2021
DOI: 10.1103/physreve.104.015309
|View full text |Cite
|
Sign up to set email alerts
|

Modeling rarefied gas-solid surface interactions for Couette flow with different wall temperatures using an unsupervised machine learning technique

Abstract: Modeling rarefied gas-solid surface interactions for Couette flow with different wall temperatures using an unsupervised machine learning technique. Physical Review E, 104(1-2), [015309].

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 12 publications
(3 citation statements)
references
References 42 publications
0
3
0
Order By: Relevance
“…Using these numbers of the Gaussian functions, the training of the GM model on a regular laptop computer takes around 3 and 40 minutes for the Ar-Au and H 2 -Ni systems. The GM model manifests its best performance when all the components of the training data are normally distributed [29]. In the case of both gas-solid pairs considered in this work, except for the normal velocities (v ′ y ,v y ) following the Rayleigh distributions, the other components in the training data follow a Gaussian distribution.…”
Section: Gm Scattering Modelmentioning
confidence: 96%
See 2 more Smart Citations
“…Using these numbers of the Gaussian functions, the training of the GM model on a regular laptop computer takes around 3 and 40 minutes for the Ar-Au and H 2 -Ni systems. The GM model manifests its best performance when all the components of the training data are normally distributed [29]. In the case of both gas-solid pairs considered in this work, except for the normal velocities (v ′ y ,v y ) following the Rayleigh distributions, the other components in the training data follow a Gaussian distribution.…”
Section: Gm Scattering Modelmentioning
confidence: 96%
“…Nevertheless, in all these scattering kernels, the gas-gas interactions that can affect the reflected gas molecules properties in the early transition regime (0.1¡Kn¡1) are ignored, and these wall models cannot deal with adsorption-related problems. Machine learning is another promising technique that can be used to establish a gas scattering kernel directly based on the collisional data obtained from MD simulations [28][29][30][31][32]. As an example, in our previous works [29,31], the Gaussian mixture (GM) approach, an unsupervised machine learning approach, was employed to construct a scattering kernel for monoatomic gases (Ar, He) interacting with the Au surface and diatomic gases (H 2 , N 2 ) interacting with the Ni surface, respectively.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation