EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Sobolev–Information Perspective on Derivative-Observation-Augmented PINNs for Parameter Identification of Second-Order Dynamical Systems

Liwen Xu, Yixuan Lin

Axioms · 09.08.2026 · 15 (8) · 602

DOI: 10.3390/axioms15080602 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Axioms, online erschienen am 09.08.2026. Verfasst von Liwen Xu und 1 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yuxiu Innovation Project of NCUT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying parameters of dynamical systems from sparse measurements is a core task in structural health monitoring and vibration engineering. For second-order oscillators, standard physics-informed neural networks (PINNs) struggle because different parameter values can produce nearly identical displacement records, making the inverse problem ill-posed. We propose the derivative-observation-augmented PINN (D-PINN), which incorporates velocity measurements into the training loss to resolve this degeneracy. Three theoretical results support the method: a Sobolev-type inequality proves that constraining the velocity error automatically bounds the displacement error; a Fisher information analysis shows that velocity observations increase the information available for parameter estimation; and a residual-based estimate bounds the parameter error in terms of the solution accuracy and its derivatives. Experiments on linear, forced near-resonance, and Duffing oscillators (10 random seeds, 20,000 epochs) show that D-PINN reduces the damping coefficient relative error from 40% to 11.7% without any parameter prior. With a weak prior (μ0=3.2, a 20% deviation from the true value 4.0), the error drops further to 2.1%, a 19-fold improvement over standard PINN. We also analyze sensitivity to prior quality, derivative observation source, and measurement noise, and identify scenarios where derivative observations do not improve displacement fitting.

Förderung

  • Yuxiu Innovation Project of NCUT

Zitieren

APA

Xu, L., & Lin, Y. (2026). A Sobolev–Information Perspective on Derivative-Observation-Augmented PINNs for Parameter Identification of Second-Order Dynamical Systems. Axioms, 15(8), 602. https://doi.org/10.3390/axioms15080602

Vancouver

Xu L, Lin Y. A Sobolev–Information Perspective on Derivative-Observation-Augmented PINNs for Parameter Identification of Second-Order Dynamical Systems. Axioms. 2026;15(8):602. doi:10.3390/axioms15080602

BibTeX
@article{Xu2026,
  author = {Xu, Liwen and Lin, Yixuan},
  title = {A Sobolev–Information Perspective on Derivative-Observation-Augmented PINNs for Parameter Identification of Second-Order Dynamical Systems},
  journal = {Axioms},
  year = {2026},
  volume = {15},
  number = {8},
  pages = {602},
  doi = {10.3390/axioms15080602}
}
Kostenlos starten →