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: | Marco Maurizi, Chao Gao, Filippo Berto |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-12-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-26424-3 |
Similar Items
-
Inverse design of truss lattice materials with superior buckling resistance
by: Marco Maurizi, et al.
Published: (2022-11-01) -
AMGNET: multi-scale graph neural networks for flow field prediction
by: Zhishuang Yang, et al.
Published: (2022-12-01) -
Materials fatigue prediction using graph neural networks on microstructure representations
by: Akhil Thomas, et al.
Published: (2023-08-01) -
Prediction of Flow Stress of Annealed 7075 Al Alloy in Hot Deformation Using Strain-Compensated Arrhenius and Neural Network Models
by: Hongbin Yang, et al.
Published: (2021-10-01) -
Improving materials property predictions for graph neural networks with minimal feature engineering
by: Guojing Cong, et al.
Published: (2023-01-01)