Repository logo
 
Publication

Unsupervised anomaly detection in industrial machines supported by vibration analysis under data scarcity constraints

2025Conference paper Restricted access
Simple item page
dc.contributor.authorTorres, Pedro
dc.contributor.authorSpencer, Geoffrey
dc.contributor.authorEsteves, Arthur
dc.contributor.authorSousa, Fernando
dc.contributor.authorPereira, Fernando J.G.
dc.contributor.authorGuerreiro, Rui M.L.
dc.date.accessioned2025-10-24T14:36:04Z
dc.date.available2025-10-24T14:36:04Z
dc.date.issued2025
dc.description.abstractThe integration of the use of Artificial Intelligence (AI) in industrial environments often faces the lack of labeled data, as well as historical records. This lack of information becomes a problem when implementing predictive maintenance solutions, particularly in monitoring the condition of industrial machines and automatic fault detection. This work addresses this issue in an industrial scenario, through the analysis of vibrations in a spindle motor of an ornamental stone cutting machine. Unsupervised learning techniques are explored for anomaly detection through vibration data, using the training and implementation of an LSTM (Long Short-Term Memory) Autoencoder model. Datasets consist only of unlabeled accelerometer signals acquired during normal machine operation. An analysis based on the extraction of statistical features from the signal is adopted to use them as inputs of the Machine Learning algorithm, to learn the normal behavior of the machine and detect deviations that may correspond to potential anomalies. The experimental results show that even in the absence of labeled data, it is possible to extract meaningful insights from the machine state and establish a practical pipeline for anomaly detection in industrial machines through vibration analysis.eng
dc.identifier.citationTORRES, Pedro [et al.] (2025) - Unsupervised anomaly detection in industrial machines supported by vibration analysis under data scarcity constraints. In IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA), Porto, 2025. DOI: 10.1109/ETFA65518.2025.11205807
dc.identifier.doi10.1109/ETFA65518.2025.11205807
dc.identifier.urihttp://hdl.handle.net/10400.11/10338
dc.language.isoeng
dc.peerreviewedyes
dc.publisherIEEE
dc.rights.uriN/A
dc.subjectCondition monitoring
dc.subjectAnomaly detection
dc.subjectVibration analysis
dc.subjectUnsupervised learning
dc.subjectData scarcity
dc.subjectLSTM Autoencoder
dc.titleUnsupervised anomaly detection in industrial machines supported by vibration analysis under data scarcity constraintseng
dc.typeconference paper
dspace.entity.typePublication
oaire.citation.conferenceDate2025
oaire.citation.conferencePlacePorto
oaire.citation.titleIEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameBAPTISTA TORRES
person.givenNamePEDRO MIGUEL
person.identifierK-5331-2015
person.identifier.ciencia-id2711-E707-519C
person.identifier.orcid0000-0003-4835-5022
person.identifier.scopus-author-id56261515100
relation.isAuthorOfPublication9d9ad49f-3c45-4a99-be21-7f13965c2628
relation.isAuthorOfPublication.latestForDiscovery9d9ad49f-3c45-4a99-be21-7f13965c2628

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Unsupervised_Anomaly_Detection.pdf
Size:
275.38 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.02 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ESTCB - Comunicações em encontros científicos e técnicos