The wake stabilization of a triangular cluster of three rotating cylinders is investigated. Experiments are performed at Reynolds number Re ∼ 2200. Flow control is realized using rotating cylinders spanning the wind-tunnel height. The cylinders are individually connected to identical brushless DC motors. Two-component planar particle image velocimetry measurements and constant temperature hot-wire anemometry were used to characterize the flow without and with actuation. Main open-loop configurations are studied and different controlled flow topologies are identified. Machine learning control is then implemented for the optimization of the flow control performance. Linear genetic algorithms are used here as the optimization technique for the open-loop constant speed-actuators. Two different cost functions are considered targeting either drag reduction or wake symmetrization. The functions are estimated based on the velocity from three hot-wire sensors in the wake. It is shown that the machine learning approach is an effective strategy for controlling the wake characteristics. More significantly, the results show that machine learning strategies can reveal unanticipated solutions or parameter relations, in addition to being a tool for optimizing searches in large parameter spaces.
Skip Nav Destination
Article navigation
January 2020
Research Article|
January 10 2020
Machine learning strategies applied to the control of a fluidic pinball
Special Collection:
Special Topic on Passive and Active Control of Turbulent Flows
C. Raibaudo
;
C. Raibaudo
1
LTRAC Laboratory, Department of Mechanical Engineering, University of Calgary
, Calgary, Alberta T2N 1N4, Canada
Search for other works by this author on:
P. Zhong;
P. Zhong
1
LTRAC Laboratory, Department of Mechanical Engineering, University of Calgary
, Calgary, Alberta T2N 1N4, Canada
Search for other works by this author on:
B. R. Noack;
B. R. Noack
a)
2
Laboratoire d’Informatique pour la Mécanique et les Sciences de l’Ingénieur LIMSI-CNRS
, Orsay, France
Search for other works by this author on:
R. J. Martinuzzi
R. J. Martinuzzi
b)
1
LTRAC Laboratory, Department of Mechanical Engineering, University of Calgary
, Calgary, Alberta T2N 1N4, Canada
b)Author to whom correspondence should be addressed: rmartinu@ucalgary.ca
Search for other works by this author on:
a)
Also at: Institut für Strömungsmechanik, Technische Universtität Braunschweig, Braunschweig, Germany.
b)Author to whom correspondence should be addressed: rmartinu@ucalgary.ca
Note: This paper is part of the Special Topic on Passive and Active Control of Turbulent Flows.
Physics of Fluids 32, 015108 (2020)
Article history
Received:
September 09 2019
Accepted:
December 19 2019
Citation
C. Raibaudo, P. Zhong, B. R. Noack, R. J. Martinuzzi; Machine learning strategies applied to the control of a fluidic pinball. Physics of Fluids 1 January 2020; 32 (1): 015108. https://doi.org/10.1063/1.5127202
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Pay-Per-View Access
$40.00
Citing articles via
On Oreology, the fracture and flow of “milk's favorite cookie®”
Crystal E. Owens, Max R. Fan (范瑞), et al.
Fluid–structure interaction on vibrating square prisms considering interference effects
Zengshun Chen (陈增顺), 陈增顺, et al.
Physics-informed neural networks for solving Reynolds-averaged Navier–Stokes equations
Hamidreza Eivazi, Mojtaba Tahani, et al.