View in EDS

An efficient intrusive deep reinforcement learning framework for OpenFOAM

Saved in:
Bibliographic Details
Title: An efficient intrusive deep reinforcement learning framework for OpenFOAM
Authors: Salehi, Saeed, 1987
Source: Artificial intelligence for enhanced hydraulic turbine lifetime Meccanica. 60(6):1673-1693
Subject Terms: Intrusive, Active flow control, OpenFOAM, Deep reinforcement learning, Computational fluid dynamics
Description: Recent advancements in artificial intelligence and deep learning offer tremendous opportunities to tackle high-dimensional and challenging problems. Particularly, deep reinforcement learning (DRL) has been shown to be able to address optimal decision-making problems and control complex dynamical systems. DRL has received increased attention in the realm of computational fluid dynamics (CFD) due to its demonstrated ability to optimize complex flow control strategies. However, DRL algorithms often suffer from low sampling efficiency and require numerous interactions between the agent and the environment, necessitating frequent data exchanges. One significant bottleneck in coupled DRL–CFD algorithms is the extensive data communication between DRL and CFD codes. Non-intrusive algorithms where the DRL agent treats the CFD environment as a black box may come with the deficiency of increased computational cost due to overhead associated with the information exchange between the two DRL and CFD modules. In this article, a TensorFlow-based intrusive DRL–CFD framework is introduced where the agent model is integrated within the open-source CFD solver OpenFOAM. The integration eliminates the need for any external information exchange during DRL episodes. The framework is parallelized using the message passing interface to manage parallel environments for computationally intensive CFD cases through distributed computing. The performance and effectiveness of the framework are verified by controlling the vortex shedding behind two and three-dimensional cylinders, achieved as a result of minimizing drag and lift forces through an active flow control mechanism. The simulation results indicate that the trained controller can stabilize the flow and effectively mitigate the vortex shedding.
File Description: electronic
Access URL: https://research.chalmers.se/publication/541542
https://research.chalmers.se/publication/541530
https://research.chalmers.se/publication/541542/file/541542_Fulltext.pdf
Database: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/541542#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=15729648&ISBN=&volume=60&issue=6&date=20250101&spage=1673&pages=1673-1693&title=Artificial intelligence for enhanced hydraulic turbine lifetime Meccanica&atitle=An%20efficient%20intrusive%20deep%20reinforcement%20learning%20framework%20for%20OpenFOAM&aulast=Salehi%2C%20Saeed&id=DOI:10.1007/s11012-024-01830-1
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Salehi%20S
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.bad5ec6a.9e93.4c57.8083.e27e6510ea54
RelevancyScore: 1115
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1114.736328125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: An efficient intrusive deep reinforcement learning framework for OpenFOAM
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Salehi%2C+Saeed%22">Salehi, Saeed</searchLink>, 1987
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Artificial intelligence for enhanced hydraulic turbine lifetime Meccanica</i>. 60(6):1673-1693
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Intrusive%22">Intrusive</searchLink><br /><searchLink fieldCode="DE" term="%22Active+flow+control%22">Active flow control</searchLink><br /><searchLink fieldCode="DE" term="%22OpenFOAM%22">OpenFOAM</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+reinforcement+learning%22">Deep reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+fluid+dynamics%22">Computational fluid dynamics</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Recent advancements in artificial intelligence and deep learning offer tremendous opportunities to tackle high-dimensional and challenging problems. Particularly, deep reinforcement learning (DRL) has been shown to be able to address optimal decision-making problems and control complex dynamical systems. DRL has received increased attention in the realm of computational fluid dynamics (CFD) due to its demonstrated ability to optimize complex flow control strategies. However, DRL algorithms often suffer from low sampling efficiency and require numerous interactions between the agent and the environment, necessitating frequent data exchanges. One significant bottleneck in coupled DRL–CFD algorithms is the extensive data communication between DRL and CFD codes. Non-intrusive algorithms where the DRL agent treats the CFD environment as a black box may come with the deficiency of increased computational cost due to overhead associated with the information exchange between the two DRL and CFD modules. In this article, a TensorFlow-based intrusive DRL–CFD framework is introduced where the agent model is integrated within the open-source CFD solver OpenFOAM. The integration eliminates the need for any external information exchange during DRL episodes. The framework is parallelized using the message passing interface to manage parallel environments for computationally intensive CFD cases through distributed computing. The performance and effectiveness of the framework are verified by controlling the vortex shedding behind two and three-dimensional cylinders, achieved as a result of minimizing drag and lift forces through an active flow control mechanism. The simulation results indicate that the trained controller can stabilize the flow and effectively mitigate the vortex shedding.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/541542" linkWindow="_blank">https://research.chalmers.se/publication/541542</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/541530" linkWindow="_blank">https://research.chalmers.se/publication/541530</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/541542/file/541542_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/541542/file/541542_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.bad5ec6a.9e93.4c57.8083.e27e6510ea54
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11012-024-01830-1
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
        StartPage: 1673
    Subjects:
      – SubjectFull: Intrusive
        Type: general
      – SubjectFull: Active flow control
        Type: general
      – SubjectFull: OpenFOAM
        Type: general
      – SubjectFull: Deep reinforcement learning
        Type: general
      – SubjectFull: Computational fluid dynamics
        Type: general
    Titles:
      – TitleFull: An efficient intrusive deep reinforcement learning framework for OpenFOAM
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Salehi, Saeed
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 15729648
            – Type: issn-print
              Value: 00256455
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 60
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Artificial intelligence for enhanced hydraulic turbine lifetime Meccanica
              Type: main
ResultId 1