This repository provides numerical examples of physics-informed neural network-based computational solid mechanics framework.
Physics-informed neural network (PINN) has recently gained increasing interest in computational mechanics.
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.
Numerical examples include:
- 1D stretching plate problem (implemented by collocation and energy-based loss functions)
- 2D in-plain stretching plate problem (implemented by collocation loss function)
- 2D in-plain stretching plate problem (implemented by energy-based loss function)
- 3D streching cube problem (implemented by collocation loss function)
Information regarding the numerical examples, please refer to our paper.
- TensorFlow 2.8.0
- Keras 2.8.0
- SciPy 1.8.0
- Matplotlib 3.6.0
Now, the paper has been accepted by the International Journal of Computational Methods(IJCM):
https://doi.org/10.1142/S0219876223500135
Besides, the preprint version can be found at:
https://arxiv.org/abs/2210.09060
[1] J. Bai, H. Jeong, C.P. Batuwatta-Gamage, S. Xiao, Q. Wang, C.M. Rathnayaka, L. Alzubaidi, G.-R. Liu, Y. Gu, An introduction to programming Physics-Informed Neural Network-based computational solid mechanics, International Journal of Computational Methods, (2023), DOI: 10.1142/S0219876223500135.
or
[1] J. Bai, H. Jeong, C.P. Batuwatta-Gamage, S. Xiao, Q. Wang, C.M. Rathnayaka, L. Alzubaidi, G.-R. Liu, Y. Gu, An introduction to programming Physics-Informed Neural Network-based computational solid mechanics, Arxiv preprint arXiv:2210.09060, (2022).
For questions regarding the code, please contact: