Graph neural networks for laminar flow prediction around random 2D shapes

Abstract

In the recent years, the domain of fast flow field prediction has been vastly dominated by pixel-based convolutional neural networks. Yet, the recent advent of graph convolutional neural networks (GCNNs) have attracted a considerable attention in the computational fluid dynamics (CFD) community. In this contribution, we proposed a GCNN structure as a surrogate model for laminar flow prediction around 2D obstacles. Unlike traditional convolution on image pixels, the graph convolution can be directly applied on body-fitted triangular meshes, hence yielding an easy coupling with CFD solvers. The proposed GCNN model is trained over a data set composed of CFD-computed laminar flows around 2,000 random 2D shapes. Accuracy levels are assessed on reconstructed velocity and pressure fields around out-of-training obstacles, and are compared with that of standard U-net architectures, especially in the boundary layer area.

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations
• Robust deep learning for emulating turbulent viscosities

Cited by in corpus (6)

• Attention-Enhanced Neural Network Models for Turbulence Simulation
• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• Finite Volume Graph Network(FVGN): Predicting unsteady incompressible fluid dynamics with finite volume informed neural network
• Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappings
• Robust deep learning for emulating turbulent viscosities
• Active learning of data-assimilation closures using Graph Neural Networks