An automatic pipeline monitoring system using sound information

Chunfeng Wan, Akira Mita, Takao Kume

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

In modern cities most pipelines such as those for oil, gas, and water supply networks are buried underground. In order to prevent these lifeline infrastructures from being broken accidentally, monitoring systems are becoming indispensable. Recent reports show that most pipeline damage is caused by third-party activities. In this paper, a novel automatic pipeline monitoring system is proposed in order to prevent accidental third-party damage. In this study, potential threat to pipeline integrity is recognized by detecting the existence of road cutters, which actually prelude ground construction. Sound recognition technologies are used to identify road cutters by sound, which can easily be captured by small sensors installed along the pipelines. A pattern classification method based on the Mel frequency cepstral coefficient (MFCC) feature is used in this study to identify cutter sounds. The location of the potential threat can be well detected by knowing which sensor is sounding an alarm and relevant measures can then be expediently executed. Experiments were conducted and the resulting data were analyzed. Results showed that cutters can be effectively recognized by the MFCC distance. This pipeline monitoring system can be deployed easily along pipelines with low cost and poses no significant privacy problems to nearby residents. It can help prevent accidental pipeline breakage thus ensuring the longevity of those underground lifeline infrastructures.

Original languageEnglish
Pages (from-to)83-97
Number of pages15
JournalStructural Control and Health Monitoring
Volume17
Issue number1
DOIs
Publication statusPublished - 2010 Feb

Fingerprint

Pipelines
Acoustic waves
Monitoring
Gas supply
Sensors
Water supply
Pattern recognition
Costs
Experiments

Keywords

  • Classification
  • MEL frequency cepstral coefficient (MFCC)
  • Monitoring system
  • Pipeline
  • Third-party damage

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Mechanics of Materials

Cite this

An automatic pipeline monitoring system using sound information. / Wan, Chunfeng; Mita, Akira; Kume, Takao.

In: Structural Control and Health Monitoring, Vol. 17, No. 1, 02.2010, p. 83-97.

Research output: Contribution to journalArticle

@article{84a3d4726165458eae8bff69227b255c,
title = "An automatic pipeline monitoring system using sound information",
abstract = "In modern cities most pipelines such as those for oil, gas, and water supply networks are buried underground. In order to prevent these lifeline infrastructures from being broken accidentally, monitoring systems are becoming indispensable. Recent reports show that most pipeline damage is caused by third-party activities. In this paper, a novel automatic pipeline monitoring system is proposed in order to prevent accidental third-party damage. In this study, potential threat to pipeline integrity is recognized by detecting the existence of road cutters, which actually prelude ground construction. Sound recognition technologies are used to identify road cutters by sound, which can easily be captured by small sensors installed along the pipelines. A pattern classification method based on the Mel frequency cepstral coefficient (MFCC) feature is used in this study to identify cutter sounds. The location of the potential threat can be well detected by knowing which sensor is sounding an alarm and relevant measures can then be expediently executed. Experiments were conducted and the resulting data were analyzed. Results showed that cutters can be effectively recognized by the MFCC distance. This pipeline monitoring system can be deployed easily along pipelines with low cost and poses no significant privacy problems to nearby residents. It can help prevent accidental pipeline breakage thus ensuring the longevity of those underground lifeline infrastructures.",
keywords = "Classification, MEL frequency cepstral coefficient (MFCC), Monitoring system, Pipeline, Third-party damage",
author = "Chunfeng Wan and Akira Mita and Takao Kume",
year = "2010",
month = "2",
doi = "10.1002/stc.295",
language = "English",
volume = "17",
pages = "83--97",
journal = "Structural Control and Health Monitoring",
issn = "1545-2255",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - An automatic pipeline monitoring system using sound information

AU - Wan, Chunfeng

AU - Mita, Akira

AU - Kume, Takao

PY - 2010/2

Y1 - 2010/2

N2 - In modern cities most pipelines such as those for oil, gas, and water supply networks are buried underground. In order to prevent these lifeline infrastructures from being broken accidentally, monitoring systems are becoming indispensable. Recent reports show that most pipeline damage is caused by third-party activities. In this paper, a novel automatic pipeline monitoring system is proposed in order to prevent accidental third-party damage. In this study, potential threat to pipeline integrity is recognized by detecting the existence of road cutters, which actually prelude ground construction. Sound recognition technologies are used to identify road cutters by sound, which can easily be captured by small sensors installed along the pipelines. A pattern classification method based on the Mel frequency cepstral coefficient (MFCC) feature is used in this study to identify cutter sounds. The location of the potential threat can be well detected by knowing which sensor is sounding an alarm and relevant measures can then be expediently executed. Experiments were conducted and the resulting data were analyzed. Results showed that cutters can be effectively recognized by the MFCC distance. This pipeline monitoring system can be deployed easily along pipelines with low cost and poses no significant privacy problems to nearby residents. It can help prevent accidental pipeline breakage thus ensuring the longevity of those underground lifeline infrastructures.

AB - In modern cities most pipelines such as those for oil, gas, and water supply networks are buried underground. In order to prevent these lifeline infrastructures from being broken accidentally, monitoring systems are becoming indispensable. Recent reports show that most pipeline damage is caused by third-party activities. In this paper, a novel automatic pipeline monitoring system is proposed in order to prevent accidental third-party damage. In this study, potential threat to pipeline integrity is recognized by detecting the existence of road cutters, which actually prelude ground construction. Sound recognition technologies are used to identify road cutters by sound, which can easily be captured by small sensors installed along the pipelines. A pattern classification method based on the Mel frequency cepstral coefficient (MFCC) feature is used in this study to identify cutter sounds. The location of the potential threat can be well detected by knowing which sensor is sounding an alarm and relevant measures can then be expediently executed. Experiments were conducted and the resulting data were analyzed. Results showed that cutters can be effectively recognized by the MFCC distance. This pipeline monitoring system can be deployed easily along pipelines with low cost and poses no significant privacy problems to nearby residents. It can help prevent accidental pipeline breakage thus ensuring the longevity of those underground lifeline infrastructures.

KW - Classification

KW - MEL frequency cepstral coefficient (MFCC)

KW - Monitoring system

KW - Pipeline

KW - Third-party damage

UR - http://www.scopus.com/inward/record.url?scp=77249088677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77249088677&partnerID=8YFLogxK

U2 - 10.1002/stc.295

DO - 10.1002/stc.295

M3 - Article

AN - SCOPUS:77249088677

VL - 17

SP - 83

EP - 97

JO - Structural Control and Health Monitoring

JF - Structural Control and Health Monitoring

SN - 1545-2255

IS - 1

ER -