解决雷诺平均纳维-斯托克斯(Navier-Stokes)解中高唤醒形成问题的神经网络模型性能改进问题

IF 1.5 4区 工程技术 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Ananthajit Ajaya Kumar, Ashwani Assam
{"title":"解决雷诺平均纳维-斯托克斯(Navier-Stokes)解中高唤醒形成问题的神经网络模型性能改进问题","authors":"Ananthajit Ajaya Kumar, Ashwani Assam","doi":"10.1108/ec-08-2023-0446","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>Deep-learning techniques are recently gaining a lot of importance in the field of turbulence. This study focuses on addressing the problem of data imbalance to improve the performance of an existing deep learning neural network to infer the Reynolds-averaged Navier–Stokes solution, proposed by Thuerey <em>et al</em>. (2020), in the cases of airfoils with high wake formation behind them. The model is based on a U-Net architecture, which calculates pressure and velocity solutions for fluid flow around an airfoil.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>In this work, we propose various methods for training the model on selectively generated data with different distributions, which would be representative of the under-performing test samples. The property we chose for selectively generating data was the fraction of negative x-velocity in the domain. We have used Grad-CAM to compare the layer activations of different models trained using the proposed methods.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>We observed that using our methods, the average performance on the samples with high wake formation (i.e. flow over airfoils at high angle of attack) has improved. Using one of the proposed methods, an average performance improvement of 15.65% was observed for samples of unknown airfoils compared to a similar model trained using the original method.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>This work demonstrates the use of imbalanced learning in the field of fluid mechanics. The performance of the model is improved by giving significance to the distribution of the training data without changes to the model architecture.</p><!--/ Abstract__block -->","PeriodicalId":50522,"journal":{"name":"Engineering Computations","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Addressing performance improvement of a neural network model for Reynolds-averaged Navier–Stokes solutions with high wake formation\",\"authors\":\"Ananthajit Ajaya Kumar, Ashwani Assam\",\"doi\":\"10.1108/ec-08-2023-0446\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3>Purpose</h3>\\n<p>Deep-learning techniques are recently gaining a lot of importance in the field of turbulence. This study focuses on addressing the problem of data imbalance to improve the performance of an existing deep learning neural network to infer the Reynolds-averaged Navier–Stokes solution, proposed by Thuerey <em>et al</em>. (2020), in the cases of airfoils with high wake formation behind them. The model is based on a U-Net architecture, which calculates pressure and velocity solutions for fluid flow around an airfoil.</p><!--/ Abstract__block -->\\n<h3>Design/methodology/approach</h3>\\n<p>In this work, we propose various methods for training the model on selectively generated data with different distributions, which would be representative of the under-performing test samples. The property we chose for selectively generating data was the fraction of negative x-velocity in the domain. We have used Grad-CAM to compare the layer activations of different models trained using the proposed methods.</p><!--/ Abstract__block -->\\n<h3>Findings</h3>\\n<p>We observed that using our methods, the average performance on the samples with high wake formation (i.e. flow over airfoils at high angle of attack) has improved. Using one of the proposed methods, an average performance improvement of 15.65% was observed for samples of unknown airfoils compared to a similar model trained using the original method.</p><!--/ Abstract__block -->\\n<h3>Originality/value</h3>\\n<p>This work demonstrates the use of imbalanced learning in the field of fluid mechanics. The performance of the model is improved by giving significance to the distribution of the training data without changes to the model architecture.</p><!--/ Abstract__block -->\",\"PeriodicalId\":50522,\"journal\":{\"name\":\"Engineering Computations\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-07-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Engineering Computations\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1108/ec-08-2023-0446\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Computations","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1108/ec-08-2023-0446","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

目的深度学习技术最近在湍流领域越来越受到重视。本研究的重点是解决数据不平衡问题,以提高现有深度学习神经网络的性能,从而推断 Thuerey 等人(2020 年)提出的雷诺平均纳维-斯托克斯解,在机翼后方形成高尾流的情况下的应用。该模型基于 U-Net 架构,可计算机翼周围流体流动的压力和速度解。在这项工作中,我们提出了多种方法,用于在选择性生成的具有不同分布的数据上训练模型,这些数据将代表性能不佳的测试样本。我们选择的选择性生成数据的属性是域中负 X 速度的分数。我们使用 Grad-CAM 比较了使用建议方法训练的不同模型的层激活情况。研究结果我们发现,使用我们的方法,在具有高尾流形成的样本上(即以高攻角流过翼面)的平均性能有所改善。与使用原始方法训练的类似模型相比,使用其中一种建议的方法,未知机翼样本的平均性能提高了 15.65%。在不改变模型结构的情况下,通过赋予训练数据分布以意义,提高了模型的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Addressing performance improvement of a neural network model for Reynolds-averaged Navier–Stokes solutions with high wake formation

Purpose

Deep-learning techniques are recently gaining a lot of importance in the field of turbulence. This study focuses on addressing the problem of data imbalance to improve the performance of an existing deep learning neural network to infer the Reynolds-averaged Navier–Stokes solution, proposed by Thuerey et al. (2020), in the cases of airfoils with high wake formation behind them. The model is based on a U-Net architecture, which calculates pressure and velocity solutions for fluid flow around an airfoil.

Design/methodology/approach

In this work, we propose various methods for training the model on selectively generated data with different distributions, which would be representative of the under-performing test samples. The property we chose for selectively generating data was the fraction of negative x-velocity in the domain. We have used Grad-CAM to compare the layer activations of different models trained using the proposed methods.

Findings

We observed that using our methods, the average performance on the samples with high wake formation (i.e. flow over airfoils at high angle of attack) has improved. Using one of the proposed methods, an average performance improvement of 15.65% was observed for samples of unknown airfoils compared to a similar model trained using the original method.

Originality/value

This work demonstrates the use of imbalanced learning in the field of fluid mechanics. The performance of the model is improved by giving significance to the distribution of the training data without changes to the model architecture.

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
Engineering Computations
Engineering Computations 工程技术-工程:综合
CiteScore
3.40
自引率
6.20%
发文量
61
审稿时长
5 months
期刊介绍: The journal presents its readers with broad coverage across all branches of engineering and science of the latest development and application of new solution algorithms, innovative numerical methods and/or solution techniques directed at the utilization of computational methods in engineering analysis, engineering design and practice. For more information visit: http://www.emeraldgrouppublishing.com/ec.htm
×
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