Repository logo
 
Publication

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

2023Journal article Open access
Simple item page
dc.contributor.authorAntunes, André
dc.contributor.authorFerreira, Bruno
dc.contributor.authorMarques, Nuno
dc.contributor.authorCarriço, Nelson
dc.date.accessioned2023-03-22T16:06:58Z
dc.date.available2023-03-22T16:06:58Z
dc.date.issued2023
dc.description.abstractThe current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training set batch size, optimizer learning rate regularization, and model structure. The study was applied using a case study of a real WDN. Obtained results indicate that the ideal model parameters consist of a CNN with a convolutional 1D layer (using 32 filters, a kernel size of 3 and strides equal to 1) for a maximum of 5000 epochs using a total of 250 datasets (using data normalization between 0 and 1 and tolerance equal to max noise) and a batch size of 500 samples per epoch step, optimized with Adam using learning rate regularization. This model was evaluated for distinct measurement noise levels and pipe burst locations. Results indicate that the parameterized model can provide a pipe burst search area with more or less dispersion depending on both the proximity of pressure sensors to the burst or the noise measurement level.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationAntunes, A., Ferreira, B., Marques, N., & Carriço, N. (2023). Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks. Journal of Imaging, 9(3), 68. http://dx.doi.org/10.3390/jimaging9030068pt_PT
dc.identifier.doi10.3390/jimaging9030068pt_PT
dc.identifier.issn2313-433X
dc.identifier.urihttp://hdl.handle.net/10400.26/44321
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.relation.publisherversionhttps://www.mdpi.com/2313-433X/9/3/68pt_PT
dc.subjectConvolutional neural networkspt_PT
dc.subjectDeep learningpt_PT
dc.subjectHydraulic modelpt_PT
dc.subjectHyper parameterizationpt_PT
dc.subjectPipe burst locationpt_PT
dc.titleHyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networkspt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FDS%2F0089%2F2018/PT
oaire.fundingStream3599-PPCDT
person.familyNameNamorado Canhoto Antunes
person.familyNameCarriço
person.givenNameAndré Miguel
person.givenNameNelson
person.identifierH-2945-2012
person.identifier.ciencia-idE717-C765-4699
person.identifier.ciencia-id3A1B-E21C-C25A
person.identifier.orcid0000-0001-9030-5956
person.identifier.orcid0000-0002-2474-7665
person.identifier.scopus-author-id55191330100
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication77b16a8b-6048-44b8-87b0-4898715f9da3
relation.isAuthorOfPublication50e5fafa-1d0d-440e-aebd-3a1a49f136c3
relation.isAuthorOfPublication.latestForDiscovery50e5fafa-1d0d-440e-aebd-3a1a49f136c3
relation.isProjectOfPublication405a772d-bf44-4595-8453-1a7e4df2a4c5
relation.isProjectOfPublication.latestForDiscovery405a772d-bf44-4595-8453-1a7e4df2a4c5

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
jimaging-09-00068.pdf
Size:
8.34 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.85 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

IPS - ESTS – DSI - Artigos científicos