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

Tejedor, Javier; Macías-Guarasa, Javier; Martins, Hugo F.; Pastor-Graells, Juan; Corredera, Pedro; Martín‐López, Sonia

doi:10.3390/app7080841

Cited by 97 publications

(53 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Post-processing and interpretation of the measured DAS data to provide reliable and comprehensible pipeline status report to the operators constitutes a crucial part of DAS-based pipeline monitoring systems. These tasks typically rely on various pattern recognition and machine learning methods which have been the subject of intense research over the last years [ 43 ]. This paper focuses on investigation of the physical capability of DAS to detect weak leak-induced pipeline vibrations.…”

Section: Resultsmentioning

confidence: 99%

Detection of Leak-Induced Pipeline Vibrations Using Fiber—Optic Distributed Acoustic Sensing

Stajanča

Chruscicki

Homann

et al. 2018

Sensors

140

View full text Add to dashboard Cite

In the presented work, the potential of fiber-optic distributed acoustic sensing (DAS) for detection of small gas pipeline leaks (<1%) is investigated. Helical wrapping of the sensing fiber directly around the pipeline is used to increase the system sensitivity for detection of weak leak-induced vibrations. DAS measurements are supplemented with reference accelerometer data to facilitate analysis and interpretation of recorded vibration signals. The results reveal that a DAS system using direct fiber application approach is capable of detecting pipeline natural vibrations excited by the broadband noise generated by the leaking medium. In the performed experiment, pipeline vibration modes with acceleration magnitudes down to single μg were detected. Simple leak detection approach based on spectral integration of time-averaged DAS signals in frequency domain was proposed. Potential benefits and limitations of the presented monitoring approach were discussed with respect to its practical applicability. We demonstrated that the approached is potentially capable of detection and localization of gas pipeline leaks with leak rates down to 0.1% of the pipeline flow volume and might be of interest for monitoring of short- and medium-length gas pipelines.

show abstract

Section: Resultsmentioning

confidence: 99%

Detection of Leak-Induced Pipeline Vibrations Using Fiber—Optic Distributed Acoustic Sensing

Stajanča

Chruscicki

Homann

et al. 2018

Sensors

140

View full text Add to dashboard Cite

show abstract

“…It is possible to monitor the sliding of the rock mass by embedding the borehole or backfilling cement mortar into the rock mass. Tejedor, J. et al [9] proposed a machine learning method for pipeline monitoring system based on distributed acoustic sensing. Before sliding, the loss curve detected by OTDR is basically flat.…”

Section: State Of the Artmentioning

confidence: 99%

Distributed Fiber Optical Technology for Damage Identification of Engineering Structure

Dong¹,

Zhou²

2018

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Abstract-To conduct optical fiber monitoring rock slide model test and optical fiber monitoring of steel concrete interface slip model test, the large triaxial shear test of geotechnical engineering was used. First, the data of sliding distance and optical loss and their dynamic range were obtained. Second, the slide distance and fiber loss relation curve and the fitting equation were worked out. Finally, the typical applications of optical fiber sensing technology in Rock Engineering (high slope engineering, rock foundation of Dam Engineering) slope stability and geological disaster monitoring were put forward. The results showed that optical fiber sensing was very sensitive, and the loss value was 30 to 50dB. The dynamic range of rock slide monitoring fiber was 3 to 3.5mm, and the dynamic range of the interface slip monitoring fiber was 1.6mm. Thus, the sensing system can detect the sliding process of the interface between the concrete and the steel plate. It provides some reference for the sliding monitoring of the composite materials.

show abstract

“…For instance, considering 20,000 traces in [4,16,18] means an overall delay of 20sec other than processing delay stage if a 100km fiber is used under test. Due to huge data manipulation in real time in φ-OTDR systems, the use of feature extractors like Short-Time Fourier Transform (STFT) and Level Crossing (LC) were quite common due to their ease of simplicity [19] even after the introduction of complex feature extractors like EMD [16] or morphologic [17] based extractors. According to the latest review [19], the simple feature extractors like LC and STFT have been used about 82% of the time of all the feature extractors used.…”

Section: Introductionmentioning

confidence: 99%

“…Due to huge data manipulation in real time in φ-OTDR systems, the use of feature extractors like Short-Time Fourier Transform (STFT) and Level Crossing (LC) were quite common due to their ease of simplicity [19] even after the introduction of complex feature extractors like EMD [16] or morphologic [17] based extractors. According to the latest review [19], the simple feature extractors like LC and STFT have been used about 82% of the time of all the feature extractors used. Unfortunately, almost a high percentage of all these feature extractors are based upon differential signals.…”

Section: Introductionmentioning

confidence: 99%

“…Improvement of parameter estimation as an application example has been explained in this paper. The additional advantages of using the proposed feature extractor include a more probable possibility of improving pattern recognition in the active region only, the use of a direct detected φ-OTDR system on the account of widely installed similar systems and a possibility of use of contemporary algorithms based on these systems [2,[15][16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nuisance alarm reduction: Using a correlation based algorithm above differential signals in direct detected phase-OTDR systems

Adeel¹,

Chen²,

Zhu³

et al. 2019

Opt. Express

View full text Add to dashboard Cite

Significant research efforts have focused on techniques for alleviating the nuisance alarm rate (NAR) in the field of φ-OTDR pattern recognition systems. Unfortunately, ephemeral events were mostly neglected in previous research, and algorithms meant for improving classification accuracy were emphasized at the cost of acquiring a very large number of traces. This problem engendered an additional source of NAR in a specific class of events. The proposed solution uses a novel correlation based wrapper on top of differential signals that aims to filter out the effect of unnecessary phases in direct detected φ-OTDR systems. This technique avoids the use of irrelevant data in these differential signals by exploiting a better use of these unnecessary phases and provides a better intensity translation with fewer acquired traces as compared with contemporary techniques of extracting features.

show abstract

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

Cited by 97 publications

References 64 publications

Detection of Leak-Induced Pipeline Vibrations Using Fiber—Optic Distributed Acoustic Sensing

Detection of Leak-Induced Pipeline Vibrations Using Fiber—Optic Distributed Acoustic Sensing

Distributed Fiber Optical Technology for Damage Identification of Engineering Structure

Nuisance alarm reduction: Using a correlation based algorithm above differential signals in direct detected phase-OTDR systems

Contact Info

Product

Resources

About