Leak detection using the pattern of sound signals in water supply systems

Toshitaka Sato, Akira Mita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Water supply systems in Japan contribute significantly to improve public health. Unfortunately, there are many age-deteriorated pipes of various sizes and leaks frequently occur. Particularly devastating are hidden leaks occurring underground because when left undetected for years these leaks result in secondary damage. Thus, early detection and treatment of leaks is an important civil engineering challenge. At present the acoustic method is the most popular leak detection method. The purpose of this study is to propose an easy and stable leak detection method using the acoustic method assisted by pattern recognition techniques. In the proposed method we collect in the form of digital signals sound and pseudo-sound samples of underground leaking pipes. Principal component analysis (PCA) of the power spectrum of one leak sound is made, and a new coordinate system is constructed. We project the other sounds in the coordinate system, and evaluate if the sounds are similar to the sample sound or not by comparing the residual between the original and the projection. Next, we evaluate the DSF (Damage Sensitive Feature), which is a function of the first three AR model. At last, the feature vectors are created by combining the residuals, the DSF, and the damping ratio of the AR model, and a leak detection method is proposed using the Support Vector Machine (SVM) based upon them. In this study, it is shown that the residual and DSF are useful indices for leak detection. Furthermore, the proposed method shows high accuracy in recognizing leaks.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6529 PART 2
DOIs
Publication statusPublished - 2007
EventSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2007 - San Diego, CA, United States
Duration: 2007 Mar 192007 Mar 22

Other

OtherSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2007
CountryUnited States
CitySan Diego, CA
Period07/3/1907/3/22

Fingerprint

Water supply systems
Leak detection
Acoustic waves
acoustics
water
damage
Acoustics
Pipe
Public health
Civil engineering
Power spectrum
public health
Principal component analysis
Pattern recognition
Support vector machines
principal components analysis
Damping
pattern recognition
power spectra
Japan

Keywords

  • Damage sensitive feature
  • Leak detection
  • Principal component analysis
  • Support vector machine

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Sato, T., & Mita, A. (2007). Leak detection using the pattern of sound signals in water supply systems. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6529 PART 2). [65292K] https://doi.org/10.1117/12.715486

Leak detection using the pattern of sound signals in water supply systems. / Sato, Toshitaka; Mita, Akira.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6529 PART 2 2007. 65292K.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sato, T & Mita, A 2007, Leak detection using the pattern of sound signals in water supply systems. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6529 PART 2, 65292K, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2007, San Diego, CA, United States, 07/3/19. https://doi.org/10.1117/12.715486
Sato T, Mita A. Leak detection using the pattern of sound signals in water supply systems. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6529 PART 2. 2007. 65292K https://doi.org/10.1117/12.715486
Sato, Toshitaka ; Mita, Akira. / Leak detection using the pattern of sound signals in water supply systems. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6529 PART 2 2007.
@inproceedings{a67749694a8e4fd882d0a11096aab24c,
title = "Leak detection using the pattern of sound signals in water supply systems",
abstract = "Water supply systems in Japan contribute significantly to improve public health. Unfortunately, there are many age-deteriorated pipes of various sizes and leaks frequently occur. Particularly devastating are hidden leaks occurring underground because when left undetected for years these leaks result in secondary damage. Thus, early detection and treatment of leaks is an important civil engineering challenge. At present the acoustic method is the most popular leak detection method. The purpose of this study is to propose an easy and stable leak detection method using the acoustic method assisted by pattern recognition techniques. In the proposed method we collect in the form of digital signals sound and pseudo-sound samples of underground leaking pipes. Principal component analysis (PCA) of the power spectrum of one leak sound is made, and a new coordinate system is constructed. We project the other sounds in the coordinate system, and evaluate if the sounds are similar to the sample sound or not by comparing the residual between the original and the projection. Next, we evaluate the DSF (Damage Sensitive Feature), which is a function of the first three AR model. At last, the feature vectors are created by combining the residuals, the DSF, and the damping ratio of the AR model, and a leak detection method is proposed using the Support Vector Machine (SVM) based upon them. In this study, it is shown that the residual and DSF are useful indices for leak detection. Furthermore, the proposed method shows high accuracy in recognizing leaks.",
keywords = "Damage sensitive feature, Leak detection, Principal component analysis, Support vector machine",
author = "Toshitaka Sato and Akira Mita",
year = "2007",
doi = "10.1117/12.715486",
language = "English",
isbn = "0819466506",
volume = "6529 PART 2",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Leak detection using the pattern of sound signals in water supply systems

AU - Sato, Toshitaka

AU - Mita, Akira

PY - 2007

Y1 - 2007

N2 - Water supply systems in Japan contribute significantly to improve public health. Unfortunately, there are many age-deteriorated pipes of various sizes and leaks frequently occur. Particularly devastating are hidden leaks occurring underground because when left undetected for years these leaks result in secondary damage. Thus, early detection and treatment of leaks is an important civil engineering challenge. At present the acoustic method is the most popular leak detection method. The purpose of this study is to propose an easy and stable leak detection method using the acoustic method assisted by pattern recognition techniques. In the proposed method we collect in the form of digital signals sound and pseudo-sound samples of underground leaking pipes. Principal component analysis (PCA) of the power spectrum of one leak sound is made, and a new coordinate system is constructed. We project the other sounds in the coordinate system, and evaluate if the sounds are similar to the sample sound or not by comparing the residual between the original and the projection. Next, we evaluate the DSF (Damage Sensitive Feature), which is a function of the first three AR model. At last, the feature vectors are created by combining the residuals, the DSF, and the damping ratio of the AR model, and a leak detection method is proposed using the Support Vector Machine (SVM) based upon them. In this study, it is shown that the residual and DSF are useful indices for leak detection. Furthermore, the proposed method shows high accuracy in recognizing leaks.

AB - Water supply systems in Japan contribute significantly to improve public health. Unfortunately, there are many age-deteriorated pipes of various sizes and leaks frequently occur. Particularly devastating are hidden leaks occurring underground because when left undetected for years these leaks result in secondary damage. Thus, early detection and treatment of leaks is an important civil engineering challenge. At present the acoustic method is the most popular leak detection method. The purpose of this study is to propose an easy and stable leak detection method using the acoustic method assisted by pattern recognition techniques. In the proposed method we collect in the form of digital signals sound and pseudo-sound samples of underground leaking pipes. Principal component analysis (PCA) of the power spectrum of one leak sound is made, and a new coordinate system is constructed. We project the other sounds in the coordinate system, and evaluate if the sounds are similar to the sample sound or not by comparing the residual between the original and the projection. Next, we evaluate the DSF (Damage Sensitive Feature), which is a function of the first three AR model. At last, the feature vectors are created by combining the residuals, the DSF, and the damping ratio of the AR model, and a leak detection method is proposed using the Support Vector Machine (SVM) based upon them. In this study, it is shown that the residual and DSF are useful indices for leak detection. Furthermore, the proposed method shows high accuracy in recognizing leaks.

KW - Damage sensitive feature

KW - Leak detection

KW - Principal component analysis

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=35548971993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35548971993&partnerID=8YFLogxK

U2 - 10.1117/12.715486

DO - 10.1117/12.715486

M3 - Conference contribution

AN - SCOPUS:35548971993

SN - 0819466506

SN - 9780819466501

VL - 6529 PART 2

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -