EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains

Yusuke Yamazaki, Ali Harandi, Mayu Muramatsu, Alexandre Viardin, Markus Apel, Tim Brepols, Stefanie Reese, Shahed Rezaei

Engineering with Computers · 2025-02 · 41 (1) · 1-29

DOI: 10.1007/s00366-024-02033-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering with Computers, online erschienen am 02.08.2024. Verfasst von Yusuke Yamazaki und 7 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, Deutsche Forschungsgemeinschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a novel finite element-based physics-informed operator learning framework that allows for predicting spatiotemporal dynamics governed by partial differential equations (PDEs). The Galerkin discretized weak formulation is employed to incorporate physics into the loss function, termed finite operator learning (FOL), along with the implicit Euler time integration scheme for temporal discretization. A transient thermal conduction problem is considered to benchmark the performance, where FOL takes a temperature field at the current time step as input and predicts a temperature field at the next time step. Upon training, the network successfully predicts the temperature evolution over time for any initial temperature field at high accuracy compared to the solution by the finite element method (FEM) even with a heterogeneous thermal conductivity and arbitrary geometry. The advantages of FOL can be summarized as follows: First, the training is performed in an unsupervised manner, avoiding the need for large data prepared from costly simulations or experiments. Instead, random temperature patterns generated by the Gaussian random process and the Fourier series, combined with constant temperature fields, are used as training data to cover possible temperature cases. Additionally, shape functions and backward difference approximation are exploited for the domain discretization, resulting in a purely algebraic equation. This enhances training efficiency, as one avoids time-consuming automatic differentiation in optimizing weights and biases while accepting possible discretization errors. Finally, thanks to the interpolation power of FEM, any arbitrary geometry with heterogeneous microstructure can be handled with FOL, which is crucial to addressing various engineering application scenarios.

Förderung

  • Japan Society for the Promotion of Science
  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Yamazaki, Y., Harandi, A., Muramatsu, M., Viardin, A., Apel, M., Brepols, T., Reese, S., & Rezaei, S. (2025). A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains. Engineering with Computers, 41(1), 1-29. https://doi.org/10.1007/s00366-024-02033-8

Vancouver

Yamazaki Y, Harandi A, Muramatsu M, Viardin A, Apel M, Brepols T, et al. A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains. Engineering with Computers. 2025;41(1):1-29. doi:10.1007/s00366-024-02033-8

BibTeX
@article{Yamazaki2025,
  author = {Yamazaki, Yusuke and Harandi, Ali and Muramatsu, Mayu and Viardin, Alexandre and Apel, Markus and Brepols, Tim and Reese, Stefanie and Rezaei, Shahed},
  title = {A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains},
  journal = {Engineering with Computers},
  year = {2025},
  volume = {41},
  number = {1},
  pages = {1--29},
  doi = {10.1007/s00366-024-02033-8}
}
Kostenlos starten →