Machine Learning Methods for Pipeline Surveillance Systems Based on Distributed Acoustic Sensing: A Review

There is an increasing interest in researchers and companies on the combination of Distributed Acoustic Sensing (DAS) and a Pattern Recognition System (PRS) to detect and classify potentially dangerous events that occur in areas above fiber optic cables deployed along active pipelines, aiming to construct pipeline surveillance systems. This paper presents a review of the literature in what respect to machine learning techniques applied to pipeline surveillance systems based on DAS+PRS (although its scope can also be extended to any other environment in which DAS+PRS strategies are to be used). To do so, we describe the fundamentals of the machine learning approaches when applied to DAS systems, and also do a detailed literature review of the main contributions on this topic. Additionally, this paper addresses the most common issues related to real field deployment and evaluation of DAS+PRS for pipeline threat monitoring, and intends to provide useful insights and recommendations in what respect to the design of such systems. The literature review concludes that a real field deployment of a PRS based on DAS technology is still a challenging area of research, far from being fully solved.

[1]  Elfed Lewis,et al.  An optical fibre distributed sensor based on pattern recognition , 2002 .

[2]  Jiwei Xu,et al.  Separation and Determination of the Disturbing Signals in Phase-Sensitive Optical Time Domain Reflectometry (Φ-OTDR) , 2015, Journal of Lightwave Technology.

[3]  Xiaoyi Bao,et al.  Wavelet Denoising Method for Improving Detection Performance of Distributed Vibration Sensor , 2012, IEEE Photonics Technology Letters.

[4]  Jingchang Huang,et al.  Seismic Target Classification Using a Wavelet Packet Manifold in Unattended Ground Sensors Systems , 2013, Sensors.

[5]  D. Hill,et al.  Distributed Acoustic Sensing (DAS): Theory and Applications , 2015 .

[6]  Z. N. Wang,et al.  Ultra-long phase-sensitive OTDR with hybrid distributed amplification. , 2014, Optics letters.

[7]  Hao Xiao,et al.  Ground target detection, classification, and sensor fusion in distributed fiber seismic sensor network , 2008, SPIE/COS Photonics Asia.

[8]  Youngsoo Kim,et al.  A GMM-Based Target Classification Scheme for a Node in Wireless Sensor Networks , 2008, IEICE Trans. Commun..

[9]  Christopher M. Kreucher,et al.  LANA: a lane extraction algorithm that uses frequency domain features , 1999, IEEE Trans. Robotics Autom..

[10]  S. Martin-Lopez,et al.  Early detection of pipeline integrity threats using a smart fiber optic surveillance system: the PIT-STOP project , 2015, International Conference on Optical Fibre Sensors.

[11]  Henry F. Taylor,et al.  Distributed fiber optic pressure/seismic sensor for low-cost monitoring of long perimeters , 2003, SPIE Defense + Commercial Sensing.

[12]  Y. Rao,et al.  Coherent Φ-OTDR based on I/Q demodulation and homodyne detection. , 2016, Optics express.

[13]  O. Frazão,et al.  Phase-sensitive Optical Time Domain Reflectometer Assisted by First-order Raman Amplification for Distributed Vibration Sensing Over >100 km , 2014, Journal of Lightwave Technology.

[14]  Xiaoyi Bao,et al.  Continuous wavelet transform for non-stationary vibration detection with phase-OTDR. , 2012, Optics express.

[15]  Jinghua Li,et al.  Battlefield Target Identification Based on Improved Grid-Search SVM Classifier , 2009, 2009 International Conference on Computational Intelligence and Software Engineering.

[16]  Heinrich Garn,et al.  A real-time algorithm for train position monitoring using optical time-domain reflectometry , 2016, 2016 IEEE International Conference on Intelligent Rail Transportation (ICIRT).

[17]  Pge Paul Lumens.  Fibre-optic sensing for application in oil and gas wells , 2014 .

[18]  A. P. Dawid,et al.  Generative or Discriminative? Getting the Best of Both Worlds , 2007 .

[19]  Elfed Lewis,et al.  A multi-point optical fibre sensor for condition monitoring in process water systems based on pattern recognition , 2003 .

