Towards Active Flow Control Strategies Through Deep Reinforcement Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Montalà, Ricard, Font, Bernat, Suárez, Pol, Rabault, Jean, Lehmkuhl, Oriol, Rodriguez, Ivette
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910689957773312
author Montalà, Ricard
Font, Bernat
Suárez, Pol
Rabault, Jean
Lehmkuhl, Oriol
Rodriguez, Ivette
author_facet Montalà, Ricard
Font, Bernat
Suárez, Pol
Rabault, Jean
Lehmkuhl, Oriol
Rodriguez, Ivette
contents This paper presents a deep reinforcement learning (DRL) framework for active flow control (AFC) to reduce drag in aerodynamic bodies. Tested on a 3D cylinder at Re = 100, the DRL approach achieved a 9.32% drag reduction and a 78.4% decrease in lift oscillations by learning advanced actuation strategies. The methodology integrates a CFD solver with a DRL model using an in-memory database for efficient communication between
format Preprint
id arxiv_https___arxiv_org_abs_2411_05536
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Active Flow Control Strategies Through Deep Reinforcement Learning
Montalà, Ricard
Font, Bernat
Suárez, Pol
Rabault, Jean
Lehmkuhl, Oriol
Rodriguez, Ivette
Machine Learning
Fluid Dynamics
This paper presents a deep reinforcement learning (DRL) framework for active flow control (AFC) to reduce drag in aerodynamic bodies. Tested on a 3D cylinder at Re = 100, the DRL approach achieved a 9.32% drag reduction and a 78.4% decrease in lift oscillations by learning advanced actuation strategies. The methodology integrates a CFD solver with a DRL model using an in-memory database for efficient communication between
title Towards Active Flow Control Strategies Through Deep Reinforcement Learning
topic Machine Learning
Fluid Dynamics
url https://arxiv.org/abs/2411.05536