基于多层感知器-卷积自编码器网络的层流预混火焰非线性动力学空间分辨建模

IF 1.4 4区 工程技术 Q3 ENGINEERING, MECHANICAL
Marcin Rywik, Axel Zimmermann, Alexander J. Eder, Edoardo Scoletta, Wolfgang Polifke
{"title":"基于多层感知器-卷积自编码器网络的层流预混火焰非线性动力学空间分辨建模","authors":"Marcin Rywik, Axel Zimmermann, Alexander J. Eder, Edoardo Scoletta, Wolfgang Polifke","doi":"10.1115/1.4063788","DOIUrl":null,"url":null,"abstract":"Abstract This work presents a multilayer perceptron-convolutional autoencoder (MLP-CAE) neural network, which accurately predicts the two-dimensional flame dynamics of an acoustically excited premixed laminar flame. The architecture maps the acoustic perturbation time series to a heat release rate field, capturing flame lengths and shapes. This extends previous neural network models, which predicted only the field-integrated value. The MLP-CAE comprises two sub-models: an MLP and a CAE. The idea behind the CAE network is to find a lower dimensional latent space of the heat release rate field. The MLP is responsible for modeling the flame dynamics by transforming the acoustic forcing signal into this latent space, enabling the decoder to produce the flow field distributions. To train the MLP-CAE, computational fluid dynamics (CFD) flame simulations with a broadband acoustic forcing were used. Its normalized amplitude was set to 0.5 and 1.0, ensuring a nonlinear flame response. The network was found to accurately predict the perturbed flame shapes. Additionally, it conserved the correct frequency response as verified by the global and local flame describing functions. The MLP-CAE provides a building block towards a potential shift away from a '0D' flame analysis with the acoustic compactness assumption. Combined with an acoustic network, the generated flame fields could provide more physical insight in the thermoacoustic dynamics. Those capabilities do not come at an additional significant computational cost, as even the previous nonspatial flame models had to train on the CFD data, which included field distributions.","PeriodicalId":15685,"journal":{"name":"Journal of Engineering for Gas Turbines and Power-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Spatially Resolved Modeling of the Nonlinear Dynamics of a Laminar Premixed Flame with a Multilayer Perceptron - Convolution Autoencoder Network\",\"authors\":\"Marcin Rywik, Axel Zimmermann, Alexander J. Eder, Edoardo Scoletta, Wolfgang Polifke\",\"doi\":\"10.1115/1.4063788\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract This work presents a multilayer perceptron-convolutional autoencoder (MLP-CAE) neural network, which accurately predicts the two-dimensional flame dynamics of an acoustically excited premixed laminar flame. The architecture maps the acoustic perturbation time series to a heat release rate field, capturing flame lengths and shapes. This extends previous neural network models, which predicted only the field-integrated value. The MLP-CAE comprises two sub-models: an MLP and a CAE. The idea behind the CAE network is to find a lower dimensional latent space of the heat release rate field. The MLP is responsible for modeling the flame dynamics by transforming the acoustic forcing signal into this latent space, enabling the decoder to produce the flow field distributions. To train the MLP-CAE, computational fluid dynamics (CFD) flame simulations with a broadband acoustic forcing were used. Its normalized amplitude was set to 0.5 and 1.0, ensuring a nonlinear flame response. The network was found to accurately predict the perturbed flame shapes. Additionally, it conserved the correct frequency response as verified by the global and local flame describing functions. The MLP-CAE provides a building block towards a potential shift away from a '0D' flame analysis with the acoustic compactness assumption. Combined with an acoustic network, the generated flame fields could provide more physical insight in the thermoacoustic dynamics. Those capabilities do not come at an additional significant computational cost, as even the previous nonspatial flame models had to train on the CFD data, which included field distributions.\",\"PeriodicalId\":15685,\"journal\":{\"name\":\"Journal of Engineering for Gas Turbines and Power-transactions of The Asme\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2023-10-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Engineering for Gas Turbines and Power-transactions of The Asme\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1115/1.4063788\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Engineering for Gas Turbines and Power-transactions of The Asme","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1115/1.4063788","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0

摘要

本文提出了一种多层感知-卷积自编码器(MLP-CAE)神经网络,可以准确预测声激励预混层流火焰的二维火焰动力学。该结构将声扰动时间序列映射到热释放率场,捕获火焰长度和形状。这扩展了以前只预测场积分值的神经网络模型。MLP-CAE包括两个子模型:MLP和CAE。CAE网络背后的思想是找到一个低维的热释放率场的潜在空间。MLP负责通过将声强迫信号转换到这个潜在空间来模拟火焰动力学,使解码器能够产生流场分布。为了训练MLP-CAE,使用了计算流体动力学(CFD)火焰模拟宽带声强迫。其归一化幅度设置为0.5和1.0,确保非线性火焰响应。发现该网络能准确预测扰动火焰的形状。此外,通过全局和局部火焰描述函数的验证,该方法保持了正确的频率响应。MLP-CAE为从“0D”火焰分析转向声学紧凑性假设提供了一个基础。结合声网络,生成的火焰场可以提供更多的热声动力学物理见解。这些功能并不需要额外的计算成本,因为即使是以前的非空间火焰模型也必须根据CFD数据进行训练,其中包括现场分布。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Spatially Resolved Modeling of the Nonlinear Dynamics of a Laminar Premixed Flame with a Multilayer Perceptron - Convolution Autoencoder Network
Abstract This work presents a multilayer perceptron-convolutional autoencoder (MLP-CAE) neural network, which accurately predicts the two-dimensional flame dynamics of an acoustically excited premixed laminar flame. The architecture maps the acoustic perturbation time series to a heat release rate field, capturing flame lengths and shapes. This extends previous neural network models, which predicted only the field-integrated value. The MLP-CAE comprises two sub-models: an MLP and a CAE. The idea behind the CAE network is to find a lower dimensional latent space of the heat release rate field. The MLP is responsible for modeling the flame dynamics by transforming the acoustic forcing signal into this latent space, enabling the decoder to produce the flow field distributions. To train the MLP-CAE, computational fluid dynamics (CFD) flame simulations with a broadband acoustic forcing were used. Its normalized amplitude was set to 0.5 and 1.0, ensuring a nonlinear flame response. The network was found to accurately predict the perturbed flame shapes. Additionally, it conserved the correct frequency response as verified by the global and local flame describing functions. The MLP-CAE provides a building block towards a potential shift away from a '0D' flame analysis with the acoustic compactness assumption. Combined with an acoustic network, the generated flame fields could provide more physical insight in the thermoacoustic dynamics. Those capabilities do not come at an additional significant computational cost, as even the previous nonspatial flame models had to train on the CFD data, which included field distributions.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
3.80
自引率
20.00%
发文量
292
审稿时长
2.0 months
期刊介绍: The ASME Journal of Engineering for Gas Turbines and Power publishes archival-quality papers in the areas of gas and steam turbine technology, nuclear engineering, internal combustion engines, and fossil power generation. It covers a broad spectrum of practical topics of interest to industry. Subject areas covered include: thermodynamics; fluid mechanics; heat transfer; and modeling; propulsion and power generation components and systems; combustion, fuels, and emissions; nuclear reactor systems and components; thermal hydraulics; heat exchangers; nuclear fuel technology and waste management; I. C. engines for marine, rail, and power generation; steam and hydro power generation; advanced cycles for fossil energy generation; pollution control and environmental effects.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信