Physics-informed neural networks for solving forward and inverse flow problems via the Boltzmann-BGK formulation
Q Lou, X Meng, GE Karniadakis - Journal of Computational Physics, 2021 - Elsevier
The Boltzmann equation with the Bhatnagar-Gross-Krook collision model (Boltzmann-BGK
equation) has been widely employed to describe multiscale flows, ie, from the hydrodynamic …
equation) has been widely employed to describe multiscale flows, ie, from the hydrodynamic …
Simulation of rarefied gas flows using physics-informed neural network combined with discrete velocity method
The linearized Bhatnagar–Gross–Krook equation is widely used to describe low-speed
rarefied gas flows and can be solved numerically using deterministic methods such as the …
rarefied gas flows and can be solved numerically using deterministic methods such as the …
An implicit adaptive unified gas-kinetic scheme for steady-state solutions of nonequilibrium flows
W Long, Y Wei, K Xu - Physics of Fluids, 2024 - pubs.aip.org
In recent years, nonequilibrium flows have been frequently encountered in various
aerospace engineering and micro-electro-mechanical systems applications. To understand …
aerospace engineering and micro-electro-mechanical systems applications. To understand …
Adaptive unified gas-kinetic scheme for diatomic gases with rotational and vibrational nonequilibrium
Y Wei, W Long, K Xu - Computer Physics Communications, 2024 - Elsevier
Multiscale nonequilibrium physics at large variations of local Knudsen number are
encountered in applications of aerospace engineering and micro-electro-mechanical …
encountered in applications of aerospace engineering and micro-electro-mechanical …
[图书][B] A unified computational fluid dynamics framework from rarefied to continuum regimes
K Xu - 2021 - cambridge.org
This Element presents a unified computational fluid dynamics framework from rarefied to
continuum regimes. The framework is based on the direct modelling of flow physics in a …
continuum regimes. The framework is based on the direct modelling of flow physics in a …
On different kinetic approaches for computing planar gas expansion under pulsed evaporation into vacuum
AA Morozov, AA Frolova, VA Titarev - Physics of Fluids, 2020 - pubs.aip.org
The numerical study of one-dimensional gas expansion under pulsed evaporation into
vacuum is carried out on the basis of the direct simulation Monte Carlo method, the exact …
vacuum is carried out on the basis of the direct simulation Monte Carlo method, the exact …
Using neural networks to accelerate the solution of the Boltzmann equation
One of the biggest challenges for simulating the Boltzmann equation is the evaluation of
fivefold collision integral. Given the recent successes of deep learning and the availability of …
fivefold collision integral. Given the recent successes of deep learning and the availability of …
A global adaptive discretization of velocity space for discrete velocity methods in predictions of rarefied and multi-scale flows
By introducing a discrete velocity space (DVS), deterministic methods in gas-kinetic theory,
such as the discrete velocity method (DVM) and unified methods, can accurately capture …
such as the discrete velocity method (DVM) and unified methods, can accurately capture …
[PDF][PDF] Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation.
In this paper, we explore applications of deep learning in statistical physics. We choose the
Boltzmann equation as a typical example, where neural networks serve as a closure to its …
Boltzmann equation as a typical example, where neural networks serve as a closure to its …