RT info:eu-repo/semantics/article
T1 Real Field Deployment of a Smart Fiber Optic Surveillance System for Pipeline Integrity Threat Detection: Architectural Issues and Blind Field Test Results
A1 Tejedor Noguerales, Javier
A1 Macías Guarasa, Javier
A1 Fidalgo Martins, Hugo
A1 Pastor Graells, Juan
A1 Martín López, Sonia
A1 Corredera, Pedro
A1 De Pauw, G.
A1 De Smet, F.
A1 Postvoll, W.
A1 Ahlen, C.H.
A1 González Herráez, Miguel
K1 Distributed fiber sensing
K1 Acoustic sensing
K1 Vibration sensing
K1 Pipeline integrity
K1 phase-sensitive OTDR
K1 Pattern recognition
K1 Electrónica
K1 Electronics
AB This paper presents an on-line augmented surveillancesystem that aims to real time monitoring of activitiesalong a pipeline. The system is deployed in a fully realisticscenario and exposed to real activities carried out in unknownplaces at unknown times within a given test time interval (socalledblind field tests). We describe the system architecture thatincludes specific modules to deal with the fact that continuouson-line monitoring needs to be carried out, while addressingthe need of limiting the false alarms at reasonable rates. Tothe best or our knowledge, this is the first published work inwhich a pipeline integrity threat detection system is deployedin a realistic scenario (using a fiber optic along an active gaspipeline) and is thoroughly and objectively evaluated in realisticblind conditions. The system integrates two operation modes:The machine+activity identification mode identifies the machinethat is carrying out a certain activity along the pipeline, and thethreat detection mode directly identifies if the activity along thepipeline is a threat or not. The blind field tests are carried outin two different pipeline sections: The first section correspondsto the case where the sensor is close to the sensed area, whilethe second one places the sensed area about 35 km far fromthe sensor. Results of the machine+activity identification modeshowed an average machine+activity classification rate of 46:6%.For the threat detection mode, 8 out of 10 threats were correctlydetected, with only 1 false alarm appearing in a 55:5-hour sensedperiod.
PB IEEE
SN 0733-8724
YR 2018
FD 2018
LK http://hdl.handle.net/10017/33080
UL http://hdl.handle.net/10017/33080
LA eng
NO European Commission
DS MINDS@UW
RD 24-mar-2023