Feature Extraction and Identification in Distributed Optical-Fiber Vibration Sensing System for Oil Pipeline Safety Monitoring  

作　　者：Huijuan WU Ya QIAN Wei ZHANG Chenghao TANG 

机构地区：[1]Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Scienceand Technology of China, Chengdu, 611731, China

出　　处：《Photonic Sensors》2017年第4期305-310,共6页光子传感器（英文版）

基　　金：The authors gratefully acknowledge the supports provided for this research by Youth Foundation （Grant No. 61301275）, Major Instrument Special Program （Grant No. 41527805）, the Major Program （Grant No. 61290312） of the National Science Foundation of China （NSFC）, and the fund of State Grid Corporation of China： Research on distributed multi-parameter sensing and measurement control technology for electric power optical fiber communication networks （Grant No. 5455HT160014）. This work is also supported by Program for Changjiang Scholars and Innovative Research Team in University （PCSIRT, IRT1218） and the 111 Project （B14039）.

摘　　要：High sensitivity of a distributed optical-fiber vibration sensing （DOVS） system based on the phase-sensitivity optical time domain reflectometry （Ф-OTDR） technology also brings in high nuisance alarm rates （NARs） in real applications. In this paper, feature extraction methods of wavelet decomposition （WD） and wavelet packet decomposition （WPD） are comparatively studied for three typical field testing signals, and an artificial neural network （ANN） is built for the event identification. The comparison results prove that the WPD performs a little better than the WD for the DOVS signal analysis and identification in oil pipeline safety monitoring. The identification rate can be improved up to 94.4%, and the nuisance alarm rate can be effectively controlled as low as 5.6% for the identification network with the wavelet packet energy distribution features.High sensitivity of a distributed optical-fiber vibration sensing （DOVS） system based on the phase-sensitivity optical time domain reflectometry （Ф-OTDR） technology also brings in high nuisance alarm rates （NARs） in real applications. In this paper, feature extraction methods of wavelet decomposition （WD） and wavelet packet decomposition （WPD） are comparatively studied for three typical field testing signals, and an artificial neural network （ANN） is built for the event identification. The comparison results prove that the WPD performs a little better than the WD for the DOVS signal analysis and identification in oil pipeline safety monitoring. The identification rate can be improved up to 94.4%, and the nuisance alarm rate can be effectively controlled as low as 5.6% for the identification network with the wavelet packet energy distribution features.

关 键 词：Distributed optical-fiber vibration sensing Ф-OTDR pattem recognition multi-scale analysis 

分 类 号：TP212.14[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]