Turbulent wake prediction using deep convolutional neural networks
Turbulent wake prediction using deep convolutional neural networks
A machine-learning based closure is explored for the prediction of the turbulent wake of flow past a circular cylinder at a high Reynolds number. We show that classic turbulence closures based on the turbulent-viscosity hypothesis are not capable of modelling the non-linear relationship between the mean quantities and the target turbulent fields. Instead, different multiple-input multiple-output auto-encoder convolutional neural networks are explored in this work to develop a data-driven closure. A detailed hyper-parameter study is completed including network architecture, loss functions and input sets, among others.
A-priori results show 80% to 90% correlation coefficients between target and predicted turbulent fields of previously unseen data. High correlation coefficients are rapidly achieved by networks with a large number of trainable parameters, whereas smaller networks require more training epochs. The integration of the model in live simulations is theoretically discussed from its stability standpoint as well as preliminary physics-based constraints ideas to provide more stable data-driven closures.
wake flow, Machine learning, neural networks
Font Garcia, Bernat
1c605529-b50d-4703-b8cc-4ccaa5dff7fc
Weymouth, Gabriel
b0c85fda-dfed-44da-8cc4-9e0cc88e2ca0
Nguyen, Vinh-Tan
6163fc4b-5e7d-48da-8000-a3c0e0e8b98e
Tutty, Owen
c9ba0b98-4790-4a72-b5b7-09c1c6e20375
October 2020
Font Garcia, Bernat
1c605529-b50d-4703-b8cc-4ccaa5dff7fc
Weymouth, Gabriel
b0c85fda-dfed-44da-8cc4-9e0cc88e2ca0
Nguyen, Vinh-Tan
6163fc4b-5e7d-48da-8000-a3c0e0e8b98e
Tutty, Owen
c9ba0b98-4790-4a72-b5b7-09c1c6e20375
Font Garcia, Bernat, Weymouth, Gabriel, Nguyen, Vinh-Tan and Tutty, Owen
(2020)
Turbulent wake prediction using deep convolutional neural networks.
33rd Symposium on Naval Hydrodynamics, Online, Osaka, Japan.
18 - 23 Oct 2020.
Record type:
Conference or Workshop Item
(Paper)
Abstract
A machine-learning based closure is explored for the prediction of the turbulent wake of flow past a circular cylinder at a high Reynolds number. We show that classic turbulence closures based on the turbulent-viscosity hypothesis are not capable of modelling the non-linear relationship between the mean quantities and the target turbulent fields. Instead, different multiple-input multiple-output auto-encoder convolutional neural networks are explored in this work to develop a data-driven closure. A detailed hyper-parameter study is completed including network architecture, loss functions and input sets, among others.
A-priori results show 80% to 90% correlation coefficients between target and predicted turbulent fields of previously unseen data. High correlation coefficients are rapidly achieved by networks with a large number of trainable parameters, whereas smaller networks require more training epochs. The integration of the model in live simulations is theoretically discussed from its stability standpoint as well as preliminary physics-based constraints ideas to provide more stable data-driven closures.
Text
Font_et_al 2020 - Turbulent wake prediction using deep convolutional neural networks
- Accepted Manuscript
Restricted to Repository staff only
Request a copy
More information
Published date: October 2020
Venue - Dates:
33rd Symposium on Naval Hydrodynamics, Online, Osaka, Japan, 2020-10-18 - 2020-10-23
Keywords:
wake flow, Machine learning, neural networks
Identifiers
Local EPrints ID: 444591
URI: http://eprints.soton.ac.uk/id/eprint/444591
PURE UUID: dfe0aff6-5304-4285-92c0-fee8ac80b23e
Catalogue record
Date deposited: 26 Oct 2020 17:33
Last modified: 17 Mar 2024 03:32
Export record
Contributors
Author:
Bernat Font Garcia
Author:
Vinh-Tan Nguyen
Author:
Owen Tutty
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics