Publication: Effective Crack Detection in Railway Axles Using Vibration Signals and WPT Energy
Loading...
Identifiers
Publication date
2018-05-17
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
MDPI
Impact
Export
Abstract
Crack detection for railway axles is key to avoiding catastrophic accidents. Currently, non-destructive testing is used for that purpose. The present work applies vibration signal analysis to diagnose cracks in real railway axles installed on a real Y21 bogie working on a rig. Vibration signals were obtained from two wheelsets with cracks at the middle section of the axle with depths from 5.7 to 15 mm, at several conditions of load and speed. Vibration signals were processed by means of wavelet packet transform energy. Energies obtained were used to train an artificial neural network, with reliable diagnosis results. The success rate of 5.7 mm defects was 96.27%, and the reliability in detecting larger defects reached almost 100%, with a false alarm ratio lower than 5.5%.
Description
Keywords
Bogies test rig, Condition monitoring, Crack detection, Vibration analysis
Bibliographic citation
Gómez, M.J., Corral, E., Castejón, C., García-Prada, J.C. Effective Crack Detection in Railway Axles Using Vibration Signals and WPT Energy. Sensors 2018, 18, 1603.