| About this Abstract |
| Meeting |
2025 TMS Annual Meeting & Exhibition
|
| Symposium
|
Artificial Intelligence Applications in Integrated Computational Materials Engineering
|
| Presentation Title |
Conditional Diffusion Models for Interlocking Metasurface Design |
| Author(s) |
Nathan Brown, Ben Young, Brad Boyce, Philip Noell |
| On-Site Speaker (Planned) |
Nathan Brown |
| Abstract Scope |
Interlocking metasurfaces (ILMs) are a novel class of mechanical metasurfaces created from arrays of interlocking features, offering a non-permanent, robust joining technology. ILM’s strength is determined by the constituent material, orientation, and topology of the latching unit cells. Furthermore, the unit cell topology can control heat transfer across a joint. This study optimized the ILM unit cell topologies using conditional diffusion models. The results demonstrated high-performing, non-intuitive design solutions, offering insights into ILM design for customizable mechanical and thermal properties. The successful application of conditional diffusion models in this work highlights their potential as a rapid, generalizable engineering design tool, urging the implementation of this method in multiple engineering applications. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Computational Materials Science & Engineering, Modeling and Simulation |