Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers

Abstract

A realistic inflow boundary condition is essential for successful simulation of the developing turbulent boundary layer or channel flows. Recent advances in artificial intelligence (AI) have enabled the development of an inflow generator that performs better than the synthetic methods based on intuitions. In the present work, we applied generative adversarial networks (GANs), a representative of unsupervised learning, to generate an inlet boundary condition of turbulent channel flow. Upon learning the two-dimensional spatial structure of turbulence using data obtained from direct numerical simulation (DNS) of turbulent channel flow, the GAN could generate instantaneous flow fields that are statistically similar to those of DNS. Surprisingly, the GAN could produce fields at various Reynolds numbers without any additional simulation based on the trained data of only three Reynolds numbers. This indicates that the GAN could learn the universal nature of Reynolds number effect and might reflect other simulation conditions. Eventually, through a combination of the GAN and a recurrent neural network (RNN), we developed a novel model (RNN-GAN) that could generate time-varying fully developed flow for a long time. The spatiotemporal correlations of the generated flow are in good agreement with those of the DNS. This proves the usefulness of unsupervised learning in the generation of synthetic turbulence fields.

References in corpus (18)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Direct numerical simulation of turbulent channel flow up to $R{e}_{\tau }\approx 5200$
• Which Training Methods for GANs do actually Converge?
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Wasserstein GAN
• Data-driven prediction of unsteady flow fields over a circular cylinder using deep learning
• Stabilizing Training of Generative Adversarial Networks through Regularization
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Synthetic turbulent inflow generator using machine learning
• A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
• Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
• Modification of particle-laden near-wall turbulence: effect of Stokes number
• Compressed Convolutional LSTM: An Efficient Deep Learning framework to Model High Fidelity 3D Turbulence
• From Deep to Physics-Informed Learning of Turbulence: Diagnostics
• Prediction of laminar vortex shedding over a cylinder using deep learning
• Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation

Cited by in corpus (25)

• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
• Physics-informed data based neural networks for two-dimensional turbulence
• Synthetic Lagrangian Turbulence by Generative Diffusion Models
• Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
• Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• An AI-based Domain-Decomposition Non-Intrusive Reduced-Order Model for Extended Domains applied to Multiphase Flow in Pipes
• Generative Modeling of Turbulence
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Mechanisms of a Convolutional Neural Network for Learning Three-dimensional Unsteady Wake Flow
• Robust deep learning for emulating turbulent viscosities
• Learning the structure of wind: A data-driven nonlocal turbulence model for the atmospheric boundary layer
• Generative Adversarial Networks with Physical Evaluators for Spray Simulation of Pintle Injector
• Learning Incompressible Fluid Dynamics from Scratch -- Towards Fast, Differentiable Fluid Models that Generalize
• Meta-Learning Dynamics Forecasting Using Task Inference
• A multiscale and multicriteria Generative Adversarial Network to synthesize 1-dimensional turbulent fields
• Turbulent Injection assisted by Diffusion Models for Scale Resolving Simulations
• Extending deep learning U-Net architecture for predicting unsteady fluid flows in textured microchannels
• Modelling of Flow Past Long Cylindrical Structures