Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
3 files | 5.84 MB
Add to list
  1. Search results
  2. Speeding up turbulent reactive flow s...

Speeding up turbulent reactive flow simulation via a deep artificial neural network : a methodology study

Yi Ouyang (UGent) , Laurien Vandewalle (UGent) , Lin Chen (UGent) , Pieter Plehiers, Maarten Dobbelaere (UGent) , Geraldine Heynderickx (UGent) , Guy Marin (UGent) and Kevin Van Geem (UGent)
(2022) CHEMICAL ENGINEERING JOURNAL. 429.
Author
Organization
Project
Abstract
Turbulent reactive flow simulation often requires accounting for turbulence-chemistry interactions and the subgrid phenomena. Their complexity leads to a trade-off between computational efficiency on one hand and computational accuracy on the other. We attempt to bridge this gap by coupling the power of machine learning with the turbulent reactive flow simulation, specifically in the form of a deep artificial neural network. The Lagrangian Monte Carlo method is chosen as a demonstration case as it is one of the most accurate models for turbulent reactive flow simulation, but also one of the most time-consuming. The workflow consists of training data generation, deep neural network construction, and implementation in ANSYS-Fluent, followed by an evaluation of model accuracy and efficiency, which results in an order of magnitude faster simulation without loss of accuracy thanks to our data-driven deep neural network. This approach can be of universal relevance in speeding up time-consuming models in the field of reactive flow simulation.
Keywords
Industrial and Manufacturing Engineering, General Chemical Engineering, Environmental Chemistry, General Chemistry, Turbulent Reactive Flow Simulation, Artificial Neural Network, Lagrangian PDF Method, Turbulence-Chemistry Interaction, Sub-Grid Effect, PROBABILITY DENSITY-FUNCTION, PARALLEL CHEMICAL-REACTIONS, PDF METHODS, DIFFERENTIAL-EQUATIONS, MODEL, ALGORITHM, REACTORS

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 4.31 MB
  • Download
    Revised Manuscript-R2.docx
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • ZIP archive
    • |
    • 1.44 MB
  • Download
    Supplementary Information-R2.docx
    • supplementary material
    • |
    • open access
    • |
    • ZIP archive
    • |
    • 90.57 KB

Citation

Please use this url to cite or link to this publication:

MLA
Ouyang, Yi, et al. “Speeding up Turbulent Reactive Flow Simulation via a Deep Artificial Neural Network : A Methodology Study.” CHEMICAL ENGINEERING JOURNAL, vol. 429, 2022, doi:10.1016/j.cej.2021.132442.
APA
Ouyang, Y., Vandewalle, L., Chen, L., Plehiers, P., Dobbelaere, M., Heynderickx, G., … Van Geem, K. (2022). Speeding up turbulent reactive flow simulation via a deep artificial neural network : a methodology study. CHEMICAL ENGINEERING JOURNAL, 429. https://doi.org/10.1016/j.cej.2021.132442
Chicago author-date
Ouyang, Yi, Laurien Vandewalle, Lin Chen, Pieter Plehiers, Maarten Dobbelaere, Geraldine Heynderickx, Guy Marin, and Kevin Van Geem. 2022. “Speeding up Turbulent Reactive Flow Simulation via a Deep Artificial Neural Network : A Methodology Study.” CHEMICAL ENGINEERING JOURNAL 429. https://doi.org/10.1016/j.cej.2021.132442.
Chicago author-date (all authors)
Ouyang, Yi, Laurien Vandewalle, Lin Chen, Pieter Plehiers, Maarten Dobbelaere, Geraldine Heynderickx, Guy Marin, and Kevin Van Geem. 2022. “Speeding up Turbulent Reactive Flow Simulation via a Deep Artificial Neural Network : A Methodology Study.” CHEMICAL ENGINEERING JOURNAL 429. doi:10.1016/j.cej.2021.132442.
Vancouver
1.
Ouyang Y, Vandewalle L, Chen L, Plehiers P, Dobbelaere M, Heynderickx G, et al. Speeding up turbulent reactive flow simulation via a deep artificial neural network : a methodology study. CHEMICAL ENGINEERING JOURNAL. 2022;429.
IEEE
[1]
Y. Ouyang et al., “Speeding up turbulent reactive flow simulation via a deep artificial neural network : a methodology study,” CHEMICAL ENGINEERING JOURNAL, vol. 429, 2022.
@article{8726389,
  abstract     = {{Turbulent reactive flow simulation often requires accounting for turbulence-chemistry interactions and the subgrid phenomena. Their complexity leads to a trade-off between computational efficiency on one hand and computational accuracy on the other. We attempt to bridge this gap by coupling the power of machine learning with the turbulent reactive flow simulation, specifically in the form of a deep artificial neural network. The Lagrangian Monte Carlo method is chosen as a demonstration case as it is one of the most accurate models for turbulent reactive flow simulation, but also one of the most time-consuming. The workflow consists of training data generation, deep neural network construction, and implementation in ANSYS-Fluent, followed by an evaluation of model accuracy and efficiency, which results in an order of magnitude faster simulation without loss of accuracy thanks to our data-driven deep neural network. This approach can be of universal relevance in speeding up time-consuming models in the field of reactive flow simulation.}},
  articleno    = {{132442}},
  author       = {{Ouyang, Yi and Vandewalle, Laurien and Chen, Lin and Plehiers, Pieter and Dobbelaere, Maarten and Heynderickx, Geraldine and Marin, Guy and Van Geem, Kevin}},
  issn         = {{1385-8947}},
  journal      = {{CHEMICAL ENGINEERING JOURNAL}},
  keywords     = {{Industrial and Manufacturing Engineering,General Chemical Engineering,Environmental Chemistry,General Chemistry,Turbulent Reactive Flow Simulation,Artificial Neural Network,Lagrangian PDF Method,Turbulence-Chemistry Interaction,Sub-Grid Effect,PROBABILITY DENSITY-FUNCTION,PARALLEL CHEMICAL-REACTIONS,PDF METHODS,DIFFERENTIAL-EQUATIONS,MODEL,ALGORITHM,REACTORS}},
  language     = {{eng}},
  pages        = {{11}},
  title        = {{Speeding up turbulent reactive flow simulation via a deep artificial neural network : a methodology study}},
  url          = {{http://dx.doi.org/10.1016/j.cej.2021.132442}},
  volume       = {{429}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: