Fully convolutional networks for velocity-field predictions based on the wall heat flux in turbulent boundary layers

TL;DR

This paper develops a fully convolutional neural network model that predicts velocity fields in turbulent boundary layers using wall heat flux measurements, enabling non-intrusive flow sensing in experiments.

Contribution

It introduces a novel FCN model that uses wall heat flux instead of wall shear stress, trained on DNS data and fine-tuned on experimental data, applying transfer learning in turbulence prediction.

Findings

Successful prediction of velocity fields from heat flux data.

First application of transfer learning on experimental turbulence data.

Demonstrates potential for non-intrusive flow sensing in practical settings.

Abstract

Fully-convolutional neural networks (FCN) were proven to be effective for predicting the instantaneous state of a fully-developed turbulent flow at different wall-normal locations using quantities measured at the wall. In Guastoni et al. [J. Fluid Mech. 928, A27 (2021)], we focused on wall-shear-stress distributions as input, which are difficult to measure in experiments. In order to overcome this limitation, we introduce a model that can take as input the heat-flux field at the wall from a passive scalar. Four different Prandtl numbers $Pr = \nu/\alpha = (1,2,4,6)$ are considered (where $\nu$ is the kinematic viscosity and $\alpha$ is the thermal diffusivity of the scalar quantity). A turbulent boundary layer is simulated since accurate heat-flux measurements can be performed in experimental settings: first we train the network on aptly-modified DNS data and then we fine-tune it on the experimental data. Finally, we test our network on experimental data sampled in a water tunnel. These predictions represent the first application of transfer learning on experimental data of neural networks trained on simulations. This paves the way for the implementation of a non-intrusive sensing approach for the flow in practical applications.