Closed-loop control of experimental shear flows using machine learning

Thomas Duriez, Vladimir Parezanovic, Jean Charles Laurentie, Carine Fourment, Joël Delville, Jean Paul Bonnet, Laurent Cordier, Bernd R. Noack, Marc Segond, Markus Abel, Nicolas Gautier, Jean Luc Aider, Cedric Raibaudo, Christophe Cuvier, Michel Stanislas, Steven L. Brunton

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

24 Scopus citations


We propose a novel closed-loop control strategy of turbulent ows using machine learning methods in a model-free manner. This strategy, called Machine Learning Control (MLC), allows-for the first time-to detect and exploit all enabling nonlinear actuation mechanisms in an un-supervised automatic manner. In this communication, we focus on MLC applications for in-time control of experimental shear ows and demonstrate how it outperforms state-of-the-art control. In particular, MLC is applied to three different experimental closed-loop control setups: (1) the TUCOROM mixing layer tunnel, (2) the Görtler PMMH water tunnel with a backward facing step, and (3) the LML Boundary Layer wind tunnel with a separating turbulent boundary layer. In all three cases, MLC finds a control which yields a signićantly better performance with respect to the given cost functional as compared to the best previously tested open-loop actuation. We foresee numerous potential applications to most nonlinear multiple-input multiple-output (MIMO) flow control problems, particularly in experiments. In particular, the model-free architecture of MLC enables its application to a large class of complex nonlinear systems in all areas of science.

Original languageBritish English
Title of host publicationAIAA AVIATION 2014 -7th AIAA Flow Control Conference
StatePublished - 2014
EventAIAA AVIATION 2014 -7th AIAA Flow Control Conference 2014 - Atlanta, GA, United States
Duration: 16 Jun 201420 Jun 2014

Publication series

NameAIAA AVIATION 2014 -7th AIAA Flow Control Conference


ConferenceAIAA AVIATION 2014 -7th AIAA Flow Control Conference 2014
Country/TerritoryUnited States
CityAtlanta, GA


Dive into the research topics of 'Closed-loop control of experimental shear flows using machine learning'. Together they form a unique fingerprint.

Cite this