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.
Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
Kahlert School of Computing（卡勒特计算学校）；University of Utah（犹他大学）；Department of Computing and Mathematical Sciences（计算与数学科学系）；California Institute of Technology（加州理工学院）
Over the past few years, deep learning methods have proved to be of great interest for the computational fluid dynamics community, especially when used as surrogate models, either for flow reconstruction, turbulence modeling, or for the prediction of aerodynamic coefficients. Overall, exceptional levels of accuracy have been obtained, but the robustness and reliability of the proposed approaches remain to be explored, particularly outside of the confidence region defined by the training dataset. In this contribution, we present a twin auto-encoder network for incompressible laminar flow recons…
The present study focuses on the development, application, and comparison of three computational frameworks of varying fidelities for assessing the effects of fuel sloshing in internal fuel tanks on the aeroelastic characteristics of a wing section. The first approach uses the coupling of compressible flow solver for external aerodynamics integrated with structural solver and incompressible multiphase flow solver for fuel sloshing in the embedded fuel tank As time-domain flutter solution of these coupled solvers is computationally expensive, two approximate surrogate models to emulate sloshing…
The Reynolds-averaged Navier-Stokes (RANS) equations for steady-state assessment of incompressible turbulent flows remain the workhorse for practical computational fluid dynamics (CFD) applications. Consequently, improvements in speed or accuracy have the potential to affect a diverse range of applications. We introduce a machine learning framework for the {surrogate modeling of steady-state turbulent eddy viscosities for RANS simulations, given the initial conditions. This modeling strategy} is assessed for parametric interpolation, while numerically solving for the pressure and velocity equa…
Numerical simulation is an essential tool in many areas of science and engineering, but its performance often limits application in practice or when used to explore large parameter spaces. On the other hand, surrogate deep learning models, while accelerating simulations, often exhibit poor accuracy and ability to generalise. In order to improve these two factors, we introduce REMuS-GNN, a rotation-equivariant multi-scale model for simulating continuum dynamical systems encompassing a range of length scales. REMuS-GNN is designed to predict an output vector field from an input vector field on a…
Physics-integrated neural differentiable modeling for immersed boundary systems
State Key Lab of Ocean Engineering, School of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China（海洋工程国家重点实验室，海洋与civil工程学院，上海交通大学，上海200240，中国）；State Key Laboratory of Maritime Technology and Safety, Shanghai Ship and Shipping Research Institute Co., Ltd, Shanghai 200135, China（海洋技术与安全国家重点实验室，上海船舶研究所有限公司，上海200135，中国）
University Grenoble Alpes（格勒诺布尔大学）；Institut Universitaire de France (IUF)（法兰西大学研究院）；IMT Atlantique（大西洋理工大学）；Laboratoire des Sciences du Climat et de l’Environnement (LSCE)（气候与环境科学实验室）；LOCEAN-IPSL, Sorbonne Université（巴黎索邦大学海洋与气候实验室（IPSL））
In this paper we present a new strategy to model the subgrid-scale scalar flux in a three-dimensional turbulent incompressible flow using physics-informed neural networks (NNs). When trained from direct numerical simulation (DNS) data, state-of-the-art neural networks, such as convolutional neural networks, may not preserve well known physical priors, which may in turn question their application to real case-studies. To address this issue, we investigate hard and soft constraints into the model based on classical transformation invariances and symmetries derived from physical laws. From simula…
The prohibitive cost and low fidelity of experimental data in industry scale thermofluid systems limit the usefulness of pure data-driven machine learning methods. Physics-informed neural networks (PINN) strive to overcome this by embedding the physics equations in the construction of the neural network loss function. In the present paper, the mixed-variable PINN methodology is applied to develop steady-state and transient surrogate models of incompressible laminar flow with heat transfer through a 2D internal domain with obstructions. Automatic spatial and temporal differentiation is applied …
ETH Zurich（苏黎世联邦理工学院）；ETH AI Center（苏黎世联邦理工学院人工智能中心）；Institute of Neuroinformatics, ETH Zurich（苏黎世联邦理工学院神经信息学研究所）
Aquatic locomotion is a classic fluid-structure interaction (FSI) problem of interest to biologists and engineers. Solving the fully coupled FSI equations for incompressible Navier-Stokes and finite elasticity is computationally expensive. Optimizing robotic swimmer design within such a system generally involves cumbersome, gradient-free procedures on top of the already costly simulation. To address this challenge we present a novel, fully differentiable hybrid approach to FSI that combines a 2D direct numerical simulation for the deformable solid structure of the swimmer and a physics-constra…
AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutions
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；ISIR（智能系统与机器人研究所）；Extrality（Extrality公司）；Institut Jean Le Rond d’Alembert（让·勒朗·达朗贝尔研究所）；Criteo AI Lab（Criteo人工智能实验室）
