Neural vortex method: from finite Lagrangian particles to infinite dimensional Eulerian dynamics

DOI10.1016/J.COMPFLUID.2023.105811MaRDI QIDQ6100103zbMATH OpenFDO

Authors Shiying Xiong, Xingzhe He, Yunjin Tong, Yitong Deng, Bo Zhu

Publication date 21 June 2023

Published in Computers and Fluids (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2006.04178

zbMATH Keywords

Eulerian dynamicsLagrangian dynamicsneural networkvortex method

Mathematics Subject Classification ID

Vortex methods applied to problems in fluid mechanics (76M23)

Abstract: In the field of fluid numerical analysis, there has been a long-standing problem: lacking of a rigorous mathematical tool to map from a continuous flow field to discrete vortex particles, hurdling the Lagrangian particles from inheriting the high resolution of a large-scale Eulerian solver. To tackle this challenge, we propose a novel learning-based framework, the Neural Vortex Method (NVM), which builds a neural-network description of the Lagrangian vortex structures and their interaction dynamics to reconstruct the high-resolution Eulerian flow field in a physically-precise manner. The key components of our infrastructure consist of two networks: a vortex representation network to identify the Lagrangian vortices from a grid-based velocity field and a vortex interaction network to learn the underlying governing dynamics of these finite structures. By embedding these two networks with a vorticity-to-velocity Poisson solver and training its parameters using the high-fidelity data obtained from high-resolution direct numerical simulation, we can predict the accurate fluid dynamics on a precision level that was infeasible for all the previous conventional vortex methods (CVMs). To the best of our knowledge, our method is the first approach that can utilize motions of finite particles to learn infinite dimensional dynamic systems. We demonstrate the efficacy of our method in generating highly accurate prediction results, with low computational cost, of the leapfrogging vortex rings system, the turbulence system, and the systems governed by Euler equations with different external forces.

Recommendations

• The neural particle method - an updated Lagrangian physics informed neural network for computational fluid dynamics
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• Deep learning of vortex-induced vibrations
• Physics-Driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
• Machine learning for vortex induced vibration in turbulent flow

Cites work

• A comparison of semi-Lagrangian vortex method and lattice Boltzmann method for incompressible flows
• A particle method and adaptive treecode for vortex sheet motion in three-dimensional flow
• A small-scale turbulence model
• Deep learning observables in computational fluid dynamics
• Direct numerical simulation of a hypersonic transitional boundary layer at suborbital enthalpies
• Direct numerical simulation of complete H-type and K-type transitions with implications for the dynamics of turbulent boundary layers
• Effects of twist on the evolution of knotted magnetic flux tubes
• Evolution of material surfaces in the temporal transition in channel flow
• Geometric study of Lagrangian and Eulerian structures in turbulent channel flow
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• Hidden physics models: machine learning of nonlinear partial differential equations
• scientific article; zbMATH DE number 4105912 (Why is no real title available?)
• Image-based modelling of the skin-friction coefficient in compressible boundary-layer transition
• Mechanisms for generating coherent packets of hairpin vortices in channel flow
• Multi-scale geometric analysis of Lagrangian structures in isotropic turbulence
• Numerical study on U-shaped vortex formation in late boundary layer transition
• On Lagrangian and vortex-surface fields for flows with Taylor-Green and Kida-Pelz initial conditions
• On the characteristics of vortex filaments in isotropic turbulence
• On the numerical simulation of a confined cavitating tip leakage vortex under geometrical and operational uncertainties
• On Vortex Methods
• Strained spiral vortex model for turbulent fine structure
• The boundary-constraint method for constructing vortex-surface fields
• The structure of intense vorticity in isotropic turbulence
• Tracking vortex surfaces frozen in the virtual velocity in non-ideal flows
• Turbulence modeling in the age of data
• Turbulence statistics in fully developed channel flow at low Reynolds number
• Vortex methods for flow simulation

Cited in

(7)

• The neural particle method - an updated Lagrangian physics informed neural network for computational fluid dynamics
• A hybrid partitioned deep learning methodology for moving interface and fluid-structure interaction
• Machine learning the kinematics of spherical particles in fluid flows
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• Neural-network-based fluid-structure interaction applied to vortex-induced vibration
• Learning Lagrangian fluid mechanics with E(3)-equivariant graph neural networks
• Roenet: predicting discontinuity of hyperbolic systems from continuous data

This page was built for publication: Neural vortex method: from finite Lagrangian particles to infinite dimensional Eulerian dynamics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6100103)