From coarse wall measurements to turbulent velocity fields through deep learning

Abstract

This work evaluates the applicability of super-resolution generative adversarial networks (SRGANs) as a methodology for the reconstruction of turbulent-flow quantities from coarse wall measurements. The method is applied both for the resolution enhancement of wall fields and the estimation of wall-parallel velocity fields from coarse wall measurements of shear stress and pressure. The analysis has been carried out with a database of a turbulent open-channel flow with friction Reynolds number $R{e}_{\tau }=180$ generated through direct numerical simulation. Coarse wall measurements have been generated with three different downsampling factors $f_d=[4,8,16]$ from the high-resolution fields, and wall-parallel velocity fields have been reconstructed at four inner-scaled wall-normal distances $y^{+}=[15,30,50,100]$. We first show that SRGAN can be used to enhance the resolution of coarse wall measurements. If compared with direct reconstruction from the sole coarse wall measurements, SRGAN provides better instantaneous reconstructions, both in terms of mean-squared error and spectral-fractional error. Even though lower resolutions in the input wall data make it more challenging to achieve highly accurate predictions, the proposed SRGAN-based network yields very good reconstruction results. Furthermore, it is shown that even for the most challenging cases the SRGAN is capable of capturing the large-scale structures that populate the flow. The proposed novel methodology has great potential for closed-loop control applications relying on non-intrusive sensing.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• The role of artificial intelligence in achieving the Sustainable Development Goals
• Machine Learning for Fluid Mechanics
• Super-resolution reconstruction of turbulent flows with machine learning
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• A Multi-Pass GAN for Fluid Flow Super-Resolution
• Logarithmic-layer turbulence: a view from the wall
• Machine-aided turbulence theory
• Prediction of wall-bounded turbulence from wall quantities using convolutional neural networks
• Mapping Saturn using deep learning

Cited by in corpus (29)

• Enhancing Computational Fluid Dynamics with Machine Learning
• Physics-informed neural networks for solving Reynolds-averaged Navier$\unicode{x2013}$Stokes equations
• Uncovering near-wall blood flow from sparse data with physics-informed neural networks
• Improving aircraft performance using machine learning: a review
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Experimental velocity data estimation for imperfect particle images using machine learning
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Towards an Ethical Framework in the Complex Digital Era
• Multi-scale data reconstruction of turbulent rotating flows with Gappy POD, Extended POD and Generative Adversarial Networks
• Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network
• Investigation of nonlocal data-driven methods for subgrid-scale stress modelling in large eddy simulation
• Three-dimensional generative adversarial networks for turbulent flow estimation from wall measurements
• Accelerating high order discontinuous Galerkin solvers using neural networks: 3D compressible Navier-Stokes equations
• Robust training approach of neural networks for fluid flow state estimations
• Machine-learned control-oriented flow estimation for multiactuator multi-sensor systems exemplified for the fluidic pinball
• Scalable communication for high-order stencil computations using CUDA-aware MPI
• Generative Adversarial Networks to infer velocity components in rotating turbulent flows
• Predicting the wall-shear stress and wall pressure through convolutional neural networks
• High-flexibility reconstruction of small-scale motions in wall turbulence using a generalized zero-shot learning
• Extreme vorticity events in turbulent Rayleigh-Bénard convection from stereoscopic measurements and reservoir computing
• Flow imaging as an alternative to pressure transducers through vision transformers and convolutional neural networks
• Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
• A deep learning approach to wall-shear stress quantification: From numerical training to zero-shot experimental application
• Some effects of limited wall-sensor availability on flow estimation with 3D-GANs
• On Deep-Learning-Based Closures for Algebraic Surrogate Models of Turbulent Flows
• Rotational and Reflectional Equivariant Convolutional Neural Network for data-limited applications: Multiphase Flow demonstration
• Data-driven prediction of reversal of large-scale circulation in turbulent convection