EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Controlling Dynamical Systems Into Unseen Target States Using Machine Learning

Daniel Köglmayr, Alexander Haluszczynski, Christoph Räth

Advanced Intelligent Systems · 2026-05 · 8 (5)

DOI: 10.1002/aisy.202501319 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 23.03.2026. Verfasst von Daniel Köglmayr und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a novel, model‐free, and data‐driven methodology for controlling complex dynamical systems into previously unseen target states, including those with significantly different and complex dynamics. Leveraging a parameter‐aware realization of next‐generation reservoir computing (NGRC), our approach accurately predicts system behavior in unobserved parameter regimes, enabling control over transitions to arbitrary target states utilizing a new prediction evaluation and selection scheme. Crucially, this includes states with dynamics that differ fundamentally from known regimes, such as shifts from periodic to intermittent or chaotic behavior. The method's parameter awareness facilitates nonstationary control with which control scenarios are generated and evaluated on the basis of predefined control objective. In addition to proving the method for transient‐free control to extrapolated chaotic target states over transition times, we demonstrate the method's effectiveness on a nonlinear power system model. Our method successfully navigates transitions even in scenarios where system collapse is observed frequently while ensuring fast transitions and avoiding prolonged transient behavior. By extending the applicability of machine learning‐based control mechanisms to previously inaccessible target dynamics, the methodology opens the door to new control applications while maintaining exceptional efficiency.

Zitieren

APA

Köglmayr, D., Haluszczynski, A., & Räth, C. (2026). Controlling Dynamical Systems Into Unseen Target States Using Machine Learning. Advanced Intelligent Systems, 8(5). https://doi.org/10.1002/aisy.202501319

Vancouver

Köglmayr D, Haluszczynski A, Räth C. Controlling Dynamical Systems Into Unseen Target States Using Machine Learning. Advanced Intelligent Systems. 2026;8(5). doi:10.1002/aisy.202501319

BibTeX
@article{Kglmayr2026,
  author = {Köglmayr, Daniel and Haluszczynski, Alexander and Räth, Christoph},
  title = {Controlling Dynamical Systems Into Unseen Target States Using Machine Learning},
  journal = {Advanced Intelligent Systems},
  year = {2026},
  volume = {8},
  number = {5},
  doi = {10.1002/aisy.202501319}
}
Kostenlos starten →