EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data-driven identification of latent port-Hamiltonian systems

Johannes Rettberg, Jonas Kneifl, Julius Herb, Patrick Buchfink, Jörg Fehr, Bernard Haasdonk

Computational Science and Engineering · 27.11.2025 · 2 (1)

DOI: 10.1007/s44207-025-00007-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Science and Engineering, online erschienen am 27.11.2025. Verfasst von Johannes Rettberg und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 92 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universität Stuttgart.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional physics-based modeling techniques involve high effort, e.g., time and expert knowledge, while data-driven methods often lack interpretability, structure, and sometimes reliability. To mitigate this, we present a data-driven system identification framework that derives models in the port-Hamiltonian (pH) formulation. This formulation is suitable for multi-physical systems while guaranteeing the useful system theoretical properties of passivity and stability. Our framework combines linear and nonlinear reduction with structured, physics-motivated system identification. In this process, high-dimensional state data obtained from possibly nonlinear systems serves as input for an autoencoder, which then performs two tasks: (i) nonlinearly transforming and (ii) reducing this data onto a low-dimensional latent space. In this space, a linear pH system that satisfies the pH properties per construction is parameterized by the weights of a neural network. The mathematical requirements are met by defining the pH matrices through Cholesky factorizations. The neural networks that define the coordinate transformation and the pH system are identified in a joint optimization process to match the dynamics observed in the data while defining a linear pH system in the latent space. The learned, low-dimensional pH system can describe even nonlinear systems and is rapidly computable due to its small size. The method is exemplified by a parametric mass-spring-damper and a nonlinear pendulum example, as well as the high-dimensional model of a disc brake with linear thermoelastic behavior.

Förderung

  • Universität Stuttgart

Zitieren

APA

Rettberg, J., Kneifl, J., Herb, J., Buchfink, P., Fehr, J., & Haasdonk, B. (2025). Data-driven identification of latent port-Hamiltonian systems. Computational Science and Engineering, 2(1). https://doi.org/10.1007/s44207-025-00007-2

Vancouver

Rettberg J, Kneifl J, Herb J, Buchfink P, Fehr J, Haasdonk B. Data-driven identification of latent port-Hamiltonian systems. Computational Science and Engineering. 2025;2(1). doi:10.1007/s44207-025-00007-2

BibTeX
@article{Rettberg2025,
  author = {Rettberg, Johannes and Kneifl, Jonas and Herb, Julius and Buchfink, Patrick and Fehr, Jörg and Haasdonk, Bernard},
  title = {Data-driven identification of latent port-Hamiltonian systems},
  journal = {Computational Science and Engineering},
  year = {2025},
  volume = {2},
  number = {1},
  doi = {10.1007/s44207-025-00007-2}
}
Kostenlos starten →