EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Grid residual adaptive resampling for physics-informed neural networks to solve incompressible Navier–Stokes equations

Lei Gao, Dan Zhang, Yaoran Chen, Yihui Tu, Xiangyu Zhang, Xiaowei Li

Journal of Applied Physics · 21.04.2025 · 137 (15)

DOI: 10.1063/5.0253222 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Physics, online erschienen am 16.04.2025. Verfasst von Lei Gao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Pujiang National Laboratory, Shanghai University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aims to tackle the challenges of nonlinearity and coupling that Physics-Informed Neural Networks (PINNs) encounter when solving the incompressible Navier–Stokes equations. The research core is centered around optimizing the sampling strategy of residual collocation points to enhance PINNs’ capability of capturing the key features of the Navier–Stokes solutions. To this end, we propose a Grid Residual Adaptive Resampling (GRAR) strategy to improve the accuracy of PINNs in solving the Navier–Stokes equations. The GRAR-PINN method selectively samples residual collocation points based on grid residual values, allowing it to more effectively capture the essential characteristics of the Navier–Stokes solutions. To validate the effectiveness of this approach, we carried out numerical experiments using two-dimensional steady Kovasznay flow and two-dimensional triangular cylinder flow. The results show that the GRAR-PINN method can significantly enhance the accuracy of PINNs in solving the Navier–Stokes equations with relatively fewer residual collocation points through continuous resampling. This method not only alleviates the problem of repeatedly adjusting the number of residual collocation points but also addresses the challenge of capturing the key features of the Navier–Stokes solutions using PINNs.

Förderung

  • National Natural Science Foundation of China
  • Pujiang National Laboratory
  • Shanghai University

Zitieren

APA

Gao, L., Zhang, D., Chen, Y., Tu, Y., Zhang, X., & Li, X. (2025). Grid residual adaptive resampling for physics-informed neural networks to solve incompressible Navier–Stokes equations. Journal of Applied Physics, 137(15). https://doi.org/10.1063/5.0253222

Vancouver

Gao L, Zhang D, Chen Y, Tu Y, Zhang X, Li X. Grid residual adaptive resampling for physics-informed neural networks to solve incompressible Navier–Stokes equations. Journal of Applied Physics. 2025;137(15). doi:10.1063/5.0253222

BibTeX
@article{Gao2025,
  author = {Gao, Lei and Zhang, Dan and Chen, Yaoran and Tu, Yihui and Zhang, Xiangyu and Li, Xiaowei},
  title = {Grid residual adaptive resampling for physics-informed neural networks to solve incompressible Navier–Stokes equations},
  journal = {Journal of Applied Physics},
  year = {2025},
  volume = {137},
  number = {15},
  doi = {10.1063/5.0253222}
}
Kostenlos starten →