EUVIMEDEUVIMED entdecken
Crossref

Comparative Analysis of PINN, Lagaris-Type PINN, and Finite Element Methods for Solving Heat Equations

A. Babni, I. Jamiai, A. Omari

Mathematical Modeling and Computing · 2026 · 13 (2) · 556-564

DOI: 10.23939/mmc2026.02.556 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Modeling and Computing, 2026. Verfasst von A. Babni und 2 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a comparative study of three numerical methods for solving partial differential equations: the classical finite element method (FEM), the standard Physics-Informed Neural Networks (PINNs), and a modified PINN approach inspired by Lagaris-method, which enforces boundary conditions exactly. Two benchmark problems are considered: the one-dimensional heat equation and the heat equation on an annular domain. For each case, the methods are implemented and compared based on accuracy and the spatial distribution of the absolute error.

Zitieren

APA

Babni, A., Jamiai, I., & Omari, A. (2026). Comparative Analysis of PINN, Lagaris-Type PINN, and Finite Element Methods for Solving Heat Equations. Mathematical Modeling and Computing, 13(2), 556-564. https://doi.org/10.23939/mmc2026.02.556

Vancouver

Babni A, Jamiai I, Omari A. Comparative Analysis of PINN, Lagaris-Type PINN, and Finite Element Methods for Solving Heat Equations. Mathematical Modeling and Computing. 2026;13(2):556-564. doi:10.23939/mmc2026.02.556

BibTeX
@article{Babni2026,
  author = {Babni, A. and Jamiai, I. and Omari, A.},
  title = {Comparative Analysis of PINN, Lagaris-Type PINN, and Finite Element Methods for Solving Heat Equations},
  journal = {Mathematical Modeling and Computing},
  year = {2026},
  volume = {13},
  number = {2},
  pages = {556--564},
  doi = {10.23939/mmc2026.02.556}
}
Kostenlos starten →