Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer

Zhanfeng Zhao; Duo Liu; Longwei Wang; Shujun Liu

doi:10.1007/978-3-030-19153-5_65

Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer

Zhanfeng Zhao
, Duo Liu^*
, Longwei Wang
, Shujun Liu

^*Corresponding author for this work

Harbin Institute of Technology Weihai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Since fiber distributed vibration sensing (DVS) system based on phase-sensitive optical time domain reflectometer (Φ-OTDR) has the characteristics of identifying intrusion signals, wide monitoring range and high system sensitivity, correct identification of intrusion types by the system is an important issue to promote the engineering of this technology. In this paper, based on the intrusion signal of Φ-OTDR system, a multi-dimensional feature extraction and selection method is proposed. The polynomial least squares method is used to remove the trend term from the vibration signal, and the wavelet threshold denoising method is used to reduce the noise interference. The short-time analysis in the time domain and the wavelet analysis in the wavelet domain are combined to extract the multi-dimensional characteristics of the signal. The feature selection is based on the QUICKREDUCT algorithm. The experimental results show that the feature vector obtained by this method is relatively complete, and it is less affected by the environment, and the recognition rate is higher, reaching over 92%.

Original language	English
Title of host publication	Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings
Editors	Min Jia, Qing Guo, Weixiao Meng
Publisher	Springer Verlag
Pages	665-675
Number of pages	11
ISBN (Print)	9783030191528
DOIs	https://doi.org/10.1007/978-3-030-19153-5_65
State	Published - 2019
Externally published	Yes
Event	10th EAI International Conference on Wireless and Satellite Systems, WiSATS 2019 - Harbin, China Duration: 12 Jan 2019 → 13 Jan 2019

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	280
ISSN (Print)	1867-8211

Conference

Conference	10th EAI International Conference on Wireless and Satellite Systems, WiSATS 2019
Country/Territory	China
City	Harbin
Period	12/01/19 → 13/01/19

Keywords

Feature extraction
Identification
Short-term analysis
Wavelet analysis
Φ-OTDR

Access to Document

10.1007/978-3-030-19153-5_65

Cite this

Zhao, Z., Liu, D., Wang, L., & Liu, S. (2019). Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer. In M. Jia, Q. Guo, & W. Meng (Eds.), Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings (pp. 665-675). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 280). Springer Verlag. https://doi.org/10.1007/978-3-030-19153-5_65

Zhao, Zhanfeng ; Liu, Duo ; Wang, Longwei et al. / Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer. Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings. editor / Min Jia ; Qing Guo ; Weixiao Meng. Springer Verlag, 2019. pp. 665-675 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{5dc4ff7aa9f0431fb5e48fc441aa0465,

title = "Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer",

abstract = "Since fiber distributed vibration sensing (DVS) system based on phase-sensitive optical time domain reflectometer (Φ-OTDR) has the characteristics of identifying intrusion signals, wide monitoring range and high system sensitivity, correct identification of intrusion types by the system is an important issue to promote the engineering of this technology. In this paper, based on the intrusion signal of Φ-OTDR system, a multi-dimensional feature extraction and selection method is proposed. The polynomial least squares method is used to remove the trend term from the vibration signal, and the wavelet threshold denoising method is used to reduce the noise interference. The short-time analysis in the time domain and the wavelet analysis in the wavelet domain are combined to extract the multi-dimensional characteristics of the signal. The feature selection is based on the QUICKREDUCT algorithm. The experimental results show that the feature vector obtained by this method is relatively complete, and it is less affected by the environment, and the recognition rate is higher, reaching over 92\%.",

keywords = "Feature extraction, Identification, Short-term analysis, Wavelet analysis, Φ-OTDR",

author = "Zhanfeng Zhao and Duo Liu and Longwei Wang and Shujun Liu",

note = "Publisher Copyright: {\textcopyright} 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.; 10th EAI International Conference on Wireless and Satellite Systems, WiSATS 2019 ; Conference date: 12-01-2019 Through 13-01-2019",

