CFDNet: a deep learning-based accelerator for fluid simulations

Abstract

CFD is widely used in physical system design and optimization, where it is used to predict engineering quantities of interest, such as the lift on a plane wing or the drag on a motor vehicle. However, many systems of interest are prohibitively expensive for design optimization, due to the expense of evaluating CFD simulations. To render the computation tractable, reduced-order or surrogate models are used to accelerate simulations while respecting the convergence constraints provided by the higher-fidelity solution. This paper introduces CFDNet -- a physical simulation and deep learning coupled framework, for accelerating the convergence of Reynolds Averaged Navier-Stokes simulations. CFDNet is designed to predict the primary physical properties of the fluid including velocity, pressure, and eddy viscosity using a single convolutional neural network at its core. We evaluate CFDNet on a variety of use-cases, both extrapolative and interpolative, where test geometries are observed/not-observed during training. Our results show that CFDNet meets the convergence constraints of the domain-specific physics solver while outperforming it by 1.9 - 7.4x on both steady laminar and turbulent flows. Moreover, we demonstrate the generalization capacity of CFDNet by testing its prediction on new geometries unseen during training. In this case, the approach meets the CFD convergence criterion while still providing significant speedups over traditional domain-only models.

It has been accepted and almost published in the International Conference in Supercomputing (ICS) 2020

References in corpus (3)

• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

Cited by in corpus (11)

• Machine learning accelerated computational fluid dynamics
• Enhancing Computational Fluid Dynamics with Machine Learning
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Learning nonlocal constitutive models with neural networks
• Finite volume method network for acceleration of unsteady computational fluid dynamics: non-reacting and reacting flows
• Assessment of Neural Network Augmented Reynolds Averaged Navier Stokes Turbulence Model in Extrapolation Modes
• Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
• DrivAer Transformer: A high-precision and fast prediction method for vehicle aerodynamic drag coefficient based on the DrivAerNet++ dataset
• A Study on the Performance of Distributed Training of Data-driven CFD Simulations
• The Anatomy of Coronary Risk: How Artery Geometry Shapes Coronary Artery Disease through Blood Flow Haemodynamics -- Latest Methods, Insights and Clinical Implications
• Reducing Spatial Discretization Error on Coarse CFD Simulations Using an OpenFOAM-Embedded Deep Learning Framework