Physics-driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks

Abstract

Recently, physics-driven deep learning methods have shown particular promise for the prediction of physical fields, especially to reduce the dependency on large amounts of pre-computed training data. In this work, we target the physics-driven learning of complex flow fields with high resolutions. We propose the use of \emph{Convolutional neural networks} (CNN) based U-net architectures to efficiently represent and reconstruct the input and output fields, respectively. By introducing Navier-Stokes equations and boundary conditions into loss functions, the physics-driven CNN is designed to predict corresponding steady flow fields directly. In particular, this prevents many of the difficulties associated with approaches employing fully connected neural networks. Several numerical experiments are conducted to investigate the behavior of the CNN approach, and the results indicate that a first-order accuracy has been achieved. Specifically for the case of a flow around a cylinder, different flow regimes can be learned and the adhered "twin-vortices" are predicted correctly. The numerical results also show that the training for multiple cases is accelerated significantly, especially for the difficult cases at low Reynolds numbers, and when limited reference solutions are used as supplementary learning targets.

arXiv comment29 pages 13 figures

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• DeepXDE: A deep learning library for solving differential equations
• Turbulence Modeling in the Age of Data
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• PDE-Net: Learning PDEs from Data
• DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks
• Learning to Control PDEs with Differentiable Physics
• Weakly-Supervised Deep Learning of Heat Transport via Physics Informed Loss
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks

Cited by in corpus (2)

• Learning finite difference methods for reaction-diffusion type equations with FCNN
• Splitting physics-informed neural networks for inferring the dynamics of integer- and fractional-order neuron models