EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Reinforcement Learning for the Management of the Wall Regeneration Cycle in Wall-Bounded Turbulent Flows

Giorgio Maria Cavallazzi, Luca Guastoni, Ricardo Vinuesa, Alfredo Pinelli

Flow, Turbulence and Combustion · 2025-09 · 115 (3) · 1291-1317

DOI: 10.1007/s10494-024-00609-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Flow, Turbulence and Combustion, online erschienen am 15.11.2024. Verfasst von Giorgio Maria Cavallazzi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering, City St George's, University of London, Northampton Square, London, EC1V 0HB UK. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council, European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The wall cycle in wall-bounded turbulent flows is a complex turbulence regeneration mechanism that remains not fully understood. This study explores the potential of deep reinforcement learning (DRL) for managing the wall regeneration cycle to achieve desired flow dynamics. To create a robust framework for DRL-based flow control, we have integrated the StableBaselines3 DRL libraries with the open-source direct numerical simulation (DNS) solver CaNS . The DRL agent interacts with the DNS environment, learning policies that modify wall boundary conditions to optimise objectives such as the reduction of the skin-friction coefficient or the enhancement of certain coherent structures’ features. The implementation makes use of the message-passing-interface (MPI) wrappers for efficient communication between the Python-based DRL agent and the DNS solver, ensuring scalability on high-performance computing architectures. Initial experiments demonstrate the capability of DRL to achieve drag reduction rates comparable with those achieved via traditional methods, although limited to short time intervals. We also propose a strategy to enhance the coherence of velocity streaks, assuming that maintaining straight streaks can inhibit instability and further reduce skin-friction. Our results highlight the promise of DRL in flow-control applications and underscore the need for more advanced control laws and objective functions. Future work will focus on optimising actuation intervals and exploring new computational architectures to extend the applicability and the efficiency of DRL in turbulent flow management.

Schlagwörter

Stichwörter der Autor:innen

Deep reinforcement learningDirect numerical simulationDrag reductionFlow control

Autor:innen und Institutionen

  • Department of Engineering, City St George's, University of London, Northampton Square, London, EC1V 0HB UK.
  • School of Computation, Information and Technology, TU Munich, Boltzmannstr. 3, 85748 Garching, Germany.
  • FLOW, Engineering Mechanics, KTH Royal Institute of Technology, 100 44 Stockholm, Sweden.

Förderung

  • Engineering and Physical Sciences Research Council
  • European Research Council

Zitieren

APA

Cavallazzi, G. M., Guastoni, L., Vinuesa, R., & Pinelli, A. (2025). Deep Reinforcement Learning for the Management of the Wall Regeneration Cycle in Wall-Bounded Turbulent Flows. Flow, Turbulence and Combustion, 115(3), 1291-1317. https://doi.org/10.1007/s10494-024-00609-4

Vancouver

Cavallazzi GM, Guastoni L, Vinuesa R, Pinelli A. Deep Reinforcement Learning for the Management of the Wall Regeneration Cycle in Wall-Bounded Turbulent Flows. Flow, Turbulence and Combustion. 2025;115(3):1291-1317. doi:10.1007/s10494-024-00609-4

BibTeX
@article{Cavallazzi2025,
  author = {Cavallazzi, Giorgio Maria and Guastoni, Luca and Vinuesa, Ricardo and Pinelli, Alfredo},
  title = {Deep Reinforcement Learning for the Management of the Wall Regeneration Cycle in Wall-Bounded Turbulent Flows},
  journal = {Flow, Turbulence and Combustion},
  year = {2025},
  volume = {115},
  number = {3},
  pages = {1291--1317},
  doi = {10.1007/s10494-024-00609-4}
}
Kostenlos starten →