kth.sePublications
Planned maintenance
A system upgrade is planned for 10/12-2024, at 12:00-13:00. During this time DiVA will be unavailable.
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Multi-agent reinforcement learning for enhanced turbulence control in bluff bodies
KTH, School of Engineering Sciences (SCI), Centres, Linné Flow Center, FLOW. KTH, School of Engineering Sciences (SCI), Engineering Mechanics.
2024 (English)Licentiate thesis, comprehensive summary (Other academic)
Sustainable development
SDG 9: Industry, innovation and infrastructure
Alternative title
Multi-agent förstärkningsinlärning för förbättrad turbulensreglering i bluffkroppar (Swedish)
Abstract [en]

This licentiate thesis explores the application of deep reinforcement learning (DRL) to flow control in bluff bodies, focusing on reducing drag forces in infinite cylinders. The research spans a range of flow conditions, from laminar to fully turbulent, aiming to advance the state-of-the-art in DRL by exploring novel scenarios not yet covered in the fluid-mechanics literature. Our focus is on the flow around cylinders in two and three dimensions, over a range of Reynolds numbers Re_D based on freestream velocity U and cylinder diameter D. We first consider a single-agent reinforcement learning (SARL) approach using the proximal-policy optimization (PPO) algorithm, coupled with the Alya numerical solver. This approach led to significant drag reductions of 20% and 17.7% for Re_D = 1000 and 2000, respectively, in a two-dimensional (2D) setting. The framework was designed for deployment on high-performance computers, enabling large-scale training with synchronized numerical simulations.

Next, we focused on three-dimensional (3D) cylinders, where spanwise instabilities emerge for Re_D > 250. Drawing inspiration from studies such as Williamson (1996) and findings from Tang et al. (2020), we explored strategies for Re_D = 100 to 400 with a multi-agent reinforcement learning (MARL) framework. This approach focused on local invariants, using multiple jets across the top and bottom surfaces. The MARL framework successfully reduced drag by 21% and 16.5% for Re_D = 300 and 400, respectively, outperforming periodic-control strategies by 10 percentage points and doubling efficiency.

Finally, the framework was tested in a fully turbulent environment at Re_D = 3900, a well-established case in the literature. Despite the significant computational challenges and complex flow structures, the MARL approach delivered significant results, with an 8.3% drag reduction and reducing the mass flow used in the actuation by two orders of magnitude compared with Kim & Choi (2005). Across these studies, the drag-reduction mechanisms learned by the agents involve altering the wake topology to attenuate and move the location of the Reynolds-stresses maximum values upstream, focusing on enlarging the recirculation bubble and reducing pressure drag.

Abstract [sv]

Denna licentiatavhandling utforskar möjligheten att använda förstärkningsin-lärning (DRL) för strömningskontroll kring trubbiga kroppar där speciellt fokus ligger på att minska motståndskrafterna på oändliga cylindrar. En rad strömningsförhållanden undersöks från laminärt till fullt utvecklad turbulent strömning. Målet är att bygga vidare på den senaste utvecklingen inom DRL genom att utforska nya strömningsförhållanden som ännu inte har behandlats inom strömningsmekaniken. Vårt fokus ligger på strömning runt cylindrar i två och tre dimensioner samt över ett spektrum av Reynolds-tal Re_D baserat på fri strömningshastigheten U och cylinderns diameter D. I den första delen av avhandlingen utvecklades en enskild agent-förstärkningsinlärningsmetod med proximal policy optimization kopplad till den numeriska lösaren Alya. Denna metod ledde till betydande minskningar i motståndskrafterna på 20% och 17,7% för Re_D = 1000 och 2000 i en tvådimensionell (2D) miljö. Detta ramverk för kontroll, numerisk simulering och analys utformades för att köras på högpresterande datorer vilket möjliggjorde storskalig träning av nätverket med synkroniserade numeriska simuleringar. Därefter fokuserade vi på tredimensionella (3D) cylindrar, där instabiliteter längs cylinderaxeln uppträder vid Re_D > 250. Inspirerade av studier som Williamson (1996) och resultat från Tang et al. (2020), undersökte vi strategier för Re_D = 100 till 400 med ett multiagent-förstärkningsinlärningsramverk (MARL). Denna metod fokuserade på lokala invariansprinciper och använde flera jetstrålar över cylinderns övre och nedre ytor för kontroll av strömningen. MARL-ramverket minskade motståndet med 21% respektive 16,5% för Re_D = 300 och 400 och överträffade periodiska kontrollstrategier med 10 procentenheter och fördubblade effektiviteten. Slutligen testades ramverket på turbulent strömning vid Re_D = 3900, ett välkänt fall i litteraturen. Trots beräkningsutmaningar och komplexa flödesstrukturer minskade MARL motståndet med 8,3% och massflödet med två storleksordningar jämfört med Kim & Choi (2005). Gemensamt för våra studier är att de motståndsminskande mekanismer som lärts av agenterna involverar att förändra strömningsvakens topologi för att dämpa och flytta Reynolds-stressernas maximala värden uppströms. Detta leder till förstora återcirkulationsbubblan och minska tryckmotståndet.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2024. , p. 124
Series
TRITA-SCI-FOU ; 2024:53
Keywords [en]
Machine learning, active flow control, deep reinforcement learning, fluid mechanics, turbulence
Keywords [sv]
Fluidmekanik, laminär-turbulent övergång, aktiv flödeskontroll, dragreduktion, maskininlärning, djup förstärkningsinlärning
National Category
Fluid Mechanics and Acoustics Engineering and Technology
Research subject
Engineering Mechanics
Identifiers
URN: urn:nbn:se:kth:diva-356281ISBN: 978-91-8106-103-1 (print)OAI: oai:DiVA.org:kth-356281DiVA, id: diva2:1912939
Presentation
2024-12-05, F2, Kungliga Tekniska Högskolan, Lindstedtsvägen 26 & 28, Stockholm, 13:00 (English)
Opponent
Supervisors
Funder
EU, European Research Council, grant no.2021-CoG-101043998, DEEPCONTROL
Note

