An Introduction to Programming Physics-Informed Neural Network-Based Computational Solid Mechanics
Article
Article Title | An Introduction to Programming Physics-Informed Neural Network-Based Computational Solid Mechanics |
---|---|
ERA Journal ID | 36477 |
Article Category | Article |
Authors | Bai, Jinshuai, Jeong, Hyogu, Batuwatta-Gamage, C. P., Xiao, Shusheng, Wang, Qingxia, Rathnayaka, C.M., Alzubaidi, Laith, Liu, Gui-Rong and Gu, Yuantong |
Journal Title | International Journal of Computational Methods |
Journal Citation | 20 (10) |
Article Number | 2350013 |
Number of Pages | 29 |
Year | 2023 |
Publisher | World Scientific Publishing |
Place of Publication | Singapore |
ISSN | 0219-8762 |
1793-6969 | |
Digital Object Identifier (DOI) | https://doi.org/10.1142/S0219876223500135 |
Web Address (URL) | https://www.worldscientific.com/doi/10.1142/S0219876223500135 |
Abstract | Physics-informed neural network (PINN) has recently gained increasing interest in computational mechanics. This work extends the PINN to computational solid mechanics problems. Our focus will be on the investigation of various formulation and programming techniques, when governing equations of solid mechanics are implemented. Two prevailingly used physics-informed loss functions for PINN-based computational solid mechanics are implemented and examined. Numerical examples ranging from 1D to 3D solid problems are presented to show the performance of PINN-based computational solid mechanics. The programs are built via Python with TensorFlow library with step-by-step explanations and can be extended for more challenging applications. This work aims to help the researchers who are interested in the PINN-based solid mechanics solver to have a clear insight into this emerging area. The programs for all the numerical examples presented in this work are available at https://github.com/JinshuaiBai/PINN_Comp_Mech. |
Keywords | Physics-informed neural network; computational mechanics; deep learning |
ANZSRC Field of Research 2020 | 4602. Artificial intelligence |
Public Notes | File reproduced in accordance with the copyright policy of the publisher/author. |
Byline Affiliations | Queensland University of Technology |
University of Queensland | |
Centre for Applied Climate Sciences | |
University of the Sunshine Coast | |
University of Cincinnati, United States |
https://research.usq.edu.au/item/z2z88/an-introduction-to-programming-physics-informed-neural-network-based-computational-solid-mechanics
Restricted files
Accepted Version
64
total views3
total downloads0
views this month0
downloads this month