Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911856701997056 |
|---|---|
| author | Patel, Ravi Safta, Cosmin Jones, Reese E. |
| author_facet | Patel, Ravi Safta, Cosmin Jones, Reese E. |
| contents | Composite materials with different microstructural material symmetries are common in engineering applications where grain structure, alloying and particle/fiber packing are optimized via controlled manufacturing. In fact these microstructural tunings can be done throughout a part to achieve functional gradation and optimization at a structural level. To predict the performance of particular microstructural configuration and thereby overall performance, constitutive models of materials with microstructure are needed.
In this work we provide neural network architectures that provide effective homogenization models of materials with anisotropic components. These models satisfy equivariance and material symmetry principles inherently through a combination of equivariant and tensor basis operations. We demonstrate them on datasets of stochastic volume elements with different textures and phases where the material undergoes elastic and plastic deformation, and show that the these network architectures provide significant performance improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17584 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response Patel, Ravi Safta, Cosmin Jones, Reese E. Materials Science Machine Learning Composite materials with different microstructural material symmetries are common in engineering applications where grain structure, alloying and particle/fiber packing are optimized via controlled manufacturing. In fact these microstructural tunings can be done throughout a part to achieve functional gradation and optimization at a structural level. To predict the performance of particular microstructural configuration and thereby overall performance, constitutive models of materials with microstructure are needed. In this work we provide neural network architectures that provide effective homogenization models of materials with anisotropic components. These models satisfy equivariance and material symmetry principles inherently through a combination of equivariant and tensor basis operations. We demonstrate them on datasets of stochastic volume elements with different textures and phases where the material undergoes elastic and plastic deformation, and show that the these network architectures provide significant performance improvements. |
| title | Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2404.17584 |