kth.sePublications
Change search
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
Deep reinforcement learning for turbulent drag reduction in channel flows
KTH, School of Engineering Sciences (SCI), Centres, Linné Flow Center, FLOW. KTH, Centres, SeRC - Swedish e-Science Research Centre. KTH, School of Engineering Sciences (SCI), Engineering Mechanics, Fluid Mechanics and Engineering Acoustics.ORCID iD: 0000-0002-8589-1572
Norwegian Meteorol Inst, IT Dept, Postboks 43, N-0313 Oslo, Norway..
KTH, School of Engineering Sciences (SCI), Centres, Linné Flow Center, FLOW. KTH, Centres, SeRC - Swedish e-Science Research Centre. KTH, School of Engineering Sciences (SCI), Engineering Mechanics, Fluid Mechanics and Engineering Acoustics.ORCID iD: 0000-0001-9627-5903
KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. KTH, Centres, SeRC - Swedish e-Science Research Centre.ORCID iD: 0000-0001-5211-6388
Show others and affiliations
2023 (English)In: The European Physical Journal E Soft matter, ISSN 1292-8941, E-ISSN 1292-895X, Vol. 46, no 4, article id 27Article in journal (Refereed) Published
Abstract [en]

We introduce a reinforcement learning (RL) environment to design and benchmark control strategies aimed at reducing drag in turbulent fluid flows enclosed in a channel. The environment provides a framework for computationally efficient, parallelized, high-fidelity fluid simulations, ready to interface with established RL agent programming interfaces. This allows for both testing existing deep reinforcement learning (DRL) algorithms against a challenging task, and advancing our knowledge of a complex, turbulent physical system that has been a major topic of research for over two centuries, and remains, even today, the subject of many unanswered questions. The control is applied in the form of blowing and suction at the wall, while the observable state is configurable, allowing to choose different variables such as velocity and pressure, in different locations of the domain. Given the complex nonlinear nature of turbulent flows, the control strategies proposed so far in the literature are physically grounded, but too simple. DRL, by contrast, enables leveraging the high-dimensional data that can be sampled from flow simulations to design advanced control strategies. In an effort to establish a benchmark for testing data-driven control strategies, we compare opposition control, a state-of-the-art turbulence-control strategy from the literature, and a commonly used DRL algorithm, deep deterministic policy gradient. Our results show that DRL leads to 43% and 30% drag reduction in a minimal and a larger channel (at a friction Reynolds number of 180), respectively, outperforming the classical opposition control by around 20 and 10 percentage points, respectively.

Place, publisher, year, edition, pages
Springer Nature , 2023. Vol. 46, no 4, article id 27
National Category
Fluid Mechanics
Identifiers
URN: urn:nbn:se:kth:diva-326639DOI: 10.1140/epje/s10189-023-00285-8ISI: 000967498000001PubMedID: 37039923Scopus ID: 2-s2.0-85152244557OAI: oai:DiVA.org:kth-326639DiVA, id: diva2:1785538
Note

Correction in European Physical Journal, vol. 46, issue. 6 DOI:10.1140/epje/s10189-023-00304-8, Scopus:2-s2.0-85163738742

QC 20230509

Available from: 2023-05-09 Created: 2023-08-03 Last updated: 2025-02-09Bibliographically approved
In thesis
1. Time, space and control: deep-learning applications to turbulent flows
Open this publication in new window or tab >>Time, space and control: deep-learning applications to turbulent flows
2023 (English)Doctoral thesis, comprehensive summary (Other academic)
Alternative title[sv]
Tid, rum och kontroll: djupinlärningsapplikationer för turbulenta flöden
Abstract [en]

In the present thesis, the application of deep learning and deep reinforcement learning to turbulent-flow simulations is investigated. Deep-learning models are trained to perform temporal and spatial predictions, while deep reinforcement learning is applied to a flow-control problem, namely the reduction of drag in an open channel flow. Long short-term memory (LSTM, Hochreiter & Schmidhuber 1997) networks and Koopman non-linear forcing (KNF) models are optimized to perform temporal predictions in two reduced-order-models of turbulence, namely the nine-equations model proposed by Moehlis et al. (2004) and a truncated proper orthogonal decomposition (POD) of a minimal channel flow (Jiménez & Moin 1991). In the first application, both models are able to produce accurate short-term predictions. Furthermore, the predicted system trajectories are statistically correct. KNF models outperform LSTM networks in short-term predictions, with a much lower training computational cost. In the second task, only LSTMs can be trained successfully, predicting trajectories that are statistically accurate. Spatial predictions are performed in two turbulent flows: an open channel flow and a boundary-layer flow. Fully-convolutional networks (FCNs) are used to predict two-dimensional velocity-fluctuation fields at a given wall-normal location using wall measurements (and vice versa). Thanks to the non-linear nature of these models, they provide a better reconstruction performance than optimal linear methods like extended POD (Borée 2003). Finally, we show the potential of deep reinforcement learning in discovering new control strategies for turbulent flows. By framing the fluid-dynamics problem as a multi-agent reinforcement-learning environment and by training the agents using a location-invariant deep deterministic policy-gradient (DDPG) algorithm, we are able to learn a control strategy that achieves a remarkable 30% drag reduction, improving over existing strategies by about 10 percentage points.

