Repository logo
 
Publication

Non-intrusive low-cost IoT-based hardware system for sustainable predictive maintenance of industrial pump systems

2025-07-21Journal article Open access
Simple item page
dc.contributor.authorBrito, Sergio
dc.contributor.authorAzinheira, Gonçalo
dc.contributor.authorSemião, Jorge
dc.contributor.authorSousa, Nelson
dc.contributor.authorPérez Litrán, Salvador
dc.date.accessioned2025-10-03T11:47:33Z
dc.date.available2025-10-03T11:47:33Z
dc.date.issued2025-07-21
dc.description.abstractIndustrial maintenance has shifted from reactive repairs and calendar-based servicing toward data-driven predictive strategies. This paper presents a non-intrusive, low-cost IoT hardware platform for sustainable predictive maintenance of rotating machinery. The system integrates an ESP32-S3 sensor node that captures vibration (100 kHz) and temperature data, performs local logging, and communicates wirelessly. An automated spectral band segmentation framework is introduced, comparing equal-energy, linear-width, nonlinear, clustering, and peak-valley partitioning methods, followed by a weighted feature scheme that emphasizes high-value bands. Three unsupervised one-class classifiers-transformer autoencoders, GANomaly, and Isolation Forest-are evaluated on these weighted spectral features. Experiments conducted on a custom pump test bench with controlled anomaly severities demonstrate strong anomaly classification performance across multiple configurations, supported by detailed threshold-characterization metrics.eng
dc.description.sponsorship0085_ATTENTIA_5_E, (POCTEP) 2021–2027
dc.identifier.doi10.3390/electronics14142913
dc.identifier.issn2079-9292
dc.identifier.urihttp://hdl.handle.net/10400.1/27786
dc.language.isoeng
dc.peerreviewedyes
dc.publisherMDPI
dc.relation.ispartofElectronics
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectPredictive maintenance
dc.subjectIoT
dc.subjectVibration analysis
dc.subjectWireless sensor networks
dc.subjectMachine learning
dc.subjectLow-cost sensors
dc.subjectFFT
dc.subjectAnomaly detection
dc.titleNon-intrusive low-cost IoT-based hardware system for sustainable predictive maintenance of industrial pump systemseng
dc.typejournal article
dspace.entity.typePublication
oaire.citation.issue14
oaire.citation.startPage2913
oaire.citation.titleElectronics
oaire.citation.volume14
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameBrito
person.familyNameAzinheira
person.familyNameSemião
person.familyNameSousa
person.givenNameSergio
person.givenNameGonçalo
person.givenNameJorge
person.givenNameNelson
person.identifier3016271
person.identifierR-001-F67
person.identifier.ciencia-idB616-9C41-C169
person.identifier.ciencia-id8C16-E46C-4C86
person.identifier.orcid0009-0008-7287-0431
person.identifier.orcid0000-0002-3139-2081
person.identifier.orcid0000-0002-7667-7910
person.identifier.orcid0000-0001-5205-8608
person.identifier.ridL-6700-2015
person.identifier.scopus-author-id15924042200
person.identifier.scopus-author-id57198012719
relation.isAuthorOfPublication458c5d10-4804-434b-a2a7-8d1d3ce16034
relation.isAuthorOfPublication6d4a399a-3824-435b-b680-2cc2539440eb
relation.isAuthorOfPublication12454e89-e25e-4e96-8b64-39974f6fba07
relation.isAuthorOfPublication2c4c30ce-220e-4381-9462-41c35985071d
relation.isAuthorOfPublication.latestForDiscovery12454e89-e25e-4e96-8b64-39974f6fba07

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
electronics-14-02913-v2 (1).pdf
Size:
6.79 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.46 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections