Flow control of three-dimensional cylinders transitioning to turbulence via multi-agent reinforcement learning

Active flow control strategies for three-dimensional bluff bodies are challenging to design, yet critical for industrial applications. Here we explore the potential of discovering novel drag-reduction strategies using deep reinforcement learning. We introduce a high-dimensional active flow control s...

Descripción completa

Detalles Bibliográficos
Autores: Suárez Morales, Pol, Alcántara Ávila, Francisco, Rabault, Jean, Miró Jané, Arnau|||0000-0002-2772-6050, Font García, Bernat, Lehmkuhl Barba, Oriol|||0000-0002-2670-1871, Vinuesa Motilva, Ricardo
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/439479
Acceso en línea:https://hdl.handle.net/2117/439479
https://dx.doi.org/10.1038/s44172-025-00446-x
Access Level:acceso abierto
Palabra clave:Adaptive control
Computational fluid dynamics
Deep learning
Flow control
Flow simulation
Multi-agent systems
Turbulence
Àrees temàtiques de la UPC::Física::Física de fluids
Descripción
Sumario:Active flow control strategies for three-dimensional bluff bodies are challenging to design, yet critical for industrial applications. Here we explore the potential of discovering novel drag-reduction strategies using deep reinforcement learning. We introduce a high-dimensional active flow control setup on a three-dimensional cylinder at Reynolds numbers (ReD) from 100 to 400, spanning the transition to three-dimensional wake instabilities. The setup involves multiple zero-net-mass-flux jets and couples a computational fluid dynamics solver with a numerical multi-agent reinforcement learning framework based on the proximal policy optimization algorithm. Our results demonstrate up to 16% drag reduction at ReD = 400, outperforming classical periodic control strategies. A proper orthogonal decomposition analysis reveals that the control leads to a stabilized wake structure with an elongated recirculation bubble. These findings represent the first demonstration of training on three-dimensional cylinders and pave the way toward active flow control of complex turbulent flows.