EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed Neural Networks for Excited Liquid Sloshing with Beating Response in Two- and Three-Dimensional Rectangular Tanks

Zhiqiang Luo

Symmetry · 27.05.2026 · 18 (6) · 917

DOI: 10.3390/sym18060917 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 27.05.2026. Verfasst von Zhiqiang Luo. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Graduate Education Reform Project of the 14th Five-Year Plan for Higher Education of Zhejiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper applies physics-informed neural networks (PINNs) to laterally excited liquid sloshing in a two-dimensional rectangular tank, where near-resonant forcing (ωe/ω1=0.9) produces a multi-frequency beating response with a period of approximately 10T1. Linearized potential flow theory governs the problem; the network learns the velocity potential φ(x,z,t) while the free-surface elevation η is injected analytically. Two training obstacles specific to forced sloshing are analyzed. First, a zero-solution trap arises because the trivial solution φ^=0 satisfies all equations except the free-surface conditions, whose residuals are roughly 10−4 times smaller than the Laplace residual; characteristic-scale normalization combined with loss weighting (λD=λK=100) breaks this trap. Second, spectral bias prevents standard MLPs from resolving the three co-existing frequencies (ω1, ωe, Δω); a Fourier time embedding that augments the input from 3 to 9 dimensions overcomes this limitation. Two additional techniques further reduce errors: a hard-wall boundary condition enforced exactly via a cos(πx/B) spatial embedding, which eliminates wall collocation points; and a gradient-enhanced Laplace regularizer (∥∇(∇2φ^)∥2) that constrains velocity smoothness through third-order automatic differentiation. An ablation study shows that these four techniques progressively reduce the horizontal velocity error from εu=12.46% to 0.84%. Results are validated against a viscous finite-difference benchmark. Over one beating cycle the errors are εη=0.15%, εu=0.84%, and εw=1.65%. A frequency parameter study across ωe/ω1 = 0.5–1.1 gives εη

Förderung

  • Graduate Education Reform Project of the 14th Five-Year Plan for Higher Education of Zhejiang Province

Zitieren

APA

Luo, Z. (2026). Physics-Informed Neural Networks for Excited Liquid Sloshing with Beating Response in Two- and Three-Dimensional Rectangular Tanks. Symmetry, 18(6), 917. https://doi.org/10.3390/sym18060917

Vancouver

Luo Z. Physics-Informed Neural Networks for Excited Liquid Sloshing with Beating Response in Two- and Three-Dimensional Rectangular Tanks. Symmetry. 2026;18(6):917. doi:10.3390/sym18060917

BibTeX
@article{Luo2026,
  author = {Luo, Zhiqiang},
  title = {Physics-Informed Neural Networks for Excited Liquid Sloshing with Beating Response in Two- and Three-Dimensional Rectangular Tanks},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {6},
  pages = {917},
  doi = {10.3390/sym18060917}
}
Kostenlos starten →