A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network

doi:10.1007/s10409-022-22302-x

IMECH-IR > 流固耦合系统力学重点实验室

	A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network
	Xu SF(许盛峰); Sun ZX(孙振旭); Huang RF(黄仁芳); Guo DL(郭迪龙); Yang GW(杨国伟); Ju SJ(鞠胜军)
发表期刊	ACTA MECHANICA SINICA
	2023-03
卷号	39 期号:3 页码:322302
ISSN	0567-7718
摘要	High resolution flow field reconstruction is prevalently recognized as a difficult task in the field of experimental fluid mechanics, since the measured data are usually sparse and incomplete in time and space. Specifically, due to the limitations of experimental equipment or measurement techniques, the expected data cannot be measured in some key areas. In this paper, a practical approach is proposed to reconstruct flow field with imperfect data based on the physics informed neural network (PINN), which integrates those known data with the physical principles. The wake flow past a circular cylinder is taken as the test case. Two kinds of the training set are investigated, one is the velocity data with different sparsity, and the other is the velocity data missing in different regions. To accelerate training convergence, the learning rate schedule is discussed, and the cosine annealing algorithm shows excellent performance. Results reveal that the proposed approach not only can reconstruct the true velocity field with high accuracy, but also can predict the pressure field precisely, even when the data sparsity reaches 1% or the core flow area data are truncated away. This study provides encouraging insights that the PINN can serve as a promising data assimilation method for experimental fluid mechanics.
关键词	Physics informed neural network Flow field reconstruction Particle image velocimetry Cosine annealing algorithm Experimental fluid dynamics
DOI	10.1007/s10409-022-22302-x
收录类别	SCI ; EI ; CSCD
语种	英语
WOS记录号	WOS:000931280400007
WOS研究方向	Engineering, Mechanical ; Mechanics
WOS类目	Engineering ; Mechanics
项目资助者	National Natural Science Foundation of China [52006232] ; Youth Innovation Promotion Association of Chinese Academy of Sciences [2019020]
论文分区	二类
力学所作者排名	1
RpAuthor	Sun, ZX ; Huang, RF (corresponding author), Chinese Acad Sci, Inst Mech, Key Lab Mech Fluid Solid Coupling Syst, Beijing 100190, Peoples R China.
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://dspace.imech.ac.cn/handle/311007/91831
专题	流固耦合系统力学重点实验室
作者单位	1.Chinese Acad Sci, Inst Mech, Key Lab Mech Fluid Solid Coupling Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Xu SF,Sun ZX,Huang RF,et al. A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network[J]. ACTA MECHANICA SINICA,2023,39,3,:322302.
APA	许盛峰,孙振旭,黄仁芳,郭迪龙,杨国伟,&鞠胜军.(2023).A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network.ACTA MECHANICA SINICA,39(3),322302.
MLA	许盛峰,et al."A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network".ACTA MECHANICA SINICA 39.3(2023):322302.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Jp2023A228.pdf（4793KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载