Unsteady-state turbulent flow field predictions with a convolutional autoencoder architecture

IF 1.8 3区 数学 Q1 MATHEMATICS
Álvaro Abucide, Koldo Portal, Unai Fernandez-Gamiz, Ekaitz Zulueta, Iker Azurmendi
{"title":"Unsteady-state turbulent flow field predictions with a convolutional autoencoder architecture","authors":"Álvaro Abucide, Koldo Portal, Unai Fernandez-Gamiz, Ekaitz Zulueta, Iker Azurmendi","doi":"10.3934/math.20231522","DOIUrl":null,"url":null,"abstract":"<abstract> <p>Traditional numerical methods, such as computational fluid dynamics (CFD), demand large computational resources and memory for modeling fluid dynamic systems. Hence, deep learning (DL) and, specifically Convolutional Neural Networks (CNN) autoencoders have resulted in accurate tools to obtain approximations of the streamwise and vertical velocities and pressure fields, when stationary flows are considered. The novelty of this paper consists of predicting the future instants from an initial one with a CNN autoencoder architecture when an unsteady flow is considered. Two neural models are proposed: The former predicts the future instants on the basis of an initial sample and the latter approximates the initial sample. The inputs of the CNNs take the signed distance function (SDF) and the flow region channel (FRC), and, for the representation of the temporal evolution, the previous CFD sample is added. To increment the amount of training data of the second neural model, a data augmentation technique based on the similarity principle for fluid dynamics is implemented. As a result, low absolute error rates are obtained in the prediction of the first samples near the shapes surfaces. Even in the most advanced time instants, the prediction of the vortices zone is quite reliable. 62.12 and 9000 speed-up ratios are achieved by the predictions of the first and second neural models, respectively, compared to the computational cost regarded by the CFD simulations.</p> </abstract>","PeriodicalId":48562,"journal":{"name":"AIMS Mathematics","volume":"159 1","pages":"0"},"PeriodicalIF":1.8000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"AIMS Mathematics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3934/math.20231522","RegionNum":3,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICS","Score":null,"Total":0}
引用次数: 0

Abstract

Traditional numerical methods, such as computational fluid dynamics (CFD), demand large computational resources and memory for modeling fluid dynamic systems. Hence, deep learning (DL) and, specifically Convolutional Neural Networks (CNN) autoencoders have resulted in accurate tools to obtain approximations of the streamwise and vertical velocities and pressure fields, when stationary flows are considered. The novelty of this paper consists of predicting the future instants from an initial one with a CNN autoencoder architecture when an unsteady flow is considered. Two neural models are proposed: The former predicts the future instants on the basis of an initial sample and the latter approximates the initial sample. The inputs of the CNNs take the signed distance function (SDF) and the flow region channel (FRC), and, for the representation of the temporal evolution, the previous CFD sample is added. To increment the amount of training data of the second neural model, a data augmentation technique based on the similarity principle for fluid dynamics is implemented. As a result, low absolute error rates are obtained in the prediction of the first samples near the shapes surfaces. Even in the most advanced time instants, the prediction of the vortices zone is quite reliable. 62.12 and 9000 speed-up ratios are achieved by the predictions of the first and second neural models, respectively, compared to the computational cost regarded by the CFD simulations.

用卷积自编码器结构预测非定常湍流流场
& lt; abstract>传统的数值方法,如计算流体动力学(CFD),需要大量的计算资源和内存来建模流体动力学系统。因此,深度学习(DL),特别是卷积神经网络(CNN)自动编码器已经产生了精确的工具,可以在考虑固定流动时获得流向和垂直速度和压力场的近似值。本文的新颖之处在于在考虑非定常流时,利用CNN自编码器结构从初始时刻预测未来时刻。提出了两种神经模型:前者基于初始样本预测未来时刻,后者近似于初始样本。cnn的输入采用有符号距离函数(SDF)和流区通道(FRC),为了表示时间演化,加入了之前的CFD样本。为了增加第二神经模型的训练数据量,采用了基于流体力学相似原理的数据增强技术。因此,在形状表面附近的第一个样本的预测中获得了较低的绝对错误率。即使在最先进的瞬间,漩涡的预测区是相当可靠的。与CFD模拟计算成本相比,第一和第二神经模型预测的加速比分别为62.12和9000。& lt; / abstract>
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
AIMS Mathematics
AIMS Mathematics Mathematics-General Mathematics
CiteScore
3.40
自引率
13.60%
发文量
769
审稿时长
90 days
期刊介绍: AIMS Mathematics is an international Open Access journal devoted to publishing peer-reviewed, high quality, original papers in all fields of mathematics. We publish the following article types: original research articles, reviews, editorials, letters, and conference reports.
×
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