| About this Abstract |
| Meeting |
2022 TMS Annual Meeting & Exhibition
|
| Symposium
|
Mechanical Behavior and Degradation of Advanced Nuclear Fuel and Structural Materials
|
| Presentation Title |
N-32: Dynamics of Helium Bubbles during Thermal Annealing: A Data-driven Approach |
| Author(s) |
Kory Durell Burns, Kayvon Tadj, Assel Aitkaliyeva, Khalid Hattar, Mary Scott |
| On-Site Speaker (Planned) |
Kory Durell Burns |
| Abstract Scope |
Helium atoms are immiscible in most metals and can diffuse until they become trapped, agglomerate, and form helium bubbles. With additional energy, these bubbles can also migrate and coalesce into large voids of various size and shapes at grain boundaries, surfaces, or in the matrix. This study aims to couple in-situ transmission electron microscopy (TEM) with deep learning methods to gain a richer understanding of helium bubbles evolution in extreme environments. First, we implant He atoms into a Palladium target and verify their presence. Then, we use in-situ TEM annealing to track the movement and changes in areal density, size, and shape of the resulting cavities. Finally, we employ a U-Net model to characterize the annotated micrographs in their completeness. We expect this method to become widely adopted to help unveil the underlying physics in in-situ TEM experiments. SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
High-Temperature Materials, Machine Learning, Characterization |