Physics guided neural networks for spatio-temporal super-resolution of turbulent flows
Physics guided neural networks for spatio-temporal super-resolution of turbulent flows
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Tianshu Bao;Shengyu Chen;Taylor T. Johnson;P. Givi;S. Sammak;Xiaowei Jia
中科院分区：
文献类型：
--
作者：
Tianshu Bao;Shengyu Chen;Taylor T. Johnson;P. Givi;S. Sammak;Xiaowei Jia
湍流的直接数值模拟（DNS）计算昂贵，并且对于模拟高雷诺数下的流动不实用。低分辨率大涡模拟（LES）是一个实用的替代方案，但它的成功取决于小尺度流动动力学的建模。从低分辨率LES重建DNS对于许多科学和工程学科至关重要，但由于湍流的复杂性和生成频繁LES数据的计算成本，它对现有的超分辨率方法提出了许多挑战。在这项工作中，我们提出了一个物理指导的神经网络重建频繁DNS稀疏LES数据，提高其空间分辨率和时间频率。我们提出的方法包括一个基于偏微分方程（PDE）的递归单元，用于捕获底层的时间过程和一个物理引导的超分辨率模型，该模型包含额外的物理约束。我们证明了这两个组件在重建模拟泰勒-格林涡稀疏LES数据产生的数据的有效性。此外，我们表明，建议的经常性单位可以保留湍流的物理特性，利用Navier-Stokes方程的物理关系。
Direct numerical simulation (DNS) of turbulent flows is computationally expensive and is not practical for simulating flows at high Reynolds numbers. Low-resolution large eddy simulation (LES) is a pragmatic alternative, but its success depends on modeling of the small scale flow dynamics. Reconstructing DNS from low-resolution LES is critical for many scientific and engineering disciplines, but it poses many challenges to existing super-resolution methods due to the complexity of turbulent flows and computational cost of generating frequent LES data. In this work, we propose a physics-guided neural network for reconstructing frequent DNS from sparse LES data by enhancing its spatial resolution and temporal frequency. Our proposed method consists of a partial differential equation (PDE)-based recurrent unit for capturing underlying temporal processes and a physics-guided super-resolution model that incorporates additional physical constraints. We demonstrate the effectiveness of both components in reconstructing the data generated by simulating the Taylor-Green Vortex sparse LES data. Moreover, we show that the proposed recurrent unit can preserve the physical characteristics of turbulent flows by leveraging the physical relationships in the Navier-Stokes equation.