Cargando…
Predicting stress, strain and deformation fields in materials and structures with graph neural networks
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...
Autores principales: | Maurizi, Marco, Gao, Chao, Berto, Filippo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9759553/ https://www.ncbi.nlm.nih.gov/pubmed/36528676 http://dx.doi.org/10.1038/s41598-022-26424-3 |
Ejemplares similares
-
Graph neural networks for materials science and chemistry
por: Reiser, Patrick, et al.
Publicado: (2022) -
Quantum Graph Neural Network Models for Materials Search
por: Ryu, Ju-Young, et al.
Publicado: (2023) -
Materials fatigue prediction using graph neural networks on microstructure representations
por: Thomas, Akhil, et al.
Publicado: (2023) -
Combining Self-Organizing and Graph Neural Networks for Modeling Deformable Objects in Robotic Manipulation
por: Valencia, Angel J., et al.
Publicado: (2020) -
Scalable deeper graph neural networks for high-performance materials property prediction
por: Omee, Sadman Sadeed, et al.
Publicado: (2022)