Please use this identifier to cite or link to this item:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Leak localization in water distribution networks using deep learning

AuthorsJavadiha, Mohammadreza; Blesa, Joaquim CSIC ORCID ; Soldevila, Adrià; Puig, Vicenç CSIC ORCID
KeywordsWater distribution networks
Leak localization
Deep Learning
Fault diagnosis
Bayesian technique
Issue Date23-Apr-2019
PublisherInstitute of Electrical and Electronics Engineers
Citation6th International Conference on Control, Decision and Information Technologies (2019)
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.
DescriptionTrabajo presentado en el 6th International Conference on Control, Decision and Information Technologies (CoDIT), celebrado en París (Francia), del 23 al 26 de abril de 2019
Publisher version (URL)
Identifiersdoi: 10.1109/CoDIT.2019.8820627
Appears in Collections:(IRII) Comunicaciones congresos

Files in This Item:
File Description SizeFormat
789988.pdf1,48 MBUnknownView/Open
Show full item record
Review this work

Google ScholarTM




WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.