{"title":"基于卷积神经网络的大涡模拟氢反应速率建模","authors":"Quentin Malé, Corentin J Lapeyre, Nicolas Noiray","doi":"arxiv-2408.16709","DOIUrl":null,"url":null,"abstract":"This paper establishes a data-driven modeling framework for lean Hydrogen\n(H2)-air reaction rates for the Large Eddy Simulation (LES) of turbulent\nreactive flows. This is particularly challenging since H2 molecules diffuse\nmuch faster than heat, leading to large variations in burning rates,\nthermodiffusive instabilities at the subfilter scale, and complex\nturbulence-chemistry interactions. Our data-driven approach leverages a\nConvolutional Neural Network (CNN), trained to approximate filtered burning\nrates from emulated LES data. First, five different lean premixed turbulent\nH2-air flame Direct Numerical Simulations (DNSs) are computed each with a\nunique global equivalence ratio. Second, DNS snapshots are filtered and\ndownsampled to emulate LES data. Third, a CNN is trained to approximate the\nfiltered burning rates as a function of LES scalar quantities: progress\nvariable, local equivalence ratio and flame thickening due to filtering.\nFinally, the performances of the CNN model are assessed on test solutions never\nseen during training. The model retrieves burning rates with very high\naccuracy. It is also tested on two filter and downsampling parameters and two\nglobal equivalence ratios between those used during training. For these\ninterpolation cases, the model approximates burning rates with low error even\nthough the cases were not included in the training dataset. This a priori study\nshows that the proposed data-driven machine learning framework is able to\naddress the challenge of modeling lean premixed H2-air burning rates. It paves\nthe way for a new modeling paradigm for the simulation of carbon-free hydrogen\ncombustion systems.","PeriodicalId":501309,"journal":{"name":"arXiv - CS - Computational Engineering, Finance, and Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation\",\"authors\":\"Quentin Malé, Corentin J Lapeyre, Nicolas Noiray\",\"doi\":\"arxiv-2408.16709\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper establishes a data-driven modeling framework for lean Hydrogen\\n(H2)-air reaction rates for the Large Eddy Simulation (LES) of turbulent\\nreactive flows. This is particularly challenging since H2 molecules diffuse\\nmuch faster than heat, leading to large variations in burning rates,\\nthermodiffusive instabilities at the subfilter scale, and complex\\nturbulence-chemistry interactions. Our data-driven approach leverages a\\nConvolutional Neural Network (CNN), trained to approximate filtered burning\\nrates from emulated LES data. First, five different lean premixed turbulent\\nH2-air flame Direct Numerical Simulations (DNSs) are computed each with a\\nunique global equivalence ratio. Second, DNS snapshots are filtered and\\ndownsampled to emulate LES data. Third, a CNN is trained to approximate the\\nfiltered burning rates as a function of LES scalar quantities: progress\\nvariable, local equivalence ratio and flame thickening due to filtering.\\nFinally, the performances of the CNN model are assessed on test solutions never\\nseen during training. The model retrieves burning rates with very high\\naccuracy. It is also tested on two filter and downsampling parameters and two\\nglobal equivalence ratios between those used during training. For these\\ninterpolation cases, the model approximates burning rates with low error even\\nthough the cases were not included in the training dataset. This a priori study\\nshows that the proposed data-driven machine learning framework is able to\\naddress the challenge of modeling lean premixed H2-air burning rates. It paves\\nthe way for a new modeling paradigm for the simulation of carbon-free hydrogen\\ncombustion systems.\",\"PeriodicalId\":501309,\"journal\":{\"name\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.16709\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computational Engineering, Finance, and Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.16709","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
本文为湍流反应流的大涡模拟(LES)建立了一个数据驱动的氢气(H2)-空气反应速率建模框架。这尤其具有挑战性,因为 H2 分子的扩散速度远远快于热量的扩散速度,从而导致燃烧速率的巨大变化、亚过滤器尺度的热扩散不稳定性以及湍流与化学的全面相互作用。我们的数据驱动方法利用了经过训练的卷积神经网络(CNN),以近似模拟 LES 数据中的过滤燃烧率。首先,计算五种不同的贫预混湍流 H2-空气火焰直接数值模拟(DNS),每种模拟都具有独特的全局等效比。其次,对 DNS 快照进行过滤和降采样,以模拟 LES 数据。第三,对 CNN 进行训练,以便将过滤后的燃烧率近似为 LES 标量的函数:进度变量、局部等效比和过滤导致的火焰增厚。该模型能非常准确地检索出燃烧率。此外,还对两个滤波和下采样参数以及两个全球等值比进行了测试。对于这些插值情况,模型以较低的误差逼近了燃烧率,尽管这些情况并未包含在训练数据集中。这项先验研究表明,所提出的数据驱动机器学习框架能够解决贫油预混合 H2- 空气燃烧率建模的难题。它为模拟无碳氢气燃烧系统的新建模范例铺平了道路。
Hydrogen reaction rate modeling based on convolutional neural network for large eddy simulation
This paper establishes a data-driven modeling framework for lean Hydrogen
(H2)-air reaction rates for the Large Eddy Simulation (LES) of turbulent
reactive flows. This is particularly challenging since H2 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
H2-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 H2-air burning rates. It paves
the way for a new modeling paradigm for the simulation of carbon-free hydrogen
combustion systems.