Publication:
Railway Axle Condition Monitoring Technique Based on Wavelet Packet Transform Features and Support Vector Machines

Simple item page
dc.affiliation.areaUC3M. Área de Ingeniería Mecánicaes
dc.affiliation.dptoUC3M. Departamento de Ingeniería Mecánicaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: MAQLAB: Laboratorio de Máquinases
dc.contributor.authorGómez García, María Jesús
dc.contributor.authorCastejón Sisamón, Cristina
dc.contributor.authorCorral Abad, Eduardo
dc.contributor.authorGarcía Prada, Juan Carlos
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.date.accessioned2021-07-01T09:19:31Z
dc.date.available2021-07-01T09:19:31Z
dc.date.issued2020-06-02
dc.description.abstractRailway axles are critical to the safety of railway vehicles. However, railway axle maintenance is currently based on scheduled preventive maintenance using Nondestructive Testing. The use of condition monitoring techniques would provide information about the status of the axle between periodical inspections, and it would be very valuable in the prevention of catastrophic failures. Nevertheless, in the literature, there are not many studies focusing on this area and there is a lack of experimental data. In this work, a reliable real-time condition-monitoring technique for railway axles is proposed. The technique was validated using vibration measurements obtained at the axle boxes of a full bogie installed on a rig, where four different cracked railway axles were tested. The technique is based on vibration analysis by means of the Wavelet Packet Transform (WPT) energy, combined with a Support Vector Machine (SVM) diagnosis model. In all cases, it was observed that the WPT energy of the vibration signals at the first natural frequency of the axle when the wheelset is first installed (the healthy condition) increases when a crack is artificially created. An SVM diagnosis model based on the WPT energy at this frequency demonstrates good reliability, with a false alarm rate of lower than 10% and defect detection for damage occurring in more than 6.5% of the section in more than 90% of the cases. The minimum number of wheelsets required to build a general model to avoid mounting effects, among others things, is also discussed.en
dc.description.sponsorshipThis research was funded by the Spanish Government through the project MAQSTATUS with grantnumber DPI2015-69325-C2-1-R.en
dc.format.extent18
dc.identifier.bibliographicCitationGómez, M. J., Castejón, C., Corral, E. & García-Prada, J. C. (2020). Railway Axle Condition Monitoring Technique Based on Wavelet Packet Transform Features and Support Vector Machines. Sensors, 20(12), 3575.en
dc.identifier.doihttps://doi.org/10.3390/s20123575
dc.identifier.issn1424-8220
dc.identifier.publicationfirstpage1
dc.identifier.publicationissue12
dc.identifier.publicationlastpage18
dc.identifier.publicationtitleSensorsen
dc.identifier.publicationvolume20
dc.identifier.urihttps://hdl.handle.net/10016/32969
dc.identifier.uxxiAR/0000026715
dc.language.isoeng
dc.publisherMDPI
dc.relation.projectIDGobierno de España. DPI2015-69325-C2-1-Res
dc.rights© 2020 by the authors.en
dc.rightsAtribución 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subject.ecienciaIngeniería Mecánicaes
dc.subject.otherBogie testingen
dc.subject.otherCondition monitoringen
dc.subject.otherRailway axlesen
dc.subject.otherSupport vector machinesen
dc.subject.otherWavelet packet transformen
dc.titleRailway Axle Condition Monitoring Technique Based on Wavelet Packet Transform Features and Support Vector Machinesen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Railway_Sensors_2020.pdf
Size:
82.82 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
DIM - MAQLAB - Artículos de revistas