Predicting stress, strain and deformation fields in materials and structures with graph neural networks
Abstract Developing accurate yet fast computational tools to simulate complex physical phenomena is a long-standing problem. Recent advances in machine learning have revolutionized the way simulations are approached, shifting from a purely physics- to AI-based paradigm. Although impressive achieveme...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-26424-3 |
| _version_ | 1797980503731601408 |
|---|---|
| author | Marco Maurizi Chao Gao Filippo Berto |
| author_facet | Marco Maurizi Chao Gao Filippo Berto |
| author_sort | Marco Maurizi |
| collection | DOAJ |
| description | Abstract Developing accurate yet fast computational tools to simulate complex physical phenomena is a long-standing problem. Recent advances in machine learning have revolutionized the way simulations are approached, shifting from a purely physics- to AI-based paradigm. Although impressive achievements have been reached, efficiently predicting complex physical phenomena in materials and structures remains a challenge. Here, we present an AI-based general framework, implemented through graph neural networks, able to learn complex mechanical behavior of materials from a few hundreds data. Harnessing the natural mesh-to-graph mapping, our deep learning model predicts deformation, stress, and strain fields in various material systems, like fiber and stratified composites, and lattice metamaterials. The model can capture complex nonlinear phenomena, from plasticity to buckling instability, seemingly learning physical relationships between the predicted physical fields. Owing to its flexibility, this graph-based framework aims at connecting materials’ microstructure, base materials’ properties, and boundary conditions to a physical response, opening new avenues towards graph-AI-based surrogate modeling. |
| first_indexed | 2024-04-11T05:55:20Z |
| format | Article |
| id | doaj.art-5327fd52308c47daa8e74f28c9ee0d4a |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T05:55:20Z |
| publishDate | 2022-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-5327fd52308c47daa8e74f28c9ee0d4a2022-12-22T04:41:55ZengNature PortfolioScientific Reports2045-23222022-12-0112111210.1038/s41598-022-26424-3Predicting stress, strain and deformation fields in materials and structures with graph neural networksMarco Maurizi0Chao Gao1Filippo Berto2Department of Mechanical and Industrial Engineering, Norwegian University of Science and Technology (NTNU)Department of Mechanical and Industrial Engineering, Norwegian University of Science and Technology (NTNU)Department of Mechanical and Industrial Engineering, Norwegian University of Science and Technology (NTNU)Abstract Developing accurate yet fast computational tools to simulate complex physical phenomena is a long-standing problem. Recent advances in machine learning have revolutionized the way simulations are approached, shifting from a purely physics- to AI-based paradigm. Although impressive achievements have been reached, efficiently predicting complex physical phenomena in materials and structures remains a challenge. Here, we present an AI-based general framework, implemented through graph neural networks, able to learn complex mechanical behavior of materials from a few hundreds data. Harnessing the natural mesh-to-graph mapping, our deep learning model predicts deformation, stress, and strain fields in various material systems, like fiber and stratified composites, and lattice metamaterials. The model can capture complex nonlinear phenomena, from plasticity to buckling instability, seemingly learning physical relationships between the predicted physical fields. Owing to its flexibility, this graph-based framework aims at connecting materials’ microstructure, base materials’ properties, and boundary conditions to a physical response, opening new avenues towards graph-AI-based surrogate modeling.https://doi.org/10.1038/s41598-022-26424-3 |
| spellingShingle | Marco Maurizi Chao Gao Filippo Berto Predicting stress, strain and deformation fields in materials and structures with graph neural networks Scientific Reports |
| title | Predicting stress, strain and deformation fields in materials and structures with graph neural networks |
| title_full | Predicting stress, strain and deformation fields in materials and structures with graph neural networks |
| title_fullStr | Predicting stress, strain and deformation fields in materials and structures with graph neural networks |
| title_full_unstemmed | Predicting stress, strain and deformation fields in materials and structures with graph neural networks |
| title_short | Predicting stress, strain and deformation fields in materials and structures with graph neural networks |
| title_sort | predicting stress strain and deformation fields in materials and structures with graph neural networks |
| url | https://doi.org/10.1038/s41598-022-26424-3 |
| work_keys_str_mv | AT marcomaurizi predictingstressstrainanddeformationfieldsinmaterialsandstructureswithgraphneuralnetworks AT chaogao predictingstressstrainanddeformationfieldsinmaterialsandstructureswithgraphneuralnetworks AT filippoberto predictingstressstrainanddeformationfieldsinmaterialsandstructureswithgraphneuralnetworks |