QC 241114

Available from: 2024-11-14 Created: 2024-11-13 Last updated: 2024-11-18Bibliographically approved
List of papers
1. Deep Reinforcement Learning for Flow Control Exploits Different Physics for Increasing Reynolds Number Regimes
Open this publication in new window or tab >>Deep Reinforcement Learning for Flow Control Exploits Different Physics for Increasing Reynolds Number Regimes
Show others...
2022 (English)In: Actuators, E-ISSN 2076-0825, Vol. 11, no 12, p. 359-359Article in journal (Refereed) Published
Place, publisher, year, edition, pages
MDPI AG, 2022
National Category
Physical Sciences Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-356269 (URN)10.3390/act11120359 (DOI)000900414000001 ()2-s2.0-85144726353 (Scopus ID)
Note

QC 20241113

Available from: 2024-11-13 Created: 2024-11-13 Last updated: 2024-11-13Bibliographically approved
2. Flow control of three-dimensional cylinders transitioning to turbulence via multi-agent reinforcement learning
Open this publication in new window or tab >>Flow control of three-dimensional cylinders transitioning to turbulence via multi-agent reinforcement learning
Show others...
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Designing active-flow-control (AFC) strategies for three-dimensional (3D) bluff bodies is a challenging task with critical industrial implications. In this study we explore the potential of discovering novel control strategies for drag reduction using deep reinforcement learning. We introduce a high-dimensional AFC setup on a 3D cylinder, considering Reynolds numbers (ReD) from 100 to 400, which is a range including the transition to 3D wake instabilities. The setup involves multiple zero-net-mass-flux jets positioned on the top and bottom surfaces, aligned into two slots. The method relies on coupling the computational-fluid-dynamics solver with a multi-agent reinforcement-learning (MARL) framework based on the proximal-policy-optimization algorithm. MARL offers several advantages: it exploits local invariance, adaptable control across geometries, facilitates transfer learning and cross-application of agents, and results in a significant training speedup. For instance, our results demonstrate 21% drag reduction for ReD=300, outperforming classical periodic control, which yields up to 6% reduction. To the authors' knowledge, the present MARL-based framework represents the first time where training is conducted in 3D cylinders. This breakthrough paves the way for conducting AFC on progressively more complex turbulent-flow configurations.

Keywords
Machine learning, active flow control, deep reinforcement learning, fluid mechanics
National Category
Fluid Mechanics and Acoustics Engineering and Technology
Research subject
Aerospace Engineering
Identifiers
urn:nbn:se:kth:diva-356270 (URN)10.48550/arXiv.2405.17210 (DOI)
Note

Under review in Nature Engineering Communications

QC 20241113

Available from: 2024-11-13 Created: 2024-11-13 Last updated: 2024-11-13Bibliographically approved
3. Active flow control for drag reduction through multi-agent reinforcement learning on a turbulent cylinder at ReD=3900
Open this publication in new window or tab >>Active flow control for drag reduction through multi-agent reinforcement learning on a turbulent cylinder at ReD=3900
Show others...
(English)Manuscript (preprint) (Other academic)
Abstract [en]

This study presents novel active-flow-control (AFC) strategies aimed at achieving drag reduction for a three-dimensional cylinder immersed in a flow at a Reynolds number based on freestream velocity and cylinder diameter of (Re_D=3900). The cylinder in this subcritical flow regime has been extensively studied in the literature and is considered a classic case of turbulent flow arising from a bluff body. The strategies presented are explored through the use of deep reinforcement learning. The cylinder is equipped with 10 independent zero-net-mass-flux jet pairs, distributed on the top and bottom surfaces, which define the AFC setup. The method is based on the coupling between a computational-fluid-dynamics solver and a multi-agent reinforcement-learning (MARL) framework using the proximal-policy-optimization algorithm. Thanks to the acceleration in training facilitated by exploiting the local invariants with MARL, a drag reduction of (8\%) was achieved, with a mass cost efficiency two orders of magnitude lower than those of the existing classical controls in the literature. This development represents a significant advancement in active flow control, particularly in turbulent regimes critical to industrial applications.

Keywords
Machine learning, active flow control, deep reinforcement learning, fluid mechanics
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-356279 (URN)10.48550/arXiv.2405.17655 (DOI)
Note

QC 20241115

Available from: 2024-11-13 Created: 2024-11-13 Last updated: 2024-11-15Bibliographically approved

Open Access in DiVA

summary_licentiate_SUAREZ(18387 kB)45 downloads
File information
File name FULLTEXT01.pdfFile size 18387 kBChecksum SHA-512
aef177419fb5e212baeeb32094d18ad211830f5768cb94f96d0e27f9d4953ceaadbcb343581d490be41da1395c69bd068e2fd185b17adecf7b902ba09ca57c17
Type summaryMimetype application/pdf

Authority records

Suarez, Pol

Search in DiVA

By author/editor
Suarez, Pol
By organisation
Linné Flow Center, FLOWEngineering Mechanics
Fluid Mechanics and AcousticsEngineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 101 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf