EUVIMEDEUVIMED entdecken
Crossref

Adaptive regularized hybrid physics-informed neural networks for large-gradient problems

Tingjie Li, Supei Zheng, Fengli Hu, Xiaoli Lu, Doudou Xu, Xiaohan Cheng, Xueli Song

Physics of Fluids · 01.08.2026 · 38 (8)

DOI: 10.1063/5.0338767 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 06.08.2026. Verfasst von Tingjie Li und 6 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: Natural Science Basic Research Program of Shaanxi Province, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the issues of insufficient accuracy and susceptibility to numerical oscillations in traditional physics-informed neural networks (PINNs) when solving large-gradient problems of hyperbolic conservation laws, this paper proposes an adaptive regularized hybrid PINN (ARH-PINN) to accurately capture large-gradient fields such as shock waves and suppress numerical oscillations. The ARH-PINNs method introduces a novel neural network architecture that integrates a Fourier embedding layer, a multi-layer perceptron, and a radial basis function layer to effectively capture both the global features and local structures of solutions to hyperbolic conservation laws. To improve the solution accuracy of large-gradient fields such as shock waves and suppress numerical oscillations, we propose an adaptive regularization strategy based on a compression indicator and a sharpness indicator and further conduct a sensitivity analysis of the associated parameters. To balance convergence speed and numerical stability, we incorporate input symmetric normalization and learning rate annealing into the training pipeline. Verified through extensive numerical examples on classical one-dimensional (1D) and two-dimensional (2D) conservation laws, the proposed ARH-PINNs can accurately resolve large-gradient fields such as shock waves, while effectively suppressing non-physical oscillations and retaining low numerical dissipation.

Förderung

  • Natural Science Basic Research Program of Shaanxi Province
  • National Natural Science Foundation of China

Zitieren

APA

Li, T., Zheng, S., Hu, F., Lu, X., Xu, D., Cheng, X., & Song, X. (2026). Adaptive regularized hybrid physics-informed neural networks for large-gradient problems. Physics of Fluids, 38(8). https://doi.org/10.1063/5.0338767

Vancouver

Li T, Zheng S, Hu F, Lu X, Xu D, Cheng X, et al. Adaptive regularized hybrid physics-informed neural networks for large-gradient problems. Physics of Fluids. 2026;38(8). doi:10.1063/5.0338767

BibTeX
@article{Li2026,
  author = {Li, Tingjie and Zheng, Supei and Hu, Fengli and Lu, Xiaoli and Xu, Doudou and Cheng, Xiaohan and Song, Xueli},
  title = {Adaptive regularized hybrid physics-informed neural networks for large-gradient problems},
  journal = {Physics of Fluids},
  year = {2026},
  volume = {38},
  number = {8},
  doi = {10.1063/5.0338767}
}
Kostenlos starten →