year = "2019",

doi = "10.1007/978-3-030-19153-5\_65",

language = "英语",

isbn = "9783030191528",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Verlag",

pages = "665--675",

editor = "Min Jia and Qing Guo and Weixiao Meng",

booktitle = "Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings",

address = "德国",

}

Zhao, Z, Liu, D, Wang, L & Liu, S 2019, Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer. in M Jia, Q Guo & W Meng (eds), Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 280, Springer Verlag, pp. 665-675, 10th EAI International Conference on Wireless and Satellite Systems, WiSATS 2019, Harbin, China, 12/01/19. https://doi.org/10.1007/978-3-030-19153-5_65

Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer. / Zhao, Zhanfeng; Liu, Duo; Wang, Longwei et al.
Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings. ed. / Min Jia; Qing Guo; Weixiao Meng. Springer Verlag, 2019. p. 665-675 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 280).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer

AU - Zhao, Zhanfeng

AU - Liu, Duo

AU - Wang, Longwei

AU - Liu, Shujun

PY - 2019

Y1 - 2019

N2 - Since fiber distributed vibration sensing (DVS) system based on phase-sensitive optical time domain reflectometer (Φ-OTDR) has the characteristics of identifying intrusion signals, wide monitoring range and high system sensitivity, correct identification of intrusion types by the system is an important issue to promote the engineering of this technology. In this paper, based on the intrusion signal of Φ-OTDR system, a multi-dimensional feature extraction and selection method is proposed. The polynomial least squares method is used to remove the trend term from the vibration signal, and the wavelet threshold denoising method is used to reduce the noise interference. The short-time analysis in the time domain and the wavelet analysis in the wavelet domain are combined to extract the multi-dimensional characteristics of the signal. The feature selection is based on the QUICKREDUCT algorithm. The experimental results show that the feature vector obtained by this method is relatively complete, and it is less affected by the environment, and the recognition rate is higher, reaching over 92%.

AB - Since fiber distributed vibration sensing (DVS) system based on phase-sensitive optical time domain reflectometer (Φ-OTDR) has the characteristics of identifying intrusion signals, wide monitoring range and high system sensitivity, correct identification of intrusion types by the system is an important issue to promote the engineering of this technology. In this paper, based on the intrusion signal of Φ-OTDR system, a multi-dimensional feature extraction and selection method is proposed. The polynomial least squares method is used to remove the trend term from the vibration signal, and the wavelet threshold denoising method is used to reduce the noise interference. The short-time analysis in the time domain and the wavelet analysis in the wavelet domain are combined to extract the multi-dimensional characteristics of the signal. The feature selection is based on the QUICKREDUCT algorithm. The experimental results show that the feature vector obtained by this method is relatively complete, and it is less affected by the environment, and the recognition rate is higher, reaching over 92%.

KW - Feature extraction

KW - Identification

KW - Short-term analysis

KW - Wavelet analysis

KW - Φ-OTDR

UR - https://www.scopus.com/pages/publications/85065908239

U2 - 10.1007/978-3-030-19153-5_65

DO - 10.1007/978-3-030-19153-5_65

M3 - 会议稿件

AN - SCOPUS:85065908239

SN - 9783030191528

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 665

EP - 675

BT - Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings

A2 - Jia, Min

A2 - Guo, Qing

A2 - Meng, Weixiao

PB - Springer Verlag

T2 - 10th EAI International Conference on Wireless and Satellite Systems, WiSATS 2019

Y2 - 12 January 2019 through 13 January 2019

ER -

Zhao Z, Liu D, Wang L, Liu S. Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer. In Jia M, Guo Q, Meng W, editors, Wireless and Satellite Systems - 10th EAI International Conference, WiSATS 2019, Proceedings. Springer Verlag. 2019. p. 665-675. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-030-19153-5_65

Feature Extraction and Identification of Pipeline Intrusion Based on Phase-Sensitive Optical Time Domain Reflectometer

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this