CFDNet: a deep learning-based accelerator for fluid simulations
CFDNet: a deep learning-based accelerator for fluid simulations
复制标题
DOI：
10.1145/3392717.3392772
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Octavi Obiols-Sales;Abhinav Vishnu;Nicholas Malaya;Aparna Chandramowlishwaran
中科院分区：
文献类型：
--
作者：
Octavi Obiols-Sales;Abhinav Vishnu;Nicholas Malaya;Aparna Chandramowlishwaran
CFD被广泛应用于物理系统设计和优化中，用于预测感兴趣的工程量，如飞机机翼上的升力或机动车辆上的阻力。然而，由于评估CFD模拟的费用，许多感兴趣的系统对于设计优化来说都昂贵得令人望而却步。为了使计算更容易处理，使用降阶或代理模型来加速模拟，同时考虑到高保真解决方案提供的收敛约束。本文介绍了一种物理模拟和深度学习耦合框架CFDNet，用于加速雷诺平均N-S模拟的收敛。CFDNet的设计目的是在其核心使用一个卷积神经网络来预测流体的主要物理性质，包括速度、压力和涡流粘度。我们在各种用例上评估CFDNet，包括外推和内插，在这些用例中，测试几何在训练期间被观察到/没有被观察到。我们的结果表明，CFDNet满足区域特定物理求解器的收敛限制，而在定常层流和湍流上的性能都比它高1.9-7.4倍。此外，我们通过测试CFDNet对训练中未见的新几何形状的预测来验证其泛化能力。在这种情况下，该方法满足CFD收敛标准，同时与传统的仅限领域的模型相比仍提供显著的加速比。
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.