kth.sePublications KTH
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
Inductive biased-deep reinforcement learning methods for flow control: Group-invariant and positional-encoding networks improve learning reproducibility and quality
Graduate School of Integrated Energy-AI, Jeonbuk National University, 54896 Jeonju, Republic of Korea; Department of Quantum System Engineering, Jeonbuk National University, 54896 Jeonju, Republic of Korea.ORCID iD: 0000-0002-9682-966X
Independent Researcher, 0313 Oslo, Norway.ORCID iD: 0000-0002-7244-6592
KTH, School of Engineering Sciences (SCI), Engineering Mechanics.ORCID iD: 0000-0003-4373-6520
KTH, School of Engineering Sciences (SCI), Engineering Mechanics, Fluid Mechanics.ORCID iD: 0000-0003-0704-6100
Show others and affiliations
2025 (English)In: Physics of fluids, ISSN 1070-6631, E-ISSN 1089-7666, Vol. 37, no 7, article id 077189Article in journal (Refereed) Published
Abstract [en]

Flow control is key to maximize energy efficiency in a wide range of applications. Despite the advancements in deep reinforcement learning (DRL) technology, there are practical difficulties due to computational cost of exploration. Inductive biases, corresponding to prior assumptions incorporated into a deep learning architecture, can help implicitly satisfy given physical laws and thereby improve training efficiency. In this study, we propose an inductive biased-DRL method for effective flow control by developing a DRL framework coupled with a group-invariant network and positional encoding. Our methods leverage multi-agent approach to exploit policy invariance in space, in combination with developed group-invariant networks to ensure local symmetry invariance. Additionally, a positional encoding is incorporated to provide location information to the agents, mitigating action constraints from strict invariance. The proposed methods are verified using a case study of Rayleigh−Bénard convection−Nusselt number control. The group-invariant neural networks (GI-NNs) show faster convergence compared to the fully connected layer, achieving better average policy performance. The GI-NNs not only cut training time in half but also notably enhance learning reproducibility. Interestingly, positional encoding specializes in improving learning quality. These results demonstrate that developing a suitable inductive-based DRL architecture by fluid mechanics knowledge of each control problem is essential. We believe that the results of this study will not only inspire novel inductive biased-DRL methods with invariant and unique representations but also provide useful insights for flow control applications.

Place, publisher, year, edition, pages
AIP Publishing , 2025. Vol. 37, no 7, article id 077189
National Category
Control Engineering
Identifiers
URN: urn:nbn:se:kth:diva-369989DOI: 10.1063/5.0276738ISI: 001541439400001Scopus ID: 2-s2.0-105012097008OAI: oai:DiVA.org:kth-369989DiVA, id: diva2:1998800
Note

QC 20250917

Available from: 2025-09-17 Created: 2025-09-17 Last updated: 2025-09-17Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Vasanth, JoelAlcantara-Avila, FranciscoVinuesa, Ricardo

Search in DiVA

By author/editor
Jeon, JoongooRabault, JeanVasanth, JoelAlcantara-Avila, FranciscoBaral, ShilajVinuesa, Ricardo
By organisation
Engineering MechanicsFluid Mechanics
In the same journal
Physics of fluids
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 65 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