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 |
Microstructure-Sensitive Design of Polycrystalline Materials |
| Author(s) |
David Montes De Oca Zapiain, Nicole Aragon, Aashique , Theron Rodgers, Hojun Lim |
| On-Site Speaker (Planned) |
David Montes De Oca Zapiain |
| Abstract Scope |
The properties and performance of polycrystalline metal alloys are greatly influenced by lower length scale details of the microstructure such as grain shape, size, orientation and its distribution. Therefore, microstructure-sensitive protocols are critical for understanding and designing alloys for specific properties and performance. In this work we present how the combination of spatial correlations obtained on Fourier representations of the microstructure with unsupervised learning enables the development of usable fingerprints that robustly capture salient microstructural features. Moreover, we validate that the obtained fingerprints set the basis for microstructure-sensitive design by allowing the establishment of accurate and computationally efficient surrogate models. These novel capabilities are demonstrated with the development of an accelerated damage prediction of polycrystalline alloys protocol, the establishment of a data-driven characterization of additive manufacturing components and by building an accelerated characterization of plastic anisotropy framework. SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525. SANDNoSAND2026-22998A. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, Machine Learning, Additive Manufacturing |