Show simple item record

dc.contributor.authorJavadiha, Mohammadreza
dc.contributor.authorBlesa Izquierdo, Joaquim
dc.contributor.authorSoldevila Coma, Adrià
dc.contributor.authorPuig Cayuela, Vicenç
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial
dc.date.accessioned2020-02-13T14:06:46Z
dc.date.available2020-02-13T14:06:46Z
dc.date.issued2019
dc.identifier.citationJavadiha, M. [et al.]. Leak localization in water distribution networks using deep learning. A: International Conference on Control, Decision and Information Technologies. "2019 6th International Conferenceon Control, Decision and Information Technologies (CoDIT’19): April 23-26, 2019, Le Cnam, Paris, France". Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 1426-1431.
dc.identifier.isbn978-1-7281-0521-5
dc.identifier.urihttp://hdl.handle.net/2117/177655
dc.description.abstractThis paper explores the use of deep learning for leak localization in Water Distribution Networks (WDNs) using pressure measurements. By using a training data set including enough samples of all possible leak localizations, a Convolutional Neural Network(CNN) can be used to learn the different pressure maps that characterized each leak localization. The generalization accuracy has validated and evaluated by means of a testing data set. All of considered training, validation,and also testing data include leak size uncertainty, nodal water demand uncertainty and sensor noise. An innovative approach is proposed to convert every pressure residuals map to an image in order to apply a CNN. In addition with the purpose of filtering the effects of uncertainty and noise a time horizon Bayesian reasoning approach is used over each time instant classification output by the CNN. The Hanoi District Metered Area (DMA) is considered as a case study to illustrate the performance of the proposed leak localization method.
dc.format.extent6 p.
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subjectÀrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica
dc.subject.lcshMachine learning
dc.subject.lcshWater -- Distribution
dc.subject.otherWater distribution networks
dc.subject.otherLeak localization
dc.subject.otherDeep Learning
dc.subject.otherFault diagnosis
dc.subject.otherBayesian technique
dc.titleLeak localization in water distribution networks using deep learning
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacAigua -- Distribució
dc.contributor.groupUniversitat Politècnica de Catalunya. SAC - Sistemes Avançats de Control
dc.identifier.doi10.1109/CoDIT.2019.8820627
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/8820627
dc.rights.accessOpen Access
local.identifier.drac26748343
dc.description.versionPostprint (author's final draft)
local.citation.authorJavadiha, M.; Blesa, J.; Soldevila, A.; Puig, V.
local.citation.contributorInternational Conference on Control, Decision and Information Technologies
local.citation.publicationName2019 6th International Conferenceon Control, Decision and Information Technologies (CoDIT’19): April 23-26, 2019, Le Cnam, Paris, France
local.citation.startingPage1426
local.citation.endingPage1431


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder