Physics Informed Neural Networks for heat conduction with phase change - Centre Henri Lebesgue
Pré-Publication, Document De Travail Année : 2024

Physics Informed Neural Networks for heat conduction with phase change

Résumé

We study numerical algorithms to solve a specific Partial Differential Equation (PDE), namely the Stefan problem, using Physics Informed Neural Networks (PINNs). This problem describes the heat propagation in a liquid-solid phase change system. It implies a heat equation and a discontinuity at the interface where the phase change occurs. In the context of PINNs, this model leads to difficulties in the learning process, especially near the interface of phase change. We present different strategies that can be used in this context. We illustrate our results and compare with classical solvers for PDEs (finite differences).

Fichier principal
Vignette du fichier
main.pdf (878.59 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04739339 , version 1 (17-10-2024)

Identifiants

Citer

Bahae-Eddine Madir, Francky Luddens, Corentin Lothodé, Ionut Danaila. Physics Informed Neural Networks for heat conduction with phase change. 2024. ⟨hal-04739339⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More