Journal
SENSORS
Volume 18, Issue 5, Pages -Publisher
MDPI
DOI: 10.3390/s18051603
Keywords
bogies test rig; condition monitoring; crack detection; vibration analysis
Funding
- Spanish Government [MAQ-STATUS DPI2015-69325-C2-1-R]
- Renfe, Alstom Spain
- SKF Spain
- Danobat Railway Systems
Ask authors/readers for more resources
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%.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available