中文版 | English
Title

级联递归神经网络架构的湍流时空预测模型

Alternative Title
Spatiotemporal Prediction Model of Turbulent Flow Based on Cascaded Recurrent Neural Network
Author
Publication Years
2022
DOI
Source Title
ISSN
1006-9348
Volume39Issue:11Pages:338-343,415
Abstract
对湍流流体进行超高速成像是研究流动燃烧机理、验证湍流流动模型和化学反应动力学模型的重要手段.平面激光诱导荧光(PLIF)技术是湍流火焰燃烧中间产物高速诊断的主要实验方法,针对超高速激光的间歇性导致其时序序列之间存在间断的问题,提出使用湍流火焰中OH自由基的PLIF实验数据,通过训练级联递归神经网络模型(CascadeRNN)建立历史图像序列和未来多帧图像的映射关系,实现预测未来多帧图像的目的,从而弥补激光光源在时序序列之间的间断.结果表明,所提出的模型能够从100kHz的16帧历史图像序列的输入中预测出未来8帧图像,并且有效地捕捉火焰的空间结构特性和时间序列上的演变规律,且预测结果优于其它模型.
Keywords
URL[Source Record]
Language
Chinese
SUSTech Authorship
Others
Funding Project
52006137:国家自然科学基金 ; 19YF1423400:上海市扬帆计划 ; 2016M600313:上海市扬帆计划
Data Source
WanFang
WanFangID
jsjfz202211067
Citation statistics
Cited Times [WOS]:0
Document TypeJournal Article
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/525035
DepartmentSouthern University of Science and Technology
Affiliation
1.上海交通大学中英国际低碳学院,上海200240
2.澳大利亚阿德莱德大学能源研究中心,澳大利亚SA5005
3.南方科技大学力学与航空系,广东深圳518000
Recommended Citation
GB/T 7714
郭昊,董雪,孙志伟,等. 级联递归神经网络架构的湍流时空预测模型[J]. 计算机仿真,2022,39(11):338-343,415.
APA
郭昊,董雪,孙志伟,&周波.(2022).级联递归神经网络架构的湍流时空预测模型.计算机仿真,39(11),338-343,415.
MLA
郭昊,et al."级联递归神经网络架构的湍流时空预测模型".计算机仿真 39.11(2022):338-343,415.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[郭昊]'s Articles
[董雪]'s Articles
[孙志伟]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[郭昊]'s Articles
[董雪]'s Articles
[孙志伟]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[郭昊]'s Articles
[董雪]'s Articles
[孙志伟]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.