Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D

Abstract

Physically plausible fluid simulations play an important role in modern computer graphics and engineering. However, in order to achieve real-time performance, computational speed needs to be traded-off with physical accuracy. Surrogate fluid models based on neural networks have the potential to achieve both, fast fluid simulations and high physical accuracy. However, these approaches rely on massive amounts of training data, require complex pipelines for training and inference or do not generalize to new fluid domains. In this work, we present significant extensions to a recently proposed deep learning framework, which addresses the aforementioned challenges in 2D. We go from 2D to 3D and propose an efficient architecture to cope with the high demands of 3D grids in terms of memory and computational complexity. Furthermore, we condition the neural fluid model on additional information about the fluid's viscosity and density which allows simulating laminar as well as turbulent flows based on the same surrogate model. Our method allows to train fluid models without requiring fluid simulation data beforehand. Inference is fast and simple, as the fluid model directly maps a fluid state and boundary conditions at a moment t to a subsequent fluid state at t+dt. We obtain real-time fluid simulations on a 128x64x64 grid that include various fluid phenomena such as the Magnus effect or Karman vortex streets and generalize to domain geometries not considered during training. Our method indicates strong improvements in terms of accuracy, speed and generalization capabilities over current 3D NN-based fluid models.

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• DGM: A deep learning algorithm for solving partial differential equations
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Accelerating Eulerian Fluid Simulation With Convolutional Networks
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
• Flexible Neural Representation for Physics Prediction
• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Well-balanced lattice Boltzmann equation for two-phase flows
• Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
• Learning to Control PDEs with Differentiable Physics
• Predictive Collective Variable Discovery with Deep Bayesian Models
• SPNets: Differentiable Fluid Dynamics for Deep Neural Networks
• Learning Incompressible Fluid Dynamics from Scratch -- Towards Fast, Differentiable Fluid Models that Generalize

Cited by in corpus (15)

• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
• Fast reactive flow simulations using analytical Jacobian and dynamic load balancing in OpenFOAM
• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning
• Finite Volume Graph Network(FVGN): Predicting unsteady incompressible fluid dynamics with finite volume informed neural network
• RBF-MGN:Solving spatiotemporal PDEs with Physics-informed Graph Neural Network
• LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data
• Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
• LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry
• Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
• Preconditioned FEM-based Neural Networks for Solving Incompressible Fluid Flows and Related Inverse Problems
• Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal