Closed-loop control of experimental shear flows using machine learning

Abstract

We propose a novel closed-loop control strategy of turbulent flows 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 flows 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 significantly 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. *

Frequency selection by feedback control in a turbulent shear flow

“…The specific aspects of implementing GPC in the mixing layer experiment are discussed in appendix B. Further details on the GPC framework can be found in Duriez et al (2014).…”

Intelligent Systems for Stabilizing Mode-Locked Lasers and Frequency Combs: Machine Learning and Equation-Free Control Paradigms for Self-Tuning Optics

“…Two recent papers of note use similar strategies for the control of turbulent flows [28] and the beam steering in metamaterial antennas [29]. In both cases, the methods have not only been theoretically proposed, but reduction to practice has been demonstrated.…”

Closed-loop separation control using machine learning

“…Following Duriez et al (2014) we refer to this approach as machine learning control (MLC). Control laws are optimized with regard to a problem-specific objective function using genetic programming (Koza et al 1999).…”

“…One of the obstacles to application of GP to experimental flow control is that a large number of experiments is required to fulfil the criterion for statistical convergence. Recently, Duriez et al (2014) used GP to find closed-loop control laws in flow control problems. This approach proved surprisingly effective when applied to complex dynamical systems for closed-loop turbulence control in an experiment .…”