A Contextual GMM-HMM Smart Fiber Optic Surveillance System for Pipeline Integrity Threat Detection

This paper presents a novel pipeline integrity surveillance system aimed to the detection and classification of threats in the vicinity of a long gas pipeline. The sensing system is based on phase-sensitive optical time domain reflectometry ($\phi$-OTDR) technology for signal acquisition and pattern recognition strategies for threat identification. The proposal incorporates contextual information at the feature level in a Gaussian Mixture Model and Hidden Markov Model (GMM-HMM) based pattern classification system and applies a system combination strategy for acoustic trace decision. System combination relies on majority voting of the decisions given by the individual contextual information sources and the number of states used for HMM modeling. The system runs in two different modes: first, machine+activity identification, which recognizes the activity being carried out by a certain machine, second, threat detection, aimed to detect threats no matter what the real activity being conducted is. In comparison with the previous systems based on the same rigorous experimental setup, the results show that the system combination from the contextual feature information and the GMM-HMM approach improves the results for both machine+activity identification (7.6% of relative improvement with respect to the best published result in the literature on this task) and threat detection (26.6% of relative improvement in the false alarm rate with 2.1% relative reduction in the threat detection rate).

[1]  Fei Jiang,et al.  An event recognition method for fiber distributed acoustic sensing systems based on the combination of MFCC and CNN , 2018, International Conference on Optical Instruments and Technology.

[2]  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.

[3]  He Zuyuan,et al.  Practical Pattern Recognition System for Distributed Optical Fiber Intrusion Monitoring Based on Ф-COTDR , 2019 .

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

[5]  Ming Bao,et al.  Pattern recognition based on enhanced multifeature parameters for vibration events in φ‐OTDR distributed optical fiber sensing system , 2017 .

[6]  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.

[7]  Dong Wang,et al.  Real-Time Distributed Vibration Monitoring System Using $\Phi$ -OTDR , 2017, IEEE Sensors Journal.

[8]  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.

[9]  Yue Yang,et al.  Distributed Vibration Sensing System for Oil and Gas Pipelines Based on COTDR and BP Neural Network , 2018 .

[10]  Geoffrey Zweig,et al.  MLP based phoneme detectors for Automatic Speech Recognition , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[12]  Dan Schonfeld,et al.  Image Segmentation and Classification Based on a 2 D Distributed Hidden Markov Model , 2008 .

[13]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[14]  Chokri Ben Amar,et al.  Facial expression recognition based on a mlp neural network using constructive training algorithm , 2014, Multimedia Tools and Applications.

[15]  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).

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

[17]  Yan Feng,et al.  Combination of Phase-Sensitive OTDR and Michelson Interferometer for Nuisance Alarm Rate Reducing and Event Identification , 2016, IEEE Photonics Journal.

[18]  G. V. Vstovsky,et al.  A class of hidden Markov models for image processing , 1993, Pattern Recognit. Lett..

[19]  Mark J. F. Gales,et al.  The Application of Hidden Markov Models in Speech Recognition , 2007, Found. Trends Signal Process..

[20]  Sonia Martin-Lopez,et al.  A Gaussian Mixture Model-Hidden Markov Model (GMM-HMM)-based fiber optic surveillance system for pipeline integrity threat detection , 2018 .

[21]  João Paulo da Silva Neto,et al.  A stream-based audio segmentation, classification and clustering pre-processing system for broadcast news using ANN models , 2005, INTERSPEECH.

[22]  Tong Zheng,et al.  A new two-dimensional method to detect harmful intrusion vibrations for optical fiber pre-warning system , 2016 .

[23]  Toygar Akgun,et al.  Deep learning based multi-threat classification for phase-OTDR fiber optic distributed acoustic sensing applications , 2017, Commercial + Scientific Sensing and Imaging.

[24]  Rupali S. Chavan,et al.  An Overview of Speech Recognition Using HMM , 2013 .

[25]  Sin-Horng Chen,et al.  A speech recognition method based on the sequential multi-layer perceptrons , 1996, Neural Networks.

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

[27]  Miloslav Filka,et al.  Distributed Fiber-Optic Sensor for Detection and Localization of Acoustic Vibrations , 2015 .

[28]  Vincent Lamour,et al.  Fiber optic sensing for monitoring structure and health of railway infrastructures , 2018 .

[29]  Kun Liu,et al.  Hybrid Feature Extraction-Based Intrusion Discrimination in Optical Fiber Perimeter Security System , 2017, IEEE Photonics Journal.

[30]  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.

[31]  Hugo F. Martins,et al.  Real Field Deployment of a Smart Fiber-Optic Surveillance System for Pipeline Integrity Threat Detection: Architectural Issues and Blind Field Test Results , 2018, Journal of Lightwave Technology.

[32]  Ujjwal Maulik,et al.  Transformation Invariant Image Recognition Using Multilayer Perceptron , 2013 .

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

[34]  Gregor Cedilnik,et al.  Advances in Train and Rail Monitoring with DAS , 2018 .

[35]  Raja Giryes,et al.  Deep Learning Approach for Processing Fiber-Optic DAS Seismic Data , 2018 .

[36]  Huijuan Wu,et al.  Feature extraction and identification in distributed optical-fiber vibration sensing system for oil pipeline safety monitoring , 2017, Photonic Sensors.

[37]  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).

[38]  Vikramjit Mitra,et al.  Content based audio classification: a neural network approach , 2008, Soft Comput..

[39]  Zhenhai Zhang,et al.  Localization and Discrimination of the Perturbation Signals in Fiber Distributed Acoustic Sensing Systems Using Spatial Average Kurtosis , 2018, Sensors.

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