EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pontryagin Neural Networks for the Class of Optimal Control Problems With Integral Quadratic Cost

Enrico Schiassi, Francesco Calabrò, Davide Elia De Falco

Aerospace Research Communications · 2024

DOI: 10.3389/arc.2024.13151 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Aerospace Research Communications, 2024. Verfasst von Enrico Schiassi und 2 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work introduces Pontryagin Neural Networks (PoNNs), a specialised subset of Physics-Informed Neural Networks (PINNs) that aim to learn optimal control actions for optimal control problems (OCPs) characterised by integral quadratic cost functions. PoNNs employ the Pontryagin Minimum Principle (PMP) to establish necessary conditions for optimality, resulting in a two-point boundary value problem (TPBVP) that involves both state and costate variables within a system of ordinary differential equations (ODEs). By modelling the unknown solutions of the TPBVP with neural networks, PoNNs effectively learn the optimal control strategies. We also derive upper bounds on the generalisation error of PoNNs in solving these OCPs, taking into account the selection and quantity of training points along with the training error. To validate our theoretical analysis, we perform numerical experiments on benchmark linear and nonlinear OCPs. The results indicate that PoNNs can successfully learn open-loop control actions for the considered class of OCPs, outperforming the commercial software GPOPS-II in terms of both accuracy and computational efficiency. The reduced computational time suggests that PoNNs hold promise for real-time applications.

Zitieren

APA

Schiassi, E., Calabrò, F., & Falco, D. E. D. (2024). Pontryagin Neural Networks for the Class of Optimal Control Problems With Integral Quadratic Cost. Aerospace Research Communications. https://doi.org/10.3389/arc.2024.13151

Vancouver

Schiassi E, Calabrò F, Falco DED. Pontryagin Neural Networks for the Class of Optimal Control Problems With Integral Quadratic Cost. Aerospace Research Communications. 2024. doi:10.3389/arc.2024.13151

BibTeX
@article{Schiassi2024,
  author = {Schiassi, Enrico and Calabrò, Francesco and Falco, Davide Elia De},
  title = {Pontryagin Neural Networks for the Class of Optimal Control Problems With Integral Quadratic Cost},
  journal = {Aerospace Research Communications},
  year = {2024},
  doi = {10.3389/arc.2024.13151}
}
Kostenlos starten →