Neural network modeling for near wall turbulent flow

Authors:
Michele Milano;Petros Koumoutsakos
Affiliations:
Graduate Aeronautics Laboratories, California Institute of Technology, Pasadena, CA;Institute of Computational Sciences, ETH Zentrum, CH-8092 Zürich, Switzerland and CTR, NASA Ames 202A-1, Moffett Field, CA
Venue:
Journal of Computational Physics
Year:
2002

Citing 2
Cited 1

Neural networks and principal component analysis: learning from examples without local minima

Neural Networks
Local Gain Adaptation in Stochastic Gradient Descent

Local Gain Adaptation in Stochastic Gradient Descent

Developing an expert system for predicting alluvial channel geometry using ANN

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	31.45

Visualization

Abstract

A neural network methodology is developed in order to reconstruct the near wall field in a turbulent flow by exploiting flow fields provided by direct numerical simulations. The results obtained from the neural network methodology are compared with the results obtained from prediction and reconstruction using proper orthogonal decomposition (POD). Using the property that the POD is equivalent to a specific linear neural network, a nonlinear neural network extension is presented. It is shown that for a relatively small additional computational cost nonlinear neural networks provide us with improved reconstruction and prediction capabilities for the near wall velocity fields. Based on these results advantages and drawbacks of both approaches are discussed with an outlook toward the development of near wall models for turbulence modeling and control.