Data-driven order reduction and velocity field reconstruction using neural networks : The case of a turbulent boundary layer

By Antonios Giannopoulos and Jean-Luc Aider in Physics of Fluids 32, 095117 (2020) ;

We present a data-driven methodology to achieve the identification of coherent structure dynamics and system order reduction of an experimental turbulent boundary layer flow. The flow is characterized using time-resolved optical flow particle image velocimetry, leading to dense velocity fields that can be used both to monitor the overall dynamics of the flow and to define as many local visual sensors as needed. A Proper Orthogonal Decomposition (POD) is first applied to define a reduced-order system. A non-linear mapping between the local upstream sensors (inputs sensors) and the full-field dynamics (POD coefficients) as outputs is sought using an optimal focused time-delay Artificial Neural Network (ANN). The choices of sensors, ANN architecture, and training parameters are shown to play a critical role. It is verified that a shallow ANN, with the proper sensor memory size, can lead to a satisfying full-field dynamics identification, coherent structure reconstruction, and system order reduction of this turbulent flow.

Haut de page

À lire aussi...

Bioinspired turbine blades offer new perspectives for wind energy

V. Cognet, S. Courrech du Pont, I. Dobrev, F. Massouh, B. Thiria ; Proc. Roy. Soc. A, 473, (2017) Wind energy is becoming a significant (...) 

> Lire la suite...

Book : Generation and Applications of Extra-Terrestrial Environments on Earth

Daniel A. Beysens and Jack J.W. A. van Loon This book has been prepared under the auspice of the European Low Gravity Research Association (...) 

> Lire la suite...


Informations Pratiques

Laboratoire : 01 40 79 45 22
Directeur : Damien Vandembroucq
Codirecteur : Philippe Petitjeans
Administratrice : Frédérique Auger (01 40 79 45 22)
Gestionnaire : Claudette Barez (01 40 79 58 53)
Courriel : dir (arobase)