[20]  Fei Peng,et al.  Ultra-long high-sensitivity Φ-OTDR for high spatial resolution intrusion detection of pipelines. , 2014, Optics express.

[21]  C. Kirkendall.  Distributed Acoustic and Seismic Sensing , 2007, OFC/NFOEC 2007 - 2007 Conference on Optical Fiber Communication and the National Fiber Optic Engineers Conference.

[22]  J. Juarez,et al.  Distributed fiber-optic intrusion sensor system , 2005, Journal of Lightwave Technology.

[23]  Gaurav Verma,et al.  Classification of ground vehicles using acoustic signal processing and neural network classifier , 2013, 2013 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATION (ICSC).

[24]  S. Martin-Lopez,et al.  Towards detection of pipeline integrity threats using a SmarT fiber-OPtic surveillance system: PIT-STOP project blind field test results , 2017, 2017 25th Optical Fiber Sensors Conference (OFS).

[25]  Hao Feng,et al.  A Long Distance Phase-Sensitive Optical Time Domain Reflectometer with Simple Structure and High Locating Accuracy , 2015, Sensors.

[26]  Fei Peng,et al.  124km phase-sensitive OTDR with Brillouin amplification , 2014, Other Conferences.

[27]  J. Buerck,et al.  OTDR fiber-optical chemical sensor system for detection and location of hydrocarbon leakage. , 2003, Journal of hazardous materials.

[28]  Andreas Stolcke,et al.  On using MLP features in LVCSR , 2004, INTERSPEECH.

[29]  Parameswaran Ramanathan,et al.  Distributed target classification and tracking in sensor networks , 2003 .

[30]  Zoran Miljkovic,et al.  A review of automated feature recognition with rule-based pattern recognition , 2008, Comput. Ind..

[31]  Xiaohan Sun,et al.  Distributed optical-fiber vibration sensing system based on differential detection of differential coherent-OTDR , 2012, 2012 IEEE Sensors.

[32]  Tao Zhu,et al.  Enhancement of SNR and Spatial Resolution in $\varphi$-OTDR System by Using Two-Dimensional Edge Detection Method , 2013, Journal of Lightwave Technology.

[33]  Hugo F. Martins,et al.  Toward Prevention of Pipeline Integrity Threats Using a Smart Fiber-Optic Surveillance System , 2016, Journal of Lightwave Technology.

[34]  Massimo L. Filograno,et al.  Coherent Noise Reduction in High Visibility Phase-Sensitive Optical Time Domain Reflectometer for Distributed Sensing of Ultrasonic Waves , 2013, Journal of Lightwave Technology.

[35]  Shrikanth Narayanan,et al.  Collaborative classification applications in sensor networks , 2002, Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2002.

[36]  Gangbing Song,et al.  Recent applications of fiber optic sensors to health monitoring in civil engineering , 2004 .

[37]  Yu Hen Hu,et al.  Detection, classification, and tracking of targets , 2002, IEEE Signal Process. Mag..

[38]  Javier Macías Guarasa,et al.  A Novel Fiber Optic Based Surveillance System for Prevention of Pipeline Integrity Threats , 2017, Sensors.

[39]  Elfed Lewis,et al.  Interrogation of multipoint optical fibre sensor signals based on artificial neural network pattern recognition techniques , 2004 .

[40]  Qian Sun,et al.  Recognition of a Phase-Sensitivity OTDR Sensing System Based on Morphologic Feature Extraction , 2015, Sensors.

[41]  Xiao-xuan Qi,et al.  An Approach of Passive Vehicle Type Recognition by Acoustic Signal Based on SVM , 2009, 2009 Third International Conference on Genetic and Evolutionary Computing.

[42]  J. Pastor-Graells,et al.  Single-shot distributed temperature and strain tracking using direct detection phase-sensitive OTDR with chirped pulses. , 2016, Optics express.

[43]  Li Zhang,et al.  175km phase-sensitive OTDR with hybrid distributed amplification , 2014, Other Conferences.

