Brillouin optical time domain analyzer enhanced by artificial/deep neural networks

Liang Wang; Biwei Wang; Chao Jin; Nan Guo; Changyuan Yu; Chao Lu

doi:10.1109/ICOCN.2017.8121527

Brillouin optical time domain analyzer enhanced by artificial/deep neural networks

Liang Wang, Biwei Wang, Chao Jin, Nan Guo, Changyuan Yu, Chao Lu

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

3 Citations (Scopus)

Abstract

We report our recent studies on the use of Neural Networks to process the measured Brillouin gain spectrum (BGS) from Brillouin Optical Time Domain Analyzer (BOTDA) and extract temperature information along fiber under test (FUT). Artificial Neural Network (ANN) is trained with ideal Lorentizian BGS before it is used for temperature extraction. Its performance is evaluated by comparison to conventional curve fitting techniques, showing better accuracy especially at large frequency scanning step during the acquisition of BGSs. We have also applied advanced hierarchical Deep Neural Network (DNN) in BOTDA for temperature extraction to improve the training and testing efficiency. We believe that ANN/DNN can be attractive tools for direct temperature or strain extraction in BOTDA system with high accuracy.

Original language	English
Title of host publication	ICOCN 2017 - 16th International Conference on Optical Communications and Networks
Publisher	IEEE
Pages	1-3
Number of pages	3
Volume	2017-January
ISBN (Electronic)	9781538632734
DOIs	https://doi.org/10.1109/ICOCN.2017.8121527
Publication status	Published - 27 Nov 2017
Event	16th International Conference on Optical Communications and Networks, ICOCN 2017 - Wuzhen, China Duration: 7 Aug 2017 → 10 Aug 2017

Conference

Conference	16th International Conference on Optical Communications and Networks, ICOCN 2017
Country/Territory	China
City	Wuzhen
Period	7/08/17 → 10/08/17

Keywords

BOTDA
Distributed fiber sensor
Neural networks
Stimulated Brillouin scattering

ASJC Scopus subject areas

Computer Networks and Communications
Instrumentation
Atomic and Molecular Physics, and Optics

More information

10.1109/ICOCN.2017.8121527

http://hdl.handle.net/10397/107215

Cite this

@inproceedings{fe655073ffba48ff9afb20ab2281e417,

title = "Brillouin optical time domain analyzer enhanced by artificial/deep neural networks",

abstract = "We report our recent studies on the use of Neural Networks to process the measured Brillouin gain spectrum (BGS) from Brillouin Optical Time Domain Analyzer (BOTDA) and extract temperature information along fiber under test (FUT). Artificial Neural Network (ANN) is trained with ideal Lorentizian BGS before it is used for temperature extraction. Its performance is evaluated by comparison to conventional curve fitting techniques, showing better accuracy especially at large frequency scanning step during the acquisition of BGSs. We have also applied advanced hierarchical Deep Neural Network (DNN) in BOTDA for temperature extraction to improve the training and testing efficiency. We believe that ANN/DNN can be attractive tools for direct temperature or strain extraction in BOTDA system with high accuracy.",

keywords = "BOTDA, Distributed fiber sensor, Neural networks, Stimulated Brillouin scattering",

author = "Liang Wang and Biwei Wang and Chao Jin and Nan Guo and Changyuan Yu and Chao Lu",

year = "2017",

month = nov,

day = "27",

doi = "10.1109/ICOCN.2017.8121527",

language = "English",

volume = "2017-January",

pages = "1--3",

booktitle = "ICOCN 2017 - 16th International Conference on Optical Communications and Networks",

publisher = "IEEE",

address = "United States",

note = "16th International Conference on Optical Communications and Networks, ICOCN 2017 ; Conference date: 07-08-2017 Through 10-08-2017",

}

Wang, L, Wang, B, Jin, C, Guo, N, Yu, C & Lu, C 2017, Brillouin optical time domain analyzer enhanced by artificial/deep neural networks. in ICOCN 2017 - 16th International Conference on Optical Communications and Networks. vol. 2017-January, IEEE, pp. 1-3, 16th International Conference on Optical Communications and Networks, ICOCN 2017, Wuzhen, China, 7/08/17. https://doi.org/10.1109/ICOCN.2017.8121527

Brillouin optical time domain analyzer enhanced by artificial/deep neural networks. / Wang, Liang; Wang, Biwei; Jin, Chao et al.
ICOCN 2017 - 16th International Conference on Optical Communications and Networks. Vol. 2017-January IEEE, 2017. p. 1-3.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Brillouin optical time domain analyzer enhanced by artificial/deep neural networks

AU - Wang, Liang

AU - Wang, Biwei

AU - Jin, Chao

AU - Guo, Nan

AU - Yu, Changyuan

AU - Lu, Chao

PY - 2017/11/27

Y1 - 2017/11/27

N2 - We report our recent studies on the use of Neural Networks to process the measured Brillouin gain spectrum (BGS) from Brillouin Optical Time Domain Analyzer (BOTDA) and extract temperature information along fiber under test (FUT). Artificial Neural Network (ANN) is trained with ideal Lorentizian BGS before it is used for temperature extraction. Its performance is evaluated by comparison to conventional curve fitting techniques, showing better accuracy especially at large frequency scanning step during the acquisition of BGSs. We have also applied advanced hierarchical Deep Neural Network (DNN) in BOTDA for temperature extraction to improve the training and testing efficiency. We believe that ANN/DNN can be attractive tools for direct temperature or strain extraction in BOTDA system with high accuracy.

AB - We report our recent studies on the use of Neural Networks to process the measured Brillouin gain spectrum (BGS) from Brillouin Optical Time Domain Analyzer (BOTDA) and extract temperature information along fiber under test (FUT). Artificial Neural Network (ANN) is trained with ideal Lorentizian BGS before it is used for temperature extraction. Its performance is evaluated by comparison to conventional curve fitting techniques, showing better accuracy especially at large frequency scanning step during the acquisition of BGSs. We have also applied advanced hierarchical Deep Neural Network (DNN) in BOTDA for temperature extraction to improve the training and testing efficiency. We believe that ANN/DNN can be attractive tools for direct temperature or strain extraction in BOTDA system with high accuracy.

KW - BOTDA

KW - Distributed fiber sensor

KW - Neural networks

KW - Stimulated Brillouin scattering

UR - http://www.scopus.com/inward/record.url?scp=85043480534&partnerID=8YFLogxK

U2 - 10.1109/ICOCN.2017.8121527

DO - 10.1109/ICOCN.2017.8121527

M3 - Conference article published in proceeding or book

VL - 2017-January

SP - 1

EP - 3

BT - ICOCN 2017 - 16th International Conference on Optical Communications and Networks

PB - IEEE

T2 - 16th International Conference on Optical Communications and Networks, ICOCN 2017

Y2 - 7 August 2017 through 10 August 2017

ER -

Brillouin optical time domain analyzer enhanced by artificial/deep neural networks

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this