Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization

Abstract

We focus on a convolutional neural network (CNN), which has recently been utilized for fluid flow analyses, from the perspective on the influence of various operations inside it by considering some canonical regression problems with fluid flow data. We consider two types of CNN-based fluid flow analyses; 1. CNN metamodeling and 2. CNN autoencoder. For the first type of CNN with additional scalar inputs, which is one of the common forms of CNN for fluid flow analysis, we investigate the influence of input placements in the CNN training pipeline. As an example, estimation of force coefficients of an inclined flat plate and two side-by-side cylinders in laminar flows is considered. We find that care should be taken for the placement of additional scalar inputs depending on the problem setting and the complexity of flows that users handle. We then discuss the influence of various parameters and operations on the CNN performance, with the utilization of autoencoder (AE). A two-dimensional turbulence is considered for the demonstration of AE. The results of AE highly rely on the decaying nature. Investigation on the influence of padding operation at a convolutional layer is also performed. The zero padding shows reasonable ability compared to other methods which account for the boundary conditions assumed in the numerical data. Moreover, the effect of the dimensional reduction/extension methods inside CNN is also examined. The CNN model is robust against the difference in dimension reduction operations, while it is sensitive to the dimensional extension methods. The findings of this paper will help us better design a CNN architecture for practical fluid flow analysis

arXiv comment24 pages, 20 figures

References in corpus (37)

• Adam: A Method for Stochastic Optimization
• Turbulence Modeling in the Age of Data
• Deep learning for universal linear embeddings of nonlinear dynamics
• A guide to convolution arithmetic for deep learning
• Super-resolution reconstruction of turbulent flows with machine learning
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Data-driven prediction of unsteady flow fields over a circular cylinder using deep learning
• Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
• Assessment of supervised machine learning methods for fluid flows
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• Machine-learning-based reduced order modeling for unsteady flows around bluff bodies of various shapes
• Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates
• Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Synthetic turbulent inflow generator using machine learning
• Physics guided machine learning using simplified theories
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Network Structure of Two-Dimensional Decaying Isotropic Turbulence
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Experimental velocity data estimation for imperfect particle images using machine learning
• Generalization techniques of neural networks for fluid flow estimation
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Deep learning of mixing by two 'atoms' of stratified turbulence
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• Multiresolution Convolutional Autoencoders
• Data-Driven Modeling of Geometry-Adaptive Steady Heat Transfer based on Convolutional Neural Networks: Heat Conduction

Cited by in corpus (19)

• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Experimental velocity data estimation for imperfect particle images using machine learning
• Generalization techniques of neural networks for fluid flow estimation
• Sparse sensor reconstruction of vortex-impinged airfoil wake with machine learning
• Nonlinear proper orthogonal decomposition for convection-dominated flows
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions
• An accuracy-enhanced transonic flow prediction method fusing deep learning and reduced-order model
• Robust training approach of neural networks for fluid flow state estimations
• Compressing fluid flows with nonlinear machine learning: mode decomposition, latent modeling, and flow control
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks
• A Machine Learning Approach to Classify Kinematics and Vortex Wake Modes of Oscillating Foils
• Compact representation of transonic airfoil buffet flows with observable-augmented machine learning
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Convolutional causal learning for aerodynamic flows
• Low-dimensional representation of intermittent geophysical turbulence with High-Order Statistics-informed Neural Networks (H-SiNN)