EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Homogenization With Guaranteed Bounds via Primal‐Dual Physically Informed Neural Networks

Liya Gaynutdinova, Ondřej Rokoš, Martin Doškář, Ivana Pultarová

International Journal for Numerical Methods in Engineering · 30.03.2026 · 127 (6)

DOI: 10.1002/nme.70302 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal for Numerical Methods in Engineering, online erschienen am 17.03.2026. Verfasst von Liya Gaynutdinova und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerstvo Školství, Mládeže a Tělovýchovy, České Vysoké Učení Technické v Praze, Grantová Agentura České Republiky.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physics‐informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs) relevant to multiscale modeling, but they often fail when applied to materials with discontinuous coefficients, such as media with piecewise constant properties. This paper introduces a dual formulation for the PINN framework to improve the reliability of the homogenization of periodic thermo‐conductive composites, for both strong and variational (weak) formulations. The dual approach facilitates the derivation of guaranteed upper and lower error bounds, enabling more robust detection of PINN failure. We compare standard PINNs applied to smoothed material approximations with variational PINNs (VPINNs) using both spectral and neural network‐based test functions. Our results indicate that while strong‐form PINNs may outperform VPINNs in controlled settings, they are sensitive to material discontinuities and may fail without clear diagnostics. In contrast, VPINNs accommodate piecewise constant material parameters directly but require careful selection of test functions to avoid instability. Dual formulation serves as a reliable indicator of convergence quality, and its integration into PINN frameworks enhances their applicability to homogenization problems in micromechanics.

Förderung

  • Ministerstvo Školství, Mládeže a Tělovýchovy
  • České Vysoké Učení Technické v Praze
  • Grantová Agentura České Republiky

Zitieren

APA

Gaynutdinova, L., Rokoš, O., Doškář, M., & Pultarová, I. (2026). Homogenization With Guaranteed Bounds via Primal‐Dual Physically Informed Neural Networks. International Journal for Numerical Methods in Engineering, 127(6). https://doi.org/10.1002/nme.70302

Vancouver

Gaynutdinova L, Rokoš O, Doškář M, Pultarová I. Homogenization With Guaranteed Bounds via Primal‐Dual Physically Informed Neural Networks. International Journal for Numerical Methods in Engineering. 2026;127(6). doi:10.1002/nme.70302

BibTeX
@article{Gaynutdinova2026,
  author = {Gaynutdinova, Liya and Rokoš, Ondřej and Doškář, Martin and Pultarová, Ivana},
  title = {Homogenization With Guaranteed Bounds via Primal‐Dual Physically Informed Neural Networks},
  journal = {International Journal for Numerical Methods in Engineering},
  year = {2026},
  volume = {127},
  number = {6},
  doi = {10.1002/nme.70302}
}
Kostenlos starten →