Bayesian optimization for active flow control

A key question in flow control is that of the design of optimal controllers when the control space is high-dimensional and the experimental or computational budget is limited. We address this formidable challenge using a particular flavor of machine learning and present the first application of Baye...

Full description

Saved in:
Bibliographic Details
Published inActa mechanica Sinica Vol. 37; no. 12; pp. 1786 - 1798
Main Authors Blanchard, Antoine B., Cornejo Maceda, Guy Y., Fan, Dewei, Li, Yiqing, Zhou, Yu, Noack, Bernd R., Sapsis, Themistoklis P.
Format Journal Article
LanguageEnglish
Published Beijing The Chinese Society of Theoretical and Applied Mechanics; Institute of Mechanics, Chinese Academy of Sciences 01.12.2021
Springer Nature B.V
EditionEnglish ed.
Subjects
Active control
Algorithms
Bayesian analysis
Classical and Continuum Physics
Computational Intelligence
Controllers
Cost function
Design optimization
Drag reduction
Engineering
Engineering Fluid Dynamics
Flow control
Fluid dynamics
Fluid flow
Machine learning
Optimization
Research Paper
Theoretical and Applied Mechanics
Turbulent jets
Flow control
Turbulence
Drag reduction
Bayesian optimization
Online AccessGet full text

Cover

More Information
Summary:A key question in flow control is that of the design of optimal controllers when the control space is high-dimensional and the experimental or computational budget is limited. We address this formidable challenge using a particular flavor of machine learning and present the first application of Bayesian optimization to the design of open-loop controllers for fluid flows. We consider a range of acquisition functions, including the recently introduced output-informed criteria of Blanchard and Sapsis (2021), and evaluate performance of the Bayesian algorithm in two iconic configurations for active flow control: computationally, with drag reduction in the fluidic pinball; and experimentally, with mixing enhancement in a turbulent jet. For these flows, we find that Bayesian optimization identifies optimal controllers at a fraction of the cost of other optimization strategies considered in previous studies. Bayesian optimization also provides, as a by-product of the optimization, a surrogate model for the latent cost function, which can be leveraged to paint a complete picture of the control landscape. The proposed methodology can be used to design open-loop controllers for virtually any complex flow and, therefore, has significant implications for active flow control at an industrial scale. Graphic Abstract
ISSN:0567-7718
1614-3116
DOI:10.1007/s10409-021-01149-0