About this Abstract |
| Meeting |
2027 TMS Annual Meeting & Exhibition
|
| Symposium
|
Microstructure-Sensitive Design and Advanced Characterization: An MPMD/SMD Symposium Honoring David T. Fullwood
|
| Presentation Title |
Spectral Decomposition, Video Games, and Transformers for Microstructure Design |
| Author(s) |
Oliver Johnson, Christopher W Adair |
| On-Site Speaker (Planned) |
Oliver Johnson |
| Abstract Scope |
Dr. David T. Fullwood has made significant contributions to the field of microstructure design. The methods he helped to develop involve the combination of probability density functions and spectral decomposition to construct structure-property linkages which enable efficient searching of the design space. In this talk we will discuss recent work that extends these techniques to enable the representation and spectral decomposition of interfacial networks. We first demonstrate the utility of these techniques for characterization of grain boundary networks. We then show how these network representations can be combined with citizen-science video games and custom microstructure transformer models to create a new approach to microstructure design. In this approach, AI models learn to solve high-dimensional configurational optimization problems by emulating human solution strategies. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, ICME, Machine Learning |