Ensemble-based machine learning approach for improved leak detection in water mains

This paper presents an acoustic leak detection system for distribution water mains using machine learning methods. The problem is formulated as a binary classifier to identify leak and no-leak cases using acoustic signals. A supervised learning methodology has been employed using several detection f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Thambirajah Ravichandran, Keyhan Gavahi, Kumaraswamy Ponnambalam, Valentin Burtea, S. Jamshid Mousavi
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	acoustic features leak detection machine learning multi-strategy ensemble learning Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
Acceso en línea:	https://doaj.org/article/96c71f6db93e4006adf40aac38e46210
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:96c71f6db93e4006adf40aac38e46210
record_format	dspace
spelling	oai:doaj.org-article:96c71f6db93e4006adf40aac38e462102021-11-05T17:42:59ZEnsemble-based machine learning approach for improved leak detection in water mains1464-71411465-173410.2166/hydro.2021.093https://doaj.org/article/96c71f6db93e4006adf40aac38e462102021-03-01T00:00:00Zhttp://jh.iwaponline.com/content/23/2/307https://doaj.org/toc/1464-7141https://doaj.org/toc/1465-1734This paper presents an acoustic leak detection system for distribution water mains using machine learning methods. The problem is formulated as a binary classifier to identify leak and no-leak cases using acoustic signals. A supervised learning methodology has been employed using several detection features extracted from acoustic signals, such as power spectral density and time-series data. The training and validation data sets have been collected over several months from multiple cities across North America. The proposed solution includes a multi-strategy ensemble learning (MEL) using a gradient boosting tree (GBT) classification model, which has performed better in maximizing detection rate and minimizing false positives as compared with other classification models such as KNN, ANN, and rule-based techniques. Further improvements have been achieved using a multitude of GBT classifiers combined in a parallel ensemble method called bagging algorithm. The proposed MEL approach demonstrates a significant improvement in performance, resulting in a reduction of false positives reports by an order of magnitude. HIGHLIGHTS State-of-the-art machine learning (ML) algorithms are used for solving the leak detection problem in water mains.; A large number of acoustic signals and data are collected and used along with dimensionality reduction techniques as input features to ML algorithms.; A novel multi-strategy ensemble-based algorithm is applied to improve further the performance of the investigated leak detection classification problem.;Thambirajah RavichandranKeyhan GavahiKumaraswamy PonnambalamValentin BurteaS. Jamshid MousaviIWA Publishingarticleacoustic featuresleak detectionmachine learningmulti-strategy ensemble learningInformation technologyT58.5-58.64Environmental technology. Sanitary engineeringTD1-1066ENJournal of Hydroinformatics, Vol 23, Iss 2, Pp 307-323 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	acoustic features leak detection machine learning multi-strategy ensemble learning Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
spellingShingle	acoustic features leak detection machine learning multi-strategy ensemble learning Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066 Thambirajah Ravichandran Keyhan Gavahi Kumaraswamy Ponnambalam Valentin Burtea S. Jamshid Mousavi Ensemble-based machine learning approach for improved leak detection in water mains
description	This paper presents an acoustic leak detection system for distribution water mains using machine learning methods. The problem is formulated as a binary classifier to identify leak and no-leak cases using acoustic signals. A supervised learning methodology has been employed using several detection features extracted from acoustic signals, such as power spectral density and time-series data. The training and validation data sets have been collected over several months from multiple cities across North America. The proposed solution includes a multi-strategy ensemble learning (MEL) using a gradient boosting tree (GBT) classification model, which has performed better in maximizing detection rate and minimizing false positives as compared with other classification models such as KNN, ANN, and rule-based techniques. Further improvements have been achieved using a multitude of GBT classifiers combined in a parallel ensemble method called bagging algorithm. The proposed MEL approach demonstrates a significant improvement in performance, resulting in a reduction of false positives reports by an order of magnitude. HIGHLIGHTS State-of-the-art machine learning (ML) algorithms are used for solving the leak detection problem in water mains.; A large number of acoustic signals and data are collected and used along with dimensionality reduction techniques as input features to ML algorithms.; A novel multi-strategy ensemble-based algorithm is applied to improve further the performance of the investigated leak detection classification problem.;
format	article
author	Thambirajah Ravichandran Keyhan Gavahi Kumaraswamy Ponnambalam Valentin Burtea S. Jamshid Mousavi
author_facet	Thambirajah Ravichandran Keyhan Gavahi Kumaraswamy Ponnambalam Valentin Burtea S. Jamshid Mousavi
author_sort	Thambirajah Ravichandran
title	Ensemble-based machine learning approach for improved leak detection in water mains
title_short	Ensemble-based machine learning approach for improved leak detection in water mains
title_full	Ensemble-based machine learning approach for improved leak detection in water mains
title_fullStr	Ensemble-based machine learning approach for improved leak detection in water mains
title_full_unstemmed	Ensemble-based machine learning approach for improved leak detection in water mains
title_sort	ensemble-based machine learning approach for improved leak detection in water mains
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/96c71f6db93e4006adf40aac38e46210
work_keys_str_mv	AT thambirajahravichandran ensemblebasedmachinelearningapproachforimprovedleakdetectioninwatermains AT keyhangavahi ensemblebasedmachinelearningapproachforimprovedleakdetectioninwatermains AT kumaraswamyponnambalam ensemblebasedmachinelearningapproachforimprovedleakdetectioninwatermains AT valentinburtea ensemblebasedmachinelearningapproachforimprovedleakdetectioninwatermains AT sjamshidmousavi ensemblebasedmachinelearningapproachforimprovedleakdetectioninwatermains
_version_	1718444114244009984

Ensemble-based machine learning approach for improved leak detection in water mains

Ejemplares similares