View in EDS

Modeling 2D unsteady flows at moderate Reynolds numbers using a 3D convolutional neural network and a mixture of experts.

Saved in:
Bibliographic Details
Title: Modeling 2D unsteady flows at moderate Reynolds numbers using a 3D convolutional neural network and a mixture of experts.
Authors: Zigon, Bob1 (AUTHOR) robert.zigon@beckman.com, Zhu, Luoding2 (AUTHOR) luozhu@iupui.edu
Source: Computer Physics Communications. May2025, Vol. 310, pN.PAG-N.PAG. 1p.
Subjects: Convolutional neural networks, Lattice Boltzmann methods, Signal-to-noise ratio, Fluid flow, Reynolds number
Abstract: We introduce MoE-Bolt (Mixture of Experts for lattice Boltzman), a novel neural network approach for predicting the unsteady state of fluid flow past a cylinder. We modeled the problem as a sequence prediction where 8 time steps previous to time t were used to predict the velocity fields of time t. With Reynolds numbers in the training set from 138 to 196, the problem was difficult because the flow was in an unsteady-state. We used a mixture of experts (MoE) to work cooperatively on solving the problem. The advantage of this cooperation is that the computing domain was decomposed without human intervention. When 4 experts were used our solution exhibited a 15 decibel improvement in the signal to noise ratio when compared to the single expert configuration. Our results and analyses show that MoE-Bolt is an effective approach for unsteady flows and it is a stepping stone for predicting flow fields at all time instants without using data from the simulation. [ABSTRACT FROM AUTHOR]
Copyright of Computer Physics Communications is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 183379468
AccessLevel: 6
PubType: Periodical
PubTypeId: serialPeriodical
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Modeling 2D unsteady flows at moderate Reynolds numbers using a 3D convolutional neural network and a mixture of experts.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zigon%2C+Bob%22">Zigon, Bob</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> robert.zigon@beckman.com</i><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Luoding%22">Zhu, Luoding</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> luozhu@iupui.edu</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computer+Physics+Communications%22">Computer Physics Communications</searchLink>. May2025, Vol. 310, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Lattice+Boltzmann+methods%22">Lattice Boltzmann methods</searchLink><br /><searchLink fieldCode="DE" term="%22Signal-to-noise+ratio%22">Signal-to-noise ratio</searchLink><br /><searchLink fieldCode="DE" term="%22Fluid+flow%22">Fluid flow</searchLink><br /><searchLink fieldCode="DE" term="%22Reynolds+number%22">Reynolds number</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: We introduce MoE-Bolt (Mixture of Experts for lattice Boltzman), a novel neural network approach for predicting the unsteady state of fluid flow past a cylinder. We modeled the problem as a sequence prediction where 8 time steps previous to time t were used to predict the velocity fields of time t. With Reynolds numbers in the training set from 138 to 196, the problem was difficult because the flow was in an unsteady-state. We used a mixture of experts (MoE) to work cooperatively on solving the problem. The advantage of this cooperation is that the computing domain was decomposed without human intervention. When 4 experts were used our solution exhibited a 15 decibel improvement in the signal to noise ratio when compared to the single expert configuration. Our results and analyses show that MoE-Bolt is an effective approach for unsteady flows and it is a stepping stone for predicting flow fields at all time instants without using data from the simulation. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Computer Physics Communications is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=183379468
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.cpc.2025.109540
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Lattice Boltzmann methods
        Type: general
      – SubjectFull: Signal-to-noise ratio
        Type: general
      – SubjectFull: Fluid flow
        Type: general
      – SubjectFull: Reynolds number
        Type: general
    Titles:
      – TitleFull: Modeling 2D unsteady flows at moderate Reynolds numbers using a 3D convolutional neural network and a mixture of experts.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zigon, Bob
      – PersonEntity:
          Name:
            NameFull: Zhu, Luoding
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 00104655
          Numbering:
            – Type: volume
              Value: 310
          Titles:
            – TitleFull: Computer Physics Communications
              Type: main
ResultId 1