Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity
Abstract We report a deep learning method to predict high-resolution stress fields from material microstructures, using a novel class of progressive attention-based transformer diffusion models. We train the model with a small dataset of pairs of input microstructures and resulting atom...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer International Publishing
2023
|
| Online Access: | https://hdl.handle.net/1721.1/147114 |
| _version_ | 1826205906368462848 |
|---|---|
| author | Buehler, Markus J. |
| author2 | Massachusetts Institute of Technology. Laboratory for Atomistic and Molecular Mechanics |
| author_facet | Massachusetts Institute of Technology. Laboratory for Atomistic and Molecular Mechanics Buehler, Markus J. |
| author_sort | Buehler, Markus J. |
| collection | MIT |
| description | Abstract
We report a deep learning method to predict high-resolution stress fields from material microstructures, using a novel class of progressive attention-based transformer diffusion models. We train the model with a small dataset of pairs of input microstructures and resulting atomic-level Von Mises stress fields obtained from molecular dynamics (MD) simulations, and show excellent capacity to accurately predict results. We conduct a series of computational experiments to explore generalizability of the model and show that while the model was trained on a small dataset that featured samples of multiple cracks, the model can accurately predict distinct fracture scenarios such as single cracks, or crack-like defects with very different shapes. A comparison with MD simulations provides excellent comparison to the ground truth results in all cases. The results indicate that exciting opportunities that lie ahead in using progressive transformer diffusion models in the physical sciences, to produce high-fidelity and high-resolution field images.
Graphical abstract |
| first_indexed | 2024-09-23T13:20:55Z |
| format | Article |
| id | mit-1721.1/147114 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:20:55Z |
| publishDate | 2023 |
| publisher | Springer International Publishing |
| record_format | dspace |
| spelling | mit-1721.1/1471142024-01-08T20:44:48Z Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity Buehler, Markus J. Massachusetts Institute of Technology. Laboratory for Atomistic and Molecular Mechanics Massachusetts Institute of Technology. Center for Computational Science and Engineering Abstract We report a deep learning method to predict high-resolution stress fields from material microstructures, using a novel class of progressive attention-based transformer diffusion models. We train the model with a small dataset of pairs of input microstructures and resulting atomic-level Von Mises stress fields obtained from molecular dynamics (MD) simulations, and show excellent capacity to accurately predict results. We conduct a series of computational experiments to explore generalizability of the model and show that while the model was trained on a small dataset that featured samples of multiple cracks, the model can accurately predict distinct fracture scenarios such as single cracks, or crack-like defects with very different shapes. A comparison with MD simulations provides excellent comparison to the ground truth results in all cases. The results indicate that exciting opportunities that lie ahead in using progressive transformer diffusion models in the physical sciences, to produce high-fidelity and high-resolution field images. Graphical abstract 2023-01-17T13:32:30Z 2023-01-17T13:32:30Z 2023-01-12 2023-01-15T04:10:48Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/147114 Buehler, Markus J. 2023. "Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity." PUBLISHER_CC en https://doi.org/10.1557/s43578-023-00892-3 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer International Publishing Springer International Publishing |
| spellingShingle | Buehler, Markus J. Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity |
| title | Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity |
| title_full | Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity |
| title_fullStr | Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity |
| title_full_unstemmed | Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity |
| title_short | Predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity |
| title_sort | predicting mechanical fields near cracks using a progressive transformer diffusion model and exploration of generalization capacity |
| url | https://hdl.handle.net/1721.1/147114 |
| work_keys_str_mv | AT buehlermarkusj predictingmechanicalfieldsnearcracksusingaprogressivetransformerdiffusionmodelandexplorationofgeneralizationcapacity |