Journal
JOURNAL OF COMPUTATIONAL PHYSICS
Volume 473, Issue -, Pages -Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jcp.2022.111768
Keywords
Scientific machine learning; Deep learning; Data-driven modeling; Asymptotic expansion; Convective transport
Ask authors/readers for more resources
Physics-informed neural networks (PINNs) have become popular for scientific machine learning and differential equation modeling. This study introduces boundary-layer PINN (BL-PINN), which treats thin boundary layers as singular perturbation problems. By incorporating classical perturbation theory, BL-PINN employs different parallel PINN networks to approximate the boundary layer problem in both inner and outer regions. BL-PINN outperforms traditional PINN and other extensions such as XPINN in various benchmark problems, providing accurate solutions.
Physics-informed neural networks (PINNs) are a recent trend in scientific machine learning research and modeling of differential equations. Despite progress in PINN research, large gradients and highly nonlinear patterns remain challenging to model. Thin boundary layer problems are prominent examples of large gradients that commonly arise in transport problems. In this study, boundary-layer PINN (BL-PINN) is proposed to enable a solution to thin boundary layers by considering them as a singular perturbation problem. Inspired by the classical perturbation theory and asymptotic expansions, BL-PINN is designed to replicate the procedure in singular perturbation theory. Namely, different parallel PINN networks are defined to represent different orders of approximation to the boundary layer problem in the inner and outer regions. In different benchmark problems (forward and inverse), BL-PINN shows superior performance compared to the traditional PINN approach and is able to produce accurate results, whereas the classical PINN approach could not provide meaningful solutions. BL-PINN also demonstrates significantly better results compared to other extensions of PINN such as the extended PINN (XPINN) approach. The natural incorporation of the perturbation parameter in BL-PINN provides the opportunity to evaluate parametric solutions without the need for retraining. BL-PINN demonstrates an example of how classical mathematical theory could be used to guide the design of deep neural networks for solving challenging problems.(c) 2022 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available