Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation
This article establishes a data-driven modeling framework for lean hydrogen ( $ {\mathrm{H}}_2 $ )-air reaction rates for the Large Eddy Simulation (LES) of turbulent reactive flows. This is particularly challenging since $ {\mathrm{H}}_2 $ molecules diffuse much faster than heat, leading to l...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2025-01-01
|
| Series: | Data-Centric Engineering |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2632673625000012/type/journal_article |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860982832693248 |
|---|---|
| author | Quentin Malé Corentin J. Lapeyre Nicolas Noiray |
| author_facet | Quentin Malé Corentin J. Lapeyre Nicolas Noiray |
| author_sort | Quentin Malé |
| collection | DOAJ |
| description | This article establishes a data-driven modeling framework for lean hydrogen (
$ {\mathrm{H}}_2 $
)-air reaction rates for the Large Eddy Simulation (LES) of turbulent reactive flows. This is particularly challenging since
$ {\mathrm{H}}_2 $
molecules diffuse much faster than heat, leading to large variations in burning rates, thermodiffusive instabilities at the subfilter scale, and complex turbulence-chemistry interactions. Our data-driven approach leverages a Convolutional Neural Network (CNN), trained to approximate filtered burning rates from emulated LES data. First, five different lean premixed turbulent
$ {\mathrm{H}}_2 $
-air flame Direct Numerical Simulations (DNSs) are computed each with a unique global equivalence ratio. Second, DNS snapshots are filtered and downsampled to emulate LES data. Third, a CNN is trained to approximate the filtered burning rates as a function of LES scalar quantities: progress variable, local equivalence ratio, and flame thickening due to filtering. Finally, the performances of the CNN model are assessed on test solutions never seen during training. The model retrieves burning rates with very high accuracy. It is also tested on two filter and downsampling parameters and two global equivalence ratios between those used during training. For these interpolation cases, the model approximates burning rates with low error even though the cases were not included in the training dataset. This a priori study shows that the proposed data-driven machine learning framework is able to address the challenge of modeling lean premixed
$ {\mathrm{H}}_2 $
-air burning rates. It paves the way for a new modeling paradigm for the simulation of carbon-free hydrogen combustion systems. |
| format | Article |
| id | doaj-art-afe8b91a503548ffbd1bcfd93bdde701 |
| institution | Kabale University |
| issn | 2632-6736 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Data-Centric Engineering |
| spelling | doaj-art-afe8b91a503548ffbd1bcfd93bdde7012025-02-10T07:49:58ZengCambridge University PressData-Centric Engineering2632-67362025-01-01610.1017/dce.2025.1Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulationQuentin Malé0https://orcid.org/0000-0002-1890-808XCorentin J. Lapeyre1Nicolas Noiray2CAPS Laboratory, Department of Mechanical and Process Engineering, ETH Zürich, Zürich, SwitzerlandNVIDIA Corporation, Santa Clara, CA, USACAPS Laboratory, Department of Mechanical and Process Engineering, ETH Zürich, Zürich, SwitzerlandThis article establishes a data-driven modeling framework for lean hydrogen ( $ {\mathrm{H}}_2 $ )-air reaction rates for the Large Eddy Simulation (LES) of turbulent reactive flows. This is particularly challenging since $ {\mathrm{H}}_2 $ molecules diffuse much faster than heat, leading to large variations in burning rates, thermodiffusive instabilities at the subfilter scale, and complex turbulence-chemistry interactions. Our data-driven approach leverages a Convolutional Neural Network (CNN), trained to approximate filtered burning rates from emulated LES data. First, five different lean premixed turbulent $ {\mathrm{H}}_2 $ -air flame Direct Numerical Simulations (DNSs) are computed each with a unique global equivalence ratio. Second, DNS snapshots are filtered and downsampled to emulate LES data. Third, a CNN is trained to approximate the filtered burning rates as a function of LES scalar quantities: progress variable, local equivalence ratio, and flame thickening due to filtering. Finally, the performances of the CNN model are assessed on test solutions never seen during training. The model retrieves burning rates with very high accuracy. It is also tested on two filter and downsampling parameters and two global equivalence ratios between those used during training. For these interpolation cases, the model approximates burning rates with low error even though the cases were not included in the training dataset. This a priori study shows that the proposed data-driven machine learning framework is able to address the challenge of modeling lean premixed $ {\mathrm{H}}_2 $ -air burning rates. It paves the way for a new modeling paradigm for the simulation of carbon-free hydrogen combustion systems.https://www.cambridge.org/core/product/identifier/S2632673625000012/type/journal_articleartificial intelligencecomputational fluid dynamicsdata-driven reacting flow modelinghydrogen combustionmachine learning |
| spellingShingle | Quentin Malé Corentin J. Lapeyre Nicolas Noiray Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation Data-Centric Engineering artificial intelligence computational fluid dynamics data-driven reacting flow modeling hydrogen combustion machine learning |
| title | Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation |
| title_full | Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation |
| title_fullStr | Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation |
| title_full_unstemmed | Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation |
| title_short | Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation |
| title_sort | hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation |
| topic | artificial intelligence computational fluid dynamics data-driven reacting flow modeling hydrogen combustion machine learning |
| url | https://www.cambridge.org/core/product/identifier/S2632673625000012/type/journal_article |
| work_keys_str_mv | AT quentinmale hydrogenreactionratemodelingbasedonconvolutionalneuralnetworkforlargeeddysimulation AT corentinjlapeyre hydrogenreactionratemodelingbasedonconvolutionalneuralnetworkforlargeeddysimulation AT nicolasnoiray hydrogenreactionratemodelingbasedonconvolutionalneuralnetworkforlargeeddysimulation |