Full Content is available to subscribers

Subscribe/Learn More  >

Modeling Track Geometry Degradation Using Support Vector Machine Technique

[+] Author Affiliations
Can Hu, Xiang Liu

Rutgers, The State University of New Jersey, Piscataway, NJ

Paper No. JRC2016-5739, pp. V001T01A011; 6 pages
  • 2016 Joint Rail Conference
  • 2016 Joint Rail Conference
  • Columbia, South Carolina, USA, April 12–15, 2016
  • Conference Sponsors: Rail Transportation Division
  • ISBN: 978-0-7918-4967-5
  • Copyright © 2016 by ASME


Analyzing track geometry defects is of crucial importance for railway safety. Understanding when a defect will need to be repaired can help in both planning a preventive maintenance schedule and reducing the probability of track failures. This paper discusses the data cleaning and analysis processes for modeling track geometry degradation. An analytical data model named the Support Vector Machine (SVM) was developed to model the deterioration of track geometry defects. This paper mainly focuses on the following three defect types — surface, cross level and dip. The model accounts for traffic volume, defect amplitude, track class, speed and other potential factors. Results demonstrate that the proposed analytical data model can have a prediction accuracy above 70%.

Copyright © 2016 by ASME



Interactive Graphics


Country-Specific Mortality and Growth Failure in Infancy and Yound Children and Association With Material Stature

Use interactive graphics and maps to view and sort country-specific infant and early dhildhood mortality and growth failure data and their association with maternal

Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In