Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control

We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is shown that, in a two-dimensional simulation of the Kármán vortex street at moderate Reynolds number ( $Re=100$ ), our artificial neural network i...

Full description

Saved in:
Bibliographic Details
Published in:Journal of fluid mechanics Vol. 865; pp. 281 - 302
Main Authors: Rabault, Jean, Kuchta, Miroslav, Jensen, Atle, Réglade, Ulysse, Cerardi, Nicolas
Format: Journal Article
Language:English
Published: Cambridge, UK Cambridge University Press 25.04.2019
Subjects:
Active control
Actuation
Algorithms
Artificial neural networks
Computer simulation
Cylinders
Drag reduction
Flow control
Flow rates
Fluid dynamics
Fluid flow
Fluid mechanics
JFM Papers
Mass
Mass flow rate
Neural networks
New class
Reinforcement
Reynolds number
Stability
Swimming
control theory
drag reduction
ISSN:0022-1120, 1469-7645
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is shown that, in a two-dimensional simulation of the Kármán vortex street at moderate Reynolds number ( $Re=100$ ), our artificial neural network is able to learn an active control strategy from experimenting with the mass flow rates of two jets on the sides of a cylinder. By interacting with the unsteady wake, the artificial neural network successfully stabilizes the vortex alley and reduces drag by approximately 8 %. This is performed while using small mass flow rates for the actuation, of the order of 0.5 % of the mass flow rate intersecting the cylinder cross-section once a new pseudo-periodic shedding regime is found. This opens the way to a new class of methods for performing active flow control.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0022-1120
1469-7645
DOI:10.1017/jfm.2019.62