kth.sePublications KTH
Operational message
There are currently operational disruptions. Troubleshooting is in progress.
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 learning to develop zero-equation based turbulence model for CFD simulations of the built environment
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Sustainable Buildings.ORCID iD: 0000-0001-9287-6103
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Sustainable Buildings.ORCID iD: 0000-0003-1285-2334
2024 (English)In: Building Simulation, ISSN 1996-3599, E-ISSN 1996-8744, Vol. 17, no 3, p. 399-414Article in journal (Refereed) Published
Abstract [en]

This study aims to improve the accuracy and speed of predictions for thermal comfort and air quality in built environments by creating a coupled framework between computational fluid dynamics (CFD) simulations and deep learning models. The coupling approach is showcased by the development of a data-driven turbulence model. The new turbulence model is built using a deep learning neural network, whose mapping structure is based on a zero-equation turbulence model for built environment simulations, and is coupled with the CFD software OpenFOAM to create a hybrid framework. The neural network is a standard shallow multi-layer perceptron. The number of hidden layers and nodes per layer was optimized using Bayesan optimization algorithm. The framework is trained on an indoor environment case study, as well as tested on an indoor office simulation and an outdoor building array simulation. Results show that the deep learning based turbulence model is more robust and faster than traditional two-equation Reynolds average Navier-Stokes (RANS) turbulence models, while maintaining a similar level of accuracy. The model also outperforms the standard algebraic zero-equation model due to its superior ability to generalize to various flow scenarios. Despite some challenges, namely the mapping constraint, the limited training dataset size and the source of generation of training data, the hybrid framework demonstrates the viability of the coupling technique and serves as a starting point for future development of more reliable and advanced models.

Place, publisher, year, edition, pages
Springer Nature , 2024. Vol. 17, no 3, p. 399-414
Keywords [en]
computational fluid dynamics (CFD), neural networks, OpenFOAM, turbulence model
National Category
Fluid Mechanics Building Technologies
Identifiers
URN: urn:nbn:se:kth:diva-367103DOI: 10.1007/s12273-023-1083-4ISI: 001131873400001Scopus ID: 2-s2.0-85180665199OAI: oai:DiVA.org:kth-367103DiVA, id: diva2:1984213
Note

QC 20250715

Available from: 2025-07-15 Created: 2025-07-15 Last updated: 2025-09-05Bibliographically approved
In thesis
1. Improving built environment aerodynamics with deep learning
Open this publication in new window or tab >>Improving built environment aerodynamics with deep learning
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis explores the intersection of deep learning (DL) and computational fluid dynamics (CFD) to improve the modeling and analysis of built environmentaerodynamics. As urbanization accelerates and sustainability challenges intensify, accurate and efficient tools for airflow prediction in cities and buildings are increasingly vital. Traditional CFD methods, while powerful, are computationally demanding and limited by model assumptions, especially in turbulence modeling. This work investigates whether deep learning techniques can enhance both the speed and generalizability of aerodynamic simulations, and whether they can support experimental measurements such as those obtained from wind tunnels. The thesis presents a comprehensive framework that integrates convolutional neural networks (CNNs), graph neural networks (GNNs), and generative adversarial networks (GANs) to accelerate large eddy simulations (LES), reconstruct flow fields, and improve experimental data processing. Notably, GNN-based models are used to operate directly on unstructured CFD meshes, preserving geometric and topological information critical for urban flow predictions. Hybrid approaches that combine physics-based knowledge with data-driven models are also introduced. Applications span both simulated and experimental domains, including a case study on wind tunnel shape optimization using reinforcement learning. While deep learning models showed strong potential for improving both simulation accuracy and speed, the work also highlights important challenges, including the need for better generalization, model interpretability, and the lack of publicly available CFD datasets.The findings suggest that combining deep learning with traditional fluid dynamics offers a promising path forward, especially when supported by open data, physical constraints, and collaborative research efforts. The thesis concludes by outlining directions for future research in physics-informed learning, dataset curation, and real-time integration of predictive models into sustainable urban design.

Abstract [sv]

Denna avhandling utforskar skärningspunkten mellan djupinlärning (DL) och beräkningsströmningsdynamik (CFD) med avsikten att förbättra modellering och analys av aerodynamiken i byggda miljöer. I takt med att urbaniseringen accelererar och hållbarhetsutmaningarna blir större, blir ökar behovet av noggranna och effektiva verktyg för luftflödesprognoser i städer och byggnader. Traditionella CFD-metoder, även om de är kraftfulla, är beräkningskrävande och begränsade av modellantaganden, särskilt inom turbulensmodellering. Detta arbete undersöker om djupinlärningstekniker kan användas för att förbättra både hastigheten och generaliserbarheten hos aerodynamiska simuleringar, och om de kan stödja experimentella mätningar som erhålls från vindtunnlar. Avhandlingen presenterar ett omfattande ramverk som integrerar faltningsneurala nätverk (CNN), grafneurala nätverk (GNN) och generativa adversariella nätverk (GAN) för att accelerera simuleringar av stora virvelsimuleringar (LES), rekonstruera flödesfält och förbättra experimentell databehandling. GNN-baserade modeller används särskilt för att arbeta direkt på ostrukturerade CFD-nät, vilket bevarar geometrisk och topologisk information som är avgörande för förutsägelser av luftflöden i stadsmiljöer. Hybridmetoder som kombinerar fysikbaserad kunskap med datadrivna modeller introduceras också. Tillämpningarna spänner över både simulerade och experimentella områden, inklusive en fallstudie om optimering av en vindtunnels form med hjälp av förstärkningsinlärning (reinforcemnt learning). Djupinlärningsmodeller visade stark potential för att förbättra både simuleringsnoggrannhet och hastighet. Samtidigt belyser arbetet också viktiga utmaningar, såsom behovet av bättre generalisering, modelltolkningsbarhet och även bristen på tillgängliga CFD-data. Resultaten tyder på att kombinationen av maskininlärning med traditionell fluiddynamik erbjuder en lovande väg framåt, särskilt när det finns tillgång till av öppna data, behov med fysiska begränsningar och även gemensamma forskningsinsatser. Avhandlingen avslutas med att skissera riktningar för framtida forskning inom fysikinformerat lärande (PINNs), datasetkurering (dataset curation) och realtidsintegration av prediktiva modeller för en hållbar stadsplanering.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2025. p. 48
Series
TRITA-ABE-DLT ; 2523
Keywords
Aerodynamics, Computational Fluid dynamics, Built Environment, Urban Airflow, Deep Learning, Wind Tunnel, Artificial Intelligence, Neural Networks, Generative Adversarial Networks., Aerodynamiken, Beräkningsströmningsdynamik, Byggda Miljöer, Stadsmiljöer, Djupinlärning, Vindtunnel, Artificiell Intelligens, Neurala Nätverk, Generativa Adversariella Nätverk.
National Category
Other Civil Engineering
Research subject
Civil and Architectural Engineering, Fluid and Climate Theory
Identifiers
urn:nbn:se:kth:diva-369447 (URN)978-91-8106-346-2 (ISBN)
Public defence
2025-09-26, B3, Brinellvägen 23, KTH Campus, public video conference link [MISSING], Stockholm, 13:00 (English)
Opponent
Supervisors
Note

QC 20250905

Available from: 2025-09-05 Created: 2025-09-05 Last updated: 2025-12-16Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Calzolari, GiovanniLiu, Wei

Search in DiVA

By author/editor
Calzolari, GiovanniLiu, Wei
By organisation
Sustainable Buildings
In the same journal
Building Simulation
Fluid MechanicsBuilding Technologies

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 36 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