PCA-based leakage detection method for water supply systems considering complex Fourier components

Chikako Kondo, Akira Mita

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

Abstract

The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds, such as gas flow sounds, water usage sounds etc., are collected by microphone put on the ground. The Fourier spectra are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components of each collected sound data. The contribution ratio and the kurtosis of the eigenvector of the first principal component show the good ability to distinguish the water leakage sounds from the pseudo sounds. Therefore, the feature vectors are created from these PCA parameters. Based on them, the Support Vector Machine (SVM) is built. The results show that the classification can reach a very high accuracy. At last, applicability of the proposed water leakage detection method is well demonstrated.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume7292
EditionPART 1
DOIs
Publication statusPublished - 2009
EventSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2009 - San Diego, CA, United States
Duration: 2009 Mar 92009 Mar 12

Other

OtherSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2009
CountryUnited States
CitySan Diego, CA
Period09/3/909/3/12

Fingerprint

Water supply systems
principal components analysis
complex systems
Leakage
Principal component analysis
Principal Component Analysis
Complex Systems
leakage
Acoustic waves
Water
acoustics
water
Short-time Fourier Transform
Fourier Spectrum
kurtosis
disasters
Kurtosis
Principal Components
Microphones
Gas Flow

Keywords

  • Auditory test
  • Leak detection
  • Principal component analysis
  • Short-time Fourier transform
  • Support Vector Machine

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Kondo, C., & Mita, A. (2009). PCA-based leakage detection method for water supply systems considering complex Fourier components. In Proceedings of SPIE - The International Society for Optical Engineering (PART 1 ed., Vol. 7292). [729234] https://doi.org/10.1117/12.815342

PCA-based leakage detection method for water supply systems considering complex Fourier components. / Kondo, Chikako; Mita, Akira.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7292 PART 1. ed. 2009. 729234.

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

Kondo, C & Mita, A 2009, PCA-based leakage detection method for water supply systems considering complex Fourier components. in Proceedings of SPIE - The International Society for Optical Engineering. PART 1 edn, vol. 7292, 729234, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2009, San Diego, CA, United States, 09/3/9. https://doi.org/10.1117/12.815342
Kondo C, Mita A. PCA-based leakage detection method for water supply systems considering complex Fourier components. In Proceedings of SPIE - The International Society for Optical Engineering. PART 1 ed. Vol. 7292. 2009. 729234 https://doi.org/10.1117/12.815342
Kondo, Chikako ; Mita, Akira. / PCA-based leakage detection method for water supply systems considering complex Fourier components. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7292 PART 1. ed. 2009.
@inproceedings{d08e84052dad4c97ab8535ba5f5ba1cb,
title = "PCA-based leakage detection method for water supply systems considering complex Fourier components",
abstract = "The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds, such as gas flow sounds, water usage sounds etc., are collected by microphone put on the ground. The Fourier spectra are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components of each collected sound data. The contribution ratio and the kurtosis of the eigenvector of the first principal component show the good ability to distinguish the water leakage sounds from the pseudo sounds. Therefore, the feature vectors are created from these PCA parameters. Based on them, the Support Vector Machine (SVM) is built. The results show that the classification can reach a very high accuracy. At last, applicability of the proposed water leakage detection method is well demonstrated.",
keywords = "Auditory test, Leak detection, Principal component analysis, Short-time Fourier transform, Support Vector Machine",
author = "Chikako Kondo and Akira Mita",
year = "2009",
doi = "10.1117/12.815342",
language = "English",
isbn = "9780819475527",
volume = "7292",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
edition = "PART 1",

}

TY - GEN

T1 - PCA-based leakage detection method for water supply systems considering complex Fourier components

AU - Kondo, Chikako

AU - Mita, Akira

PY - 2009

Y1 - 2009

N2 - The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds, such as gas flow sounds, water usage sounds etc., are collected by microphone put on the ground. The Fourier spectra are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components of each collected sound data. The contribution ratio and the kurtosis of the eigenvector of the first principal component show the good ability to distinguish the water leakage sounds from the pseudo sounds. Therefore, the feature vectors are created from these PCA parameters. Based on them, the Support Vector Machine (SVM) is built. The results show that the classification can reach a very high accuracy. At last, applicability of the proposed water leakage detection method is well demonstrated.

AB - The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds, such as gas flow sounds, water usage sounds etc., are collected by microphone put on the ground. The Fourier spectra are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components of each collected sound data. The contribution ratio and the kurtosis of the eigenvector of the first principal component show the good ability to distinguish the water leakage sounds from the pseudo sounds. Therefore, the feature vectors are created from these PCA parameters. Based on them, the Support Vector Machine (SVM) is built. The results show that the classification can reach a very high accuracy. At last, applicability of the proposed water leakage detection method is well demonstrated.

KW - Auditory test

KW - Leak detection

KW - Principal component analysis

KW - Short-time Fourier transform

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=77955707880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955707880&partnerID=8YFLogxK

U2 - 10.1117/12.815342

DO - 10.1117/12.815342

M3 - Conference contribution

AN - SCOPUS:77955707880

SN - 9780819475527

VL - 7292

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

ER -