Leakage detection in water distribution networks using hybrid feedforward artificial neural networks

Water leakage control in water distribution networks (WDNs) is one of the main challenges of water utilities. The present study proposes a new method to locate a leakage in WDNs using feedforward artificial neural networks (ANNs). For this purpose, two ANNs training cases are considered. For case 1,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hamideh Fallahi, Mohammadreza Jalili Ghazizadeh, Babak Aminnejad, Jafar Yazdi
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	feedforward artificial neural network hourly water demand leakage variable hourly nodal leakage water distribution networks Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/daa4e5d4b2c045fc85062b5d2fb0e8b7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:daa4e5d4b2c045fc85062b5d2fb0e8b7
record_format	dspace
spelling	oai:doaj.org-article:daa4e5d4b2c045fc85062b5d2fb0e8b72021-11-05T17:13:30ZLeakage detection in water distribution networks using hybrid feedforward artificial neural networks2709-80282709-803610.2166/aqua.2021.140https://doaj.org/article/daa4e5d4b2c045fc85062b5d2fb0e8b72021-08-01T00:00:00Zhttp://aqua.iwaponline.com/content/70/5/637https://doaj.org/toc/2709-8028https://doaj.org/toc/2709-8036Water leakage control in water distribution networks (WDNs) is one of the main challenges of water utilities. The present study proposes a new method to locate a leakage in WDNs using feedforward artificial neural networks (ANNs). For this purpose, two ANNs training cases are considered. For case 1, the ANNs are trained by average daily water demand, including small to large hypothetical leakages. In case 2, the ANNs are trained by hourly water demand and variable hourly nodal leakages over 24 hours. The training parameters are determined by EPANET2.0 hydraulic simulation software using MATLAB programming language. In both cases, first, ANNs are trained using flow rates of total pipes number. Then, sensitivity analysis is performed by hybrid ANNs for the flow rates of pipes number less than the number of the total pipes. The results of proposed hybrid ANNs indicate that if at least the flow rates of 10% of the total pipes are known (using flowmeters), then the leakage locations in both cases can be determined. Despite the complexity of case 2, because of the variations of demand and leakage over the 24-hour period, the proposed method could detect the leakage location with high accuracy. HIGHLIGHTS A leakage detection algorithm for WDNs using feedforward ANNs.; ANNs were applied for two cases: average daily water demand and hypothetical leakages; variable water demand and nodal leakages over the 24-hour.; ANNs training based on pipe flow rates and nodal leakage.; A sensitivity analysis using Hybrid ANNs.; The proposed algorithm successfully detects the leakage locations in both cases by the flow rates of 10% pipes.;Hamideh FallahiMohammadreza Jalili GhazizadehBabak AminnejadJafar YazdiIWA Publishingarticlefeedforward artificial neural networkhourly water demandleakagevariable hourly nodal leakagewater distribution networksEnvironmental technology. Sanitary engineeringTD1-1066Environmental sciencesGE1-350ENAqua, Vol 70, Iss 5, Pp 637-653 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	feedforward artificial neural network hourly water demand leakage variable hourly nodal leakage water distribution networks Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
spellingShingle	feedforward artificial neural network hourly water demand leakage variable hourly nodal leakage water distribution networks Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350 Hamideh Fallahi Mohammadreza Jalili Ghazizadeh Babak Aminnejad Jafar Yazdi Leakage detection in water distribution networks using hybrid feedforward artificial neural networks
description	Water leakage control in water distribution networks (WDNs) is one of the main challenges of water utilities. The present study proposes a new method to locate a leakage in WDNs using feedforward artificial neural networks (ANNs). For this purpose, two ANNs training cases are considered. For case 1, the ANNs are trained by average daily water demand, including small to large hypothetical leakages. In case 2, the ANNs are trained by hourly water demand and variable hourly nodal leakages over 24 hours. The training parameters are determined by EPANET2.0 hydraulic simulation software using MATLAB programming language. In both cases, first, ANNs are trained using flow rates of total pipes number. Then, sensitivity analysis is performed by hybrid ANNs for the flow rates of pipes number less than the number of the total pipes. The results of proposed hybrid ANNs indicate that if at least the flow rates of 10% of the total pipes are known (using flowmeters), then the leakage locations in both cases can be determined. Despite the complexity of case 2, because of the variations of demand and leakage over the 24-hour period, the proposed method could detect the leakage location with high accuracy. HIGHLIGHTS A leakage detection algorithm for WDNs using feedforward ANNs.; ANNs were applied for two cases: average daily water demand and hypothetical leakages; variable water demand and nodal leakages over the 24-hour.; ANNs training based on pipe flow rates and nodal leakage.; A sensitivity analysis using Hybrid ANNs.; The proposed algorithm successfully detects the leakage locations in both cases by the flow rates of 10% pipes.;
format	article
author	Hamideh Fallahi Mohammadreza Jalili Ghazizadeh Babak Aminnejad Jafar Yazdi
author_facet	Hamideh Fallahi Mohammadreza Jalili Ghazizadeh Babak Aminnejad Jafar Yazdi
author_sort	Hamideh Fallahi
title	Leakage detection in water distribution networks using hybrid feedforward artificial neural networks
title_short	Leakage detection in water distribution networks using hybrid feedforward artificial neural networks
title_full	Leakage detection in water distribution networks using hybrid feedforward artificial neural networks
title_fullStr	Leakage detection in water distribution networks using hybrid feedforward artificial neural networks
title_full_unstemmed	Leakage detection in water distribution networks using hybrid feedforward artificial neural networks
title_sort	leakage detection in water distribution networks using hybrid feedforward artificial neural networks
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/daa4e5d4b2c045fc85062b5d2fb0e8b7
work_keys_str_mv	AT hamidehfallahi leakagedetectioninwaterdistributionnetworksusinghybridfeedforwardartificialneuralnetworks AT mohammadrezajalilighazizadeh leakagedetectioninwaterdistributionnetworksusinghybridfeedforwardartificialneuralnetworks AT babakaminnejad leakagedetectioninwaterdistributionnetworksusinghybridfeedforwardartificialneuralnetworks AT jafaryazdi leakagedetectioninwaterdistributionnetworksusinghybridfeedforwardartificialneuralnetworks
_version_	1718444132103356416

Leakage detection in water distribution networks using hybrid feedforward artificial neural networks

Ejemplares similares