Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method

The main purpose of this study was to investigate whether machine learning can be used to detect leak sounds in the field. A method for detecting water leaks was developed using a convolutional neural network (CNN), after taking recurrence plots and visualising the time series as input data. In coll...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Y. W. Nam, Y. Arai, T. Kunizane, A. Koizumi
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	actual leaks convolutional neural network hold-out method recurrence plot water leak detection water pipeline Water supply for domestic and industrial purposes TD201-500 River, lake, and water-supply engineering (General) TC401-506
Acceso en línea:	https://doaj.org/article/c2ca1ab646d24faab4a5f480ce3a704a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c2ca1ab646d24faab4a5f480ce3a704a
record_format	dspace
spelling	oai:doaj.org-article:c2ca1ab646d24faab4a5f480ce3a704a2021-11-23T18:55:55ZWater leak detection based on convolutional neural network using actual leak sounds and the hold-out method1606-97491607-079810.2166/ws.2021.109https://doaj.org/article/c2ca1ab646d24faab4a5f480ce3a704a2021-11-01T00:00:00Zhttp://ws.iwaponline.com/content/21/7/3477https://doaj.org/toc/1606-9749https://doaj.org/toc/1607-0798The main purpose of this study was to investigate whether machine learning can be used to detect leak sounds in the field. A method for detecting water leaks was developed using a convolutional neural network (CNN), after taking recurrence plots and visualising the time series as input data. In collaboration with a pipeline restoration company, 20 acoustic datasets of leak sounds were recorded by sensors at 10 leak sites. The detection ability of the constructed CNN model was tested using the hold-out method for the 20 cases: 19 showed more than 70% accuracy, of which 15 showed more than 80%. HIGHLIGHTS We are introducing a next-generation leak detection technique.; We are targeting the analysis of actual leaks, not virtual.; We visualised the inherent characteristics of water leak sound.; This study introduces leak detection techniques through artificial intelligence technology.; The leak detection model proposed in this study has been proven to have sufficient reliability.;Y. W. NamY. AraiT. KunizaneA. KoizumiIWA Publishingarticleactual leaksconvolutional neural networkhold-out methodrecurrence plotwater leak detectionwater pipelineWater supply for domestic and industrial purposesTD201-500River, lake, and water-supply engineering (General)TC401-506ENWater Supply, Vol 21, Iss 7, Pp 3477-3485 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	actual leaks convolutional neural network hold-out method recurrence plot water leak detection water pipeline Water supply for domestic and industrial purposes TD201-500 River, lake, and water-supply engineering (General) TC401-506
spellingShingle	actual leaks convolutional neural network hold-out method recurrence plot water leak detection water pipeline Water supply for domestic and industrial purposes TD201-500 River, lake, and water-supply engineering (General) TC401-506 Y. W. Nam Y. Arai T. Kunizane A. Koizumi Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method
description	The main purpose of this study was to investigate whether machine learning can be used to detect leak sounds in the field. A method for detecting water leaks was developed using a convolutional neural network (CNN), after taking recurrence plots and visualising the time series as input data. In collaboration with a pipeline restoration company, 20 acoustic datasets of leak sounds were recorded by sensors at 10 leak sites. The detection ability of the constructed CNN model was tested using the hold-out method for the 20 cases: 19 showed more than 70% accuracy, of which 15 showed more than 80%. HIGHLIGHTS We are introducing a next-generation leak detection technique.; We are targeting the analysis of actual leaks, not virtual.; We visualised the inherent characteristics of water leak sound.; This study introduces leak detection techniques through artificial intelligence technology.; The leak detection model proposed in this study has been proven to have sufficient reliability.;
format	article
author	Y. W. Nam Y. Arai T. Kunizane A. Koizumi
author_facet	Y. W. Nam Y. Arai T. Kunizane A. Koizumi
author_sort	Y. W. Nam
title	Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method
title_short	Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method
title_full	Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method
title_fullStr	Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method
title_full_unstemmed	Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method
title_sort	water leak detection based on convolutional neural network using actual leak sounds and the hold-out method
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/c2ca1ab646d24faab4a5f480ce3a704a
work_keys_str_mv	AT ywnam waterleakdetectionbasedonconvolutionalneuralnetworkusingactualleaksoundsandtheholdoutmethod AT yarai waterleakdetectionbasedonconvolutionalneuralnetworkusingactualleaksoundsandtheholdoutmethod AT tkunizane waterleakdetectionbasedonconvolutionalneuralnetworkusingactualleaksoundsandtheholdoutmethod AT akoizumi waterleakdetectionbasedonconvolutionalneuralnetworkusingactualleaksoundsandtheholdoutmethod
_version_	1718416180198244352

Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method

Ejemplares similares