Abstract [sv]

I den förinställda avhandlingen undersöks tillämpningen av djupinlärning och djupförstärkningsinlärning på turbulenta flödessimuleringar. Modeller för djupinlärning tränas för att utföra tids- och rumsförutsägelser, medan djupförstärkningsinlärning tillämpas på ett flödeskontrollproblem, nämligen minskningen av motståndet i ett öppet kanalflöde. Long short-term memory (LSTM, Hochreiter & Schmidhuber 1997) nätverk och Koopman non-linear forcing (KNF) modeller optimeras för att utföratidsförutsägelser i två turbulensmodeller med reducerad ordning, nämligen nio-ekvationsmodellen som föreslagits av Moehlis et al. (2004) och en trunkerad proper orthogonal decomposition (POD) av ett minimalt kanalflöde (Jiménez & Moin 1991). I den första applikationen kan båda modellerna producera korrekta korttidsförutsägelser, dessutom är de förutsagda trajektorierna statistiskt korrekta. KNF-modeller överträffar LSTM-nätverk i kortsiktiga förutsägelser, med en mycket lägre utbildningsberäkningskostnad. I den andra uppgiften kan endast LSTM nätverken tränas framgångsrikt, med trajektorier som är statistiskt korrekta. Spatiala förutsägelser utförs i två turbulenta flöden, en öppen kanal flöde och en gränsskikt. Fully-convolutional networks (FCN) används för att förutsäga tvådimensionella hastighetsfluktuationsfält vid givet avstånd från väggen med hjälp av väggmätningar (och vice versa). Tack vare deras icke-linjär karaktär ger dessa modeller bättre rekonstruktionsprestanda än optimala linjära metoder som extended POD (Borée 2003). Slutligen visar vi potentialen med djup förstärkningsinlärning för att upptäcka nya kontrollstrategier i turbulenta flöden. Genom att inrama strömningsmekaniska problemet som en förstärknings-inlärningsmiljö med flera agenter och genom att träna agenterna med hjälp av en positionsinvariant deep deterministic policy gradient (DDPG) algoritm, kan vi lära oss en kontrollstrategi som uppnår en anmärkningsvärd 30% minskning av luftmotståndet, vilket jämfört med existerande strategier är en förbättring med cirka 10 procentenheter.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2023. p. 342
Series
TRITA-SCI-FOU ; 2023:27
Keywords
turbulence, deep learning, deep reinforcement learning, flow control, turbulens, djupinlärning, djupförstärkningsinlärning, flödeskontroll
National Category
Fluid Mechanics
Research subject
Engineering Mechanics
Identifiers
urn:nbn:se:kth:diva-326961 (URN)978-91-8040-601-7 (ISBN)
Public defence
2023-06-12, F3, Lindstedtsvägen 26 & 28, Stockholm, 10:00 (English)
Opponent
Supervisors
Funder
EU, European Research Council, 2021-CoG-101043998, DEEPCONTROLSwedish e‐Science Research CenterKnut and Alice Wallenberg Foundation
Note

QC 230516

Available from: 2023-05-16 Created: 2023-05-15 Last updated: 2025-02-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Guastoni, LucaSchlatter, PhilippAzizpour, HosseinVinuesa, Ricardo

Search in DiVA

By author/editor
Guastoni, LucaSchlatter, PhilippAzizpour, HosseinVinuesa, Ricardo
By organisation
Linné Flow Center, FLOWSeRC - Swedish e-Science Research CentreFluid Mechanics and Engineering AcousticsScience for Life Laboratory, SciLifeLabRobotics, Perception and Learning, RPL
In the same journal
The European Physical Journal E Soft matter
Fluid Mechanics

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 253 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