Fluid Simulation System Based on Graph Neural Network

TL;DR

This paper introduces a graph neural network-based fluid simulation system that significantly accelerates computation and reduces resource consumption while maintaining high accuracy, enabling real-time fluid flow analysis.

Contribution

The authors develop a novel fluid simulation approach using attention graph neural networks, achieving high speed and accuracy with the ability to extrapolate beyond training data.

Findings

Achieves 100-1000x speedup over traditional CFD methods.

Maintains high accuracy in flow field prediction.

Capable of extrapolating flow fields outside training scenarios.

Abstract

Traditional computational fluid dynamics calculates the physical information of the flow field by solving partial differential equations, which takes a long time to calculate and consumes a lot of computational resources. We build a fluid simulation simulator based on the graph neural network architecture. The simulator has fast computing speed and low consumption of computing resources. We regard the computational domain as a structural graph, and the computational nodes in the structural graph determine neighbor nodes through adaptive sampling. Building deep learning architectures with attention graph neural networks. The fluid simulation simulator is trained according to the simulation results of the flow field around the cylinder with different Reynolds numbers. The trained fluid simulation simulator not only has a very high accuracy for the prediction of the flow field in the training set, but also can extrapolate the flow field outside the training set. Compared to traditional CFD solvers, the fluid simulation simulator achieves a speedup of 2-3 orders of magnitude. The fluid simulation simulator provides new ideas for the rapid optimization and design of fluid mechanics models and the real-time control of intelligent fluid mechanisms.