IMECH-IR  > 非线性力学国家重点实验室
Classifying wakes produced by self-propelled fish-like swimmers using neural networks
Li BL(李秉霖)1,2; Zhang X(张翔)1,2; Zhang X(张星)1,2
Source PublicationTheoretical and Applied Mechanics Letters
2020-03
Volume10Issue:2Pages:1-6
Abstract

We consider the classification of wake structures produced by self-propelled fish-like swimmers based on local measurements of flow variables. This problem is inspired by the extraordinary capability of animal swimmers in perceiving their hydrodynamic environments under dark condition. We train different neural networks to classify wake structures by using the streamwise velocity component, the crosswise velocity component, the vorticity and the combination of three flow variables, respectively. It is found that the neural networks trained using the two velocity components perform well in identifying the wake types, whereas the neural network trained using the vorticity suffers from a high rate of misclassification. When the neural network is trained using the combination of all three flow variables, a remarkably high accuracy in wake classification can be achieved. The results of this study can be helpful to the design of flow sensory systems in robotic underwater vehicles.

Subject Area计算流体力学
DOI10.1016/j.taml.2020.01.010
Indexed ByCSCD
Language英语
DepartmentLNM湍流
Classification二类
Ranking1
Citation statistics
Document Type期刊论文
Identifierhttp://dspace.imech.ac.cn/handle/311007/81451
Collection非线性力学国家重点实验室
Corresponding AuthorLi BL(李秉霖)
Affiliation1.中国科学院力学研究所非线性力学国家重点实验室
2.中国科学院大学工程科学学院
Recommended Citation
GB/T 7714
Li BL,Zhang X,Zhang X. Classifying wakes produced by self-propelled fish-like swimmers using neural networks[J]. Theoretical and Applied Mechanics Letters,2020,10(2):1-6.
APA Li BL,Zhang X,&Zhang X.(2020).Classifying wakes produced by self-propelled fish-like swimmers using neural networks.Theoretical and Applied Mechanics Letters,10(2),1-6.
MLA Li BL,et al."Classifying wakes produced by self-propelled fish-like swimmers using neural networks".Theoretical and Applied Mechanics Letters 10.2(2020):1-6.
Files in This Item: Download All
File Name/Size DocType Version Access License
TAML-19-137-final.pd(2661KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li BL(李秉霖)]'s Articles
[Zhang X(张翔)]'s Articles
[Zhang X(张星)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li BL(李秉霖)]'s Articles
[Zhang X(张翔)]'s Articles
[Zhang X(张星)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li BL(李秉霖)]'s Articles
[Zhang X(张翔)]'s Articles
[Zhang X(张星)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: TAML-19-137-final.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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