Wheel Defect Detection With Machine Learning

Wheel defects on railway wagons have been identified as an important source of damage to the railway infrastructure and rolling stock. They also cause noise and vibration emissions that are costly to mitigate. The authors propose two machine learning methods to automatically detect these wheel defects, based on the wheel vertical force measured by a permanently installed sensor system on the railway network. Their methods automatically learn different types of wheel defects and predict during normal operation if a wheel has a defect or not. The first method is based on novel features for classifying time series data and it is used for classification with a support vector machine. To evaluate the performance of their method the authors construct multiple data sets for the following defect types: flat spot, shelling, and non-roundness. The authors outperform classical defect detection methods for flat spots and demonstrate prediction for the other two defect types for the first time. Motivated by the recent success of artificial neural networks for image classification, they train custom artificial neural networks with convolutional layers on 2-D representations of the measurement time series. The neural network approach improves the performance on wheels with flat spots and non-roundness by explicitly modeling the multi sensor structure of the measurement system through multiple instance learning and shift invariant networks.

• Record URL:
  • https://doi.org/10.1109/TITS.2017.2720721
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2018, IEEE.
• Authors:
  • Krummenacher, Gabriel
  • Ong, Cheng Soon
  • Koller, Stefan
  • Kobayashi, Seijin
  • Buhmann, Joachim M
• Publication Date: 2018-4

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 1176-1187
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 19
  • Issue Number: 4
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Algorithms; Defects; Flaw detection; Machine learning; Neural networks; Railroad crashes; Railroad safety; Railroad wheelsets; Rolling contact; Rolling stock; Statistical analysis
• Subject Areas: Data and Information Technology; Maintenance and Preservation; Railroads; Vehicles and Equipment;

Filing Info

• Accession Number: 01671069
• Record Type: Publication
• Files: TLIB, TRIS
• Created Date: May 29 2018 5:18PM