Fully convolutional networks for velocity-field predictions based on the wall heat flux in turbulent boundary layers
2025

Using Neural Networks to Predict Turbulent Flow from Wall Heat Flux

Sample size: 7474 publication 10 minutes Evidence: moderate

Author Information

Author(s): Guastoni Luca, Balasubramanian Arivazhagan G., Foroozan Firoozeh, Güemes Alejandro, Ianiro Andrea, Discetti Stefano, Schlatter Philipp, Azizpour Hossein, Vinuesa Ricardo

Primary Institution: KTH Royal Institute of Technology

Hypothesis

Can fully convolutional networks effectively predict the velocity field in turbulent boundary layers using wall heat flux data?

Conclusion

The study demonstrates that fully convolutional networks can accurately predict turbulent flow fields from wall heat flux measurements, paving the way for non-intrusive sensing in practical applications.

Supporting Evidence

  • Neural networks were trained on numerical simulations and fine-tuned with experimental data.
  • The model achieved a 50% lower error compared to previous architectures.
  • Predictions were validated against experimental data from a water tunnel.
  • Different Prandtl numbers were tested to assess the model's robustness.

Takeaway

This study shows that we can use special computer programs called neural networks to guess how fast the water is moving just by looking at the heat coming from the wall.

Methodology

The study used fully convolutional networks trained on numerical simulations and fine-tuned with experimental data to predict velocity fields from wall heat flux measurements.

Limitations

The predictions are less accurate for higher Prandtl numbers and the model's performance is limited by the amount of experimental data available.

Digital Object Identifier (DOI)

10.1007/s00162-024-00732-y

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication