Published on Sun Aug 01 2021

Data Driven Macroscopic Modeling across Knudsen Numbers for Rarefied Gas Dynamics and Application to Rayleigh Scattering

Candi Zheng, Yang Wang, Shiyi Chen

The DUAL model is accurate across a range of Knudsen numbers, from dense to rarefied. It is consistent with the Navier-Stokes equation under the hydrodynamic limit, by utilizing a neural network.

1
0
0
Abstract

Macroscopic modeling of the gas dynamics across Knudsen numbers from dense gas region to rarefied gas region remains a great challenge. The reason is macroscopic models lack accurate constitutive relations valid across different Knudsen numbers. To address this problem, we proposed a Data-driven, KnUdsen number Adaptive Linear constitutive relation model named DUAL. The DUAL model is accurate across a range of Knudsen numbers, from dense to rarefied, through learning to adapt Knudsen number change from observed data. It is consistent with the Navier-Stokes equation under the hydrodynamic limit, by utilizing a constrained neural network. In addition, it naturally satisfies the second law of thermodynamics and is robust to noisy data. We test the DUAL model on the calculation of Rayleigh scattering spectra. The DUAL model gives accurate spectra for various Knudsen numbers and is superior to traditional perturbation and moment expansion methods.

Fri Mar 05 2021
Machine Learning
Physics-aware deep neural networks for surrogate modeling of turbulent natural convection
0
0
0
Fri Nov 22 2019
Machine Learning
Trend to Equilibrium for the Kinetic Fokker-Planck Equation via the Neural Network Approach
The issue of the relaxation to equilibrium has been at the core of the kinetic theory of rarefied gas dynamics. In the paper, we introduce the Deep.Neural Network (DNN) approximated solutions to the kinetic Fokker-Planck.equation.
0
0
0
Wed Jan 15 2020
Machine Learning
Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
Methodology relies on a series of deep adversarial neural network with physics-based regularization. The approach is used to simulate a 2 phase immiscible transport problem (Buckley Leverett) From a very limited dataset, the model learns the parameters of the governing equation.
0
0
0
Mon Nov 30 2020
Machine Learning
An accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data
We present a hybrid model/model-free data-driven approach to solve poroelasticity problems. We introduce one model-free and two hybrid model-based/data-driven formulations. Numerical experiments are designed to verify the implementation and compare it to other alternatives.
0
0
0
Thu Aug 05 2021
Machine Learning
Lossless Multi-Scale Constitutive Elastic Relations with Artificial Intelligence
The elastic properties of materials derive from their electronic and atomic nature. However, simulating bulk materials fully at these scales is not feasible. Here we show how this problem can be overcome by using Artificial Intelligence. A Convolutional Neural Network (CNN) model is trained, by taking the structure image of a nanoporous material as input.
1
0
0
Thu Sep 07 2017
Machine Learning
Deep Learning the Physics of Transport Phenomena
Using conditional generative adversarial networks (cGAN), we train models for steady state heat conduction andcompressible fluid flow purely on observation. Rather than using iterative numerical methods, cGANs learn to generate the solutions to these phenomena, given arbitrary boundary conditions.
0
0
0
Mon Dec 22 2014
Machine Learning
Adam: A Method for Stochastic Optimization
Adam is an algorithm for first-order gradient-based optimization of stochastic objective functions. The method is straightforward to implement and has little memory requirements. It is well suited for problems that are large in terms of data and parameters.
3
0
2
Tue Jan 10 2017
Machine Learning
Machine Learning of Linear Differential Equations using Gaussian Processes
This work leverages recent advances in probabilistic machine learning to discover conservation laws expressed by parametric linear equations. Such equations involve, but are not limited to, ordinary and partial differential,integro-differential, and fractional order operators.
0
0
0
Tue Apr 02 2019
Machine Learning
Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks
We are interested in the approximation of partial differential equations with a data-driven approach based on the reduced basis method and machine learning. We suppose that the phenomenon of interest can be modeled by a parametrized partial differential equation, but that the value of the physical parameters is unknown or difficult
0
0
0
Thu Oct 26 2017
Neural Networks
PDE-Net: Learning PDEs from Data
We propose a new feed-forward deep network, called PDE-Net, to accurately predict dynamics of complex systems and to uncover the underlying hidden PDE models. The basic idea is to learn differential operators by learning convolution kernels (filters) and apply neural networks or other machine learning methods to approximate the unknown nonlinear responses.
0
0
0
Unknown
other
Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
0
0
0
Unknown
other
Data-driven discovery of partial differential equations
0
0
0