEA) with multiple principal elements together in solution have demonstrated enhanced properties that can rival or exceed conventional alloy systems. Given the large combinatorial composition space, computational tools are vital to sort through combinations and identify the most promising candidates. A variety of analytical and other relatively fast computational models are available to help identify candidates. We will describe our machine learned based framework that assists in identifying candidates. By incorporating a combination of objectives and constraints, this machine learning approach enables us to set initial criteria and identify promising composition families based on targeted component performance metrics. The framework can be further bolstered through incorporating data. Examples of using the framework to identify potential new HEA candidates will be discussed along with the role more detailed characterization and experimentation can contribute to accelerate HEA identification. |