PMSM fault detection using unsupervised learning methods based on conditional convolution autoencoder

Simple item page
dc.contributor.authorKozovský, Matúšcs
dc.contributor.authorBuchta, Luděkcs
dc.contributor.authorBlaha, Petrcs
dc.date.accessioned2025-04-04T11:56:51Z
dc.date.available2025-04-04T11:56:51Z
dc.date.issued2024-11-03cs
dc.description.abstractThe challenges of fault detection and condition monitoring in powertrain systems have become increasingly prominent, particularly with the widespread adoption of failoperational systems. These systems are pivotal in diverse sectors, including the robotics, automotive industry, and various industrial applications. A critical attribute of such systems lies in their capability to identify non-standard behaviour of the system. This study describes a inovative conditional convolutional autoencoder-based fault detection algorithm for the permanent magnet synchronous motor. The study compares a train process of conditional convolutional autoencoder with a classical convolutional autoencoder. The presented autoencoder structure was designed to be implementable into the target microcontroller AURIX TC397 while providing sufficient recognition capabilities of the interturn short-circuit. Autoencoders are trained on data obtained during healthy motor operation and subsequently used to detect interturn short-circuit faults on the experimental dual three-phase permanent magnet synchronous motor with the possibility of emulating an interturn short-circuit fault. The paper provides insights into the achieved autoencoder inference times and the sensitivity in detecting the fault.en
dc.formattextcs
dc.format.extent1-6cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationIECON 2024- 50th Annual Conference of the IEEE Industrial Electronics Society. 2024, p. 1-6.en
dc.identifier.doi10.1109/IECON55916.2024.10905074cs
dc.identifier.isbn978-1-6654-6454-3cs
dc.identifier.orcid0000-0002-1547-1003cs
dc.identifier.orcid0000-0002-8954-3495cs
dc.identifier.orcid0000-0001-5534-2065cs
dc.identifier.other193461cs
dc.identifier.researcheridE-2371-2018cs
dc.identifier.researcheridG-8085-2014cs
dc.identifier.researcheridD-6854-2012cs
dc.identifier.scopus56028720700cs
dc.identifier.scopus7006825993cs
dc.identifier.urihttps://hdl.handle.net/11012/250793
dc.language.isoencs
dc.publisherIEEEcs
dc.relation.ispartofIECON 2024- 50th Annual Conference of the IEEE Industrial Electronics Societycs
dc.relation.urihttps://ieeexplore.ieee.org/document/10905074cs
dc.rights(C) IEEEcs
dc.rights.accessopenAccesscs
dc.subjectautoencoderen
dc.subjectconditional convolutionen
dc.subjectfault diagnosticen
dc.subjectpermanent magnet synchronous motor (PMSM)en
dc.titlePMSM fault detection using unsupervised learning methods based on conditional convolution autoencoderen
dc.type.driverconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionacceptedVersionen
sync.item.dbidVAV-193461en
sync.item.dbtypeVAVen
sync.item.insts2025.04.04 13:56:51en
sync.item.modts2025.04.03 13:32:14en
thesis.grantorVysoké učení technické v Brně. Středoevropský technologický institut VUT. Kybernetika a robotikacs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
IECON55916.2024.10905074_accepted.pdf
Size:
1.22 MB
Format:
Adobe Portable Document Format
Description:
file IECON55916.2024.10905074_accepted.pdf
Download
Collections
Kybernetika a robotika