Closed-loop control of an experimental mixing layer using machine learning control
Abstract
A novel framework for closed-loop control of turbulent flows is tested in an experimental mixing layer flow. This framework, called Machine Learning Control (MLC), provides a model-free method of searching for the best function, to be used as a control law in closed-loop flow control. MLC is based on genetic programming, a function optimization method of machine learning. In this article, MLC is benchmarked against classical open-loop actuation of the mixing layer. Results show that this method is capable of producing sensor-based control laws which can rival or surpass the best open-loop forcing, and be robust to changing flow conditions. Additionally, MLC can detect non-linear mechanisms present in the controlled plant, and exploit them to find a better type of actuation than the best periodic forcing.
Keywords
Cite
@article{arxiv.1408.3259,
title = {Closed-loop control of an experimental mixing layer using machine learning control},
author = {Vladimir Parezanović and Thomas Duriez and Laurent Cordier and Bernd R. Noack and Joël Delville and Jean-Paul Bonnet and Marc Segond and Markus Abel and Steven L. Brunton},
journal= {arXiv preprint arXiv:1408.3259},
year = {2014}
}