Flow Completion Network: Inferring the Fluid Dynamics from Incomplete Flow Information using Graph Neural Networks

TL;DR

This paper presents a graph neural network called Flow Completion Network (FCN) that accurately infers fluid flow fields and forces from incomplete data, outperforming traditional neural networks in fluid dynamics tasks.

Contribution

The novel FCN model effectively handles both structured and unstructured data, improving fluid dynamics inference from incomplete flow information using graph attention mechanisms.

Findings

Achieves a maximum norm mean square error of 5.86% on CFD data

Outperforms traditional CNN and DNN models in accuracy

Effectively utilizes flow and gradient information simultaneously

Abstract

This paper introduces a novel neural network - flow completion network (FCN) - to infer the fluid dynamics, includ-ing the flow field and the force acting on the body, from the incomplete data based on Graph Convolution AttentionNetwork. The FCN is composed of several graph convolution layers and spatial attention layers. It is designed to inferthe velocity field and the vortex force contribution of the flow field when combined with the vortex force map (VFM)method. Compared with other neural networks adopted in fluid dynamics, the FCN is capable of dealing with bothstructured data and unstructured data. The performance of the proposed FCN is assessed by the computational fluiddynamics (CFD) data on the flow field around a circular cylinder. The force coefficients predicted by our model arevalidated against those obtained directly from CFD. Moreover, it is shown that our model effectively utilizes the exist-ing flow field information and the gradient information simultaneously, giving a better performance than the traditionalconvolution neural network (CNN)-based and deep neural network (DNN)-based models. Specifically, among all thecases of different Reynolds numbers and different proportions of the training dataset, the results show that the proposedFCN achieves a maximum norm mean square error of 5.86% in the test dataset, which is much lower than those of thetraditional CNN-based and DNN-based models (42.32% and 15.63% respectively).