[44]  Tang Tian Guo,et al.  Experimental research on distributed fiber sensor for sliding damage monitoring , 2009 .

[45]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[46]  Hao Feng,et al.  A SVM-based pipeline leakage detection and pre-warning system , 2010 .

[47]  Hong Huo,et al.  An Improvement on Discrete Wavelet Transform-based Algorithm for Vehicle Classification in Wireless Sensor Networks , 2006, 2006 1ST IEEE Conference on Industrial Electronics and Applications.

[48]  S J Savory,et al.  Real time dynamic strain monitoring of optical links using the backreflection of live PSK data. , 2016, Optics express.

[49]  Xiao-xuan Qi,et al.  An Approach of Automatic Vehicle Classification by Acoustic Wave Based on PCA-RBF , 2009, 2009 International Conference on Information Engineering and Computer Science.

[50]  Elfed Lewis,et al.  Principal component analysis and artificial neural network based approach to analysing optical fibre sensors signals , 2007 .

[51]  Victoria Stodden,et al.  Implementing Reproducible Research , 2018 .

[52]  Leena Mary,et al.  Vehicle detection and classification from acoustic signal using ANN and KNN , 2013, 2013 International Conference on Control Communication and Computing (ICCC).

[53]  Z. N. Wang,et al.  Phase-sensitive optical time-domain reflectometry with Brillouin amplification. , 2014, Optics letters.

[54]  Chris.  An introduction to fibre optic Intelligent Distributed Acoustic Sensing (iDAS) technology for power industry applications , 2015 .

[55]  Pedro Corredera,et al.  Distributed Vibration Sensing Over 125 km With Enhanced SNR Using Phi-OTDR Over a URFL Cavity , 2015, Journal of Lightwave Technology.

[56]  F. Hlawatsch,et al.  Linear and quadratic time-frequency signal representations , 1992, IEEE Signal Processing Magazine.

[57]  Zhi Zhou,et al.  Long-distance fiber-optic Φ-OTDR intrusion sensing system , 2009, International Conference on Optical Fibre Sensors.

[58]  Elfed Lewis,et al.  A multipoint optical fibre sensor system for use in process water systems based on artificial neural network pattern recognition techniques , 2004 .

[59]  Juan C Juarez,et al.  Field test of a distributed fiber-optic intrusion sensor system for long perimeters. , 2007, Applied optics.

[60]  Xiaohan Sun,et al.  Vibration pattern recognition and classification in OTDR based distributed optical-fiber vibration sensing system , 2014, Smart Structures.

[61]  Qing Ye,et al.  High sampling rate multi-pulse phase-sensitive OTDR employing frequency division multiplexing , 2014, Other Conferences.

[62]  B. Samanta,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES , 2003 .

[63]  Garry M. Jacyna,et al.  Vehicle acoustic classification in netted sensor systems using Gaussian mixture models , 2005, SPIE Defense + Commercial Sensing.

[64]  Hairong Qi,et al.  Collaborative multi-modality target classification in distributed sensor networks , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[65]  Michael I. Jordan,et al.  On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes , 2001, NIPS.

[66]  Akbar M. Sayeed,et al.  Detection, Classification and Tracking of Targets in Distributed Sensor Networks , 2002 .

[67]  Juan C Juarez,et al.  Polarization discrimination in a phase-sensitive optical time-domain reflectometer intrusion-sensor system. , 2005, Optics letters.

[68]  Yunjiang Rao,et al.  A novel intrusion signal processing method for phase-sensitive optical time-domain reflectometry (Φ-OTDR) , 2014, Other Conferences.

[69]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[70]  Zuyuan He,et al.  Practical Pattern Recognition System for Distributed Optical Fiber Intrusion Monitoring System Based on Phase-Sensitive Coherent OTDR , 2015 .

[71]  Fei Peng,et al.  Field test of a fully distributed fiber optic intrusion detection system for long-distance security monitoring of national borderline , 2014, Other Conferences.

[72]  Christi K. Madsen,et al.  Intruder signature analysis from a phase-sensitive distributed fiber-optic perimeter sensor , 2007, SPIE Optics East.