An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics

Abstract

We present an efficient deep learning technique for the model reduction of the Navier-Stokes equations for unsteady flow problems. The proposed technique relies on the Convolutional Neural Network (CNN) and the stochastic gradient descent method. Of particular interest is to predict the unsteady fluid forces for different bluff body shapes at low Reynolds number. The discrete convolution process with a nonlinear rectification is employed to approximate the mapping between the bluff-body shape and the fluid forces. The deep neural network is fed by the Euclidean distance function as the input and the target data generated by the full-order Navier-Stokes computations for primitive bluff body shapes. The convolutional networks are iteratively trained using the stochastic gradient descent method with the momentum term to predict the fluid force coefficients of different geometries and the results are compared with the full-order computations. We attempt to provide a physical analogy of the stochastic gradient method with the momentum term with the simplified form of the incompressible Navier-Stokes momentum equation. We also construct a direct relationship between the CNN-based deep learning and the Mori-Zwanzig formalism for the model reduction of a fluid dynamical system. A systematic convergence and sensitivity study is performed to identify the effective dimensions of the deep-learned CNN process such as the convolution kernel size, the number of kernels and the convolution layers. Within the error threshold, the prediction based on our deep convolutional network has a speed-up nearly four orders of magnitude compared to the full-order results and consumes an insignificant fraction of computational resources. The proposed CNN-based approximation procedure has a profound impact on the parametric design of bluff bodies and the feedback control of separated flows.

49 pages, 12 figures

References in corpus (1)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations

Cited by in corpus (25)

• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Intelligent metaphotonics empowered by machine learning
• Deep learning observables in computational fluid dynamics
• DeepMoD: Deep learning for Model Discovery in noisy data
• Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Graph Convolutional Neural Networks for Body Force Prediction
• Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number
• Decomposition of wake dynamics in fluid-structure interaction via low-dimensional models
• Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning
• Flow Completion Network: Inferring the Fluid Dynamics from Incomplete Flow Information using Graph Neural Networks
• Predicting waves in fluids with deep neural network
• SPNets: Differentiable Fluid Dynamics for Deep Neural Networks
• From Deep to Physics-Informed Learning of Turbulence: Diagnostics
• Prediction of laminar vortex shedding over a cylinder using deep learning
• Mechanisms of a Convolutional Neural Network for Learning Three-dimensional Unsteady Wake Flow
• A machine learning framework for data driven acceleration of computations of differential equations
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Deep learning approach in multi-scale prediction of turbulent mixing-layer
• Towards Sustainable Architecture: 3D Convolutional Neural Networks for Computational Fluid Dynamics Simulation and Reverse DesignWorkflow
• A novel Artificial Neural Network-based streamline tracing strategy applied to hypersonic waverider design
• A robust and accurate finite element framework for cavitating flows with fluid-structure interaction
• Deep learning based on PINN for solving 2 D0F vortex induced vibration of cylinder with high Reynolds number
• Deep learning based on mixed-variable physics informed neural network for solving fluid dynamics without simulation data
• Sensitivity Analysis of Lift and Drag Coefficients for Flow over Elliptical Cylinders of Arbitrary Aspect Ratio and Angle of Attack using Neural Network