EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Physics‐informed reinforcement learning for optimal control of nonlinear systems

Yujia Wang, Zhe Wu

AIChE Journal · 2024-10 · 70 (10)

DOI: 10.1002/aic.18542 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIChE Journal, online erschienen am 17.07.2024. Verfasst von Yujia Wang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article proposes a model‐free framework to solve the optimal control problem with an infinite‐horizon performance function for nonlinear systems with input constraints. Specifically, two Physics‐Informed Neural Networks (PINNs) that incorporate the knowledge of the Lyapunov stability theorem and the convergence conditions of the policy iteration algorithm are utilized to approximate the value function and control policy, respectively. Then, a Reinforcement Learning (RL) algorithm that does not require any first‐principles or data‐driven models of nonlinear systems is developed to iteratively learn a nearly optimal control policy. Furthermore, we provide a rigorous theoretical analysis showing the conditions that ensure the stability of closed‐loop systems with the control policy learned by RL and guarantee the convergence of the iteration algorithm. Finally, the proposed Physics‐Informed Reinforcement Learning (PIRL) method is applied to a chemical process example to demonstrate its effectiveness.

Zitieren

APA

Wang, Y., & Wu, Z. (2024). Physics‐informed reinforcement learning for optimal control of nonlinear systems. AIChE Journal, 70(10). https://doi.org/10.1002/aic.18542

Vancouver

Wang Y, Wu Z. Physics‐informed reinforcement learning for optimal control of nonlinear systems. AIChE Journal. 2024;70(10). doi:10.1002/aic.18542

BibTeX
@article{Wang2024,
  author = {Wang, Yujia and Wu, Zhe},
  title = {Physics‐informed reinforcement learning for optimal control of nonlinear systems},
  journal = {AIChE Journal},
  year = {2024},
  volume = {70},
  number = {10},
  doi = {10.1002/aic.18542}
}
Kostenlos starten →