Published on Wed Nov 13 2019

Deep learning velocity signals allows to quantify turbulence intensity

Alessandro Corbetta, Vlado Menkovski, Roberto Benzi, Federico Toschi

Turbulence is characterized by strong and statistically non-trivial fluctuations of the violentlyvelocity field. Strongly non-stationarities hinder the possibility to achieve statistical convergence. By employing Deep Neural Networks we can accurately estimate the Reynolds number within accuracy.

0
0
0
Abstract

Turbulence, the ubiquitous and chaotic state of fluid motions, is characterized by strong and statistically non-trivial fluctuations of the velocity field, over a wide range of length- and time-scales, and it can be quantitatively described only in terms of statistical averages. Strong non-stationarities hinder the possibility to achieve statistical convergence, making it impossible to define the turbulence intensity and, in particular, its basic dimensionless estimator, the Reynolds number. Here we show that by employing Deep Neural Networks (DNN) we can accurately estimate the Reynolds number within accuracy, from a statistical sample as small as two large-scale eddy-turnover times. In contrast, physics-based statistical estimators are limited by the rate of convergence of the central limit theorem, and provide, for the same statistical sample, an error at least times larger. Our findings open up new perspectives in the possibility to quantitatively define and, therefore, study highly non-stationary turbulent flows as ordinarily found in nature as well as in industrial processes.

Tue Oct 16 2018
Machine Learning
From Deep to Physics-Informed Learning of Turbulence: Diagnostics
Tests validating progress made toward acceleration and automation of hydrodynamic codes in the regime of developed turbulence by three Deep Learning (DL) Neural Network (NN) schemes.
0
0
0
Wed Nov 20 2019
Machine Learning
Towards Physics-informed Deep Learning for Turbulent Flow Prediction
Deep learning has shown tremendous success in a wide range of domains. It remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models. We adopt a hybrid approach by marrying two well-established turbulent flow simulation techniques with deep learning.
0
0
0
Tue Feb 04 2020
Machine Learning
On the use of recurrent neural networks for predictions of turbulent flows
In this paper, the prediction capabilities of recurrent neural networks are assessed in the low-order model of near-wall turbulence. It is possible to obtain excellent predictions of the turbulence statistics and the dynamic behavior of the flow with properly trained long short-term memory (LSTM) networks.
0
0
0
Tue Nov 19 2019
Machine Learning
Modelling pressure-Hessian from local velocity gradients information in an incompressible turbulent flow field using deep neural networks
0
0
0
Thu Jul 15 2021
Machine Learning
Predicting the near-wall region of turbulence through convolutional neural networks
Modelling the near-wall region of wall-bounded turbulent flows is a widespread practice to reduce the computational cost of large-eddy simulations. Guastoni et al. propose a neural-network-based approach to predict the behaviour of turbulence at the wall.
2
9
29
Tue Jun 02 2020
Machine Learning
Identification of hydrodynamic instability by convolutional neural networks
The onset of hydrodynamic instabilities is of great importance in both industry and daily life. Modern machine learning techniques, especially the convolutional neural networks (CNN), are used to identify the transition between different flow motions.
0
0
0