Using delay based networks for detecting coherent structures in turbulence from hot-wire anemometer signals

A delay based artificial neural network is used to analyse turbulent flow temporal signals obtained by a hot wire anemometer in a single point within the wake of a cylinder. Values of the Reynolds number are ranging from 2000 to 8000, covering flows from almost laminar to fully turbulent. The implemented trainable delay based artificial neural network is able to autonomously obtain the embedding dimension as well as the normalized embedding delay and permits performing short and long term predictions. The predictions are mainly concerned with the larger eddies and coherent structures present in the turbulent flow-field.