Closed-loop separation control using machine learning

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "N. Gautier and J.-L. Aider and T. Duriez and 
                 B. R. Noack and M. Segond and M. Abel",
  title =        "Closed-loop separation control using machine
  journal =      "Journal of Fluid Mechanics",
  volume =       "770",
  month =        "5",
  year =         "2015",
  ISSN =         "1469-7645",
  pages =        "442--457",
  oai =          "",
  keywords =     "genetic algorithms, genetic programming, control
                 theory, flow control, separated flows, physics - fluid
  URL =          "",
  URL =          "",
  DOI =          "doi:10.1017/jfm.2015.95",
  size =         "16 pages",
  abstract =     "We present the first closed-loop separation control
                 experiment using a novel, model-free strategy based on
                 genetic programming, which we call machine learning
                 control. The goal is to reduce the recirculation zone
                 of backward-facing step flow at Reh=1350 manipulated by
                 a slotted jet and optically sensed by online particle
                 image velocimetry. The feedback control law is
                 optimised with respect to a cost functional based on
                 the recirculation area and a penalization of the
                 actuation. This optimisation is performed employing
                 genetic programming. After 12 generations comprised of
                 500 individuals, the algorithm converges to a feedback
                 law which reduces the recirculation zone by 80 percent.
                 This machine learning control is benchmarked against
                 the best periodic forcing which excites
                 Kelvin-Helmholtz vortices. The machine learning control
                 yields a new actuation mechanism resonating with the
                 low-frequency flapping mode instability. This feedback
                 control performs similarly to periodic forcing at the
                 design condition but outperforms periodic forcing when
                 the Reynolds number is varied by a factor two. The
                 current study indicates that machine learning control
                 can effectively explore and optimise new feedback
                 actuation mechanisms in numerous experimental

Genetic Programming entries for Nicolas Gautier Jean-Luc Aider Thomas Duriez Bernd R Noack Marc Segond Markus W Abel