Location method of in-line Sagnac distributed optical fiber sensing system based on CNN regression model and time domain signals

Haiying Dong; Nian Fang

doi:10.1117/12.3048679

5 December 2024 Location method of in-line Sagnac distributed optical fiber sensing system based on CNN regression model and time domain signals

Haiying Dong, Nian Fang

Author Affiliations +

Proceedings Volume 13418, Fifteenth International Conference on Information Optics and Photonics (CIOP 2024); 1341836 (2024) https://doi.org/10.1117/12.3048679
Event: 15th International Conference on Information Optics and Photonics (CIOP2024), 2024, Xi’an, China

Abstract

Detection and location of pipeline leakage is of great significance to the safety of oil and gas pipeline transportation. A Sagnac distributed optical fiber sensing (DOFS) system is a suitable candidate in monitoring of pipeline leakage because of its strong anti-interference ability and low requirement for a light source. In order to accurately determine the leakage position, this paper proposes a location method based on a convolutional neural network (CNN) regression model and time domain input signals for an in-line Sagnac DOFS system. The sensing signals are acquired with a simulation system and a sinc signal with a bandwidth of 62 kHz is used to simulate a leakage signal. One leakage point is arranged every 100 m on the 40 km sensing fiber to get signals for training and new leakage positions are randomly selected for testing. Furthermore, Gaussian white noises with different intensities are added to the acquired signals to verify the applicability of the proposed location method for noise. The mean absolute error on the whole test set is 39.8 m, and the proportion of prediction samples with an absolute error of less than 60 m is 95.7%, and the location resolution is about 20 m. The simulation results show that the proposed method can accurately predict the leakage position within a certain range of error across the entire sensing fiber only using a single model, and has a high location resolution and good tolerance to noise.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Haiying Dong and Nian Fang "Location method of in-line Sagnac distributed optical fiber sensing system based on CNN regression model and time domain signals", Proc. SPIE 13418, Fifteenth International Conference on Information Optics and Photonics (CIOP 2024), 1341836 (5 December 2024); https://doi.org/10.1117/12.3048679

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Education and training

Sensing systems

Optical fibers

Error analysis

Signal processing

Optical sensing

Show All Keywords

Keywords/Phrases

Search In:

Publication Years