Towards Active Flow Control Strategies Through Deep Reinforcement Learning
Machine Learning
2024-11-11 v1 Fluid Dynamics
Abstract
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
Keywords
Cite
@article{arxiv.2411.05536,
title = {Towards Active Flow Control Strategies Through Deep Reinforcement Learning},
author = {Ricard Montalà and Bernat Font and Pol Suárez and Jean Rabault and Oriol Lehmkuhl and Ivette Rodriguez},
journal= {arXiv preprint arXiv:2411.05536},
year = {2024}
}
Comments
ECOMMAS 2024 conference proceeding paper