An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm

This paper discusses a flaw detection system that uses automated long range ultrasonic detectors modeled on a successful pattern recognition method. The procedure has three stages: 1. a variety of feature extraction methods to better represent the signals; 2. feature ranking based on feature selection; and 3. classification using a kernel-based support vector machine (SVM). The results of analysis indicate that the proposed algorithm is successful at detecting flaws.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9781845646165
• Corporate Authors:

  WIT Press

  Computational Mechanics, 25 Bridge Street
  Billerica, MA  United States  01821
• Authors:
  • Moustakidis, S
  • Kappatos, V
  • Karlsson, P
  • Selcuk, C
  • Hrissagis, K
  • Gan, T H
• Conference:
  • Thirteenth International Conference on Design and Operation in Railway Engineering (COMPRAIL 2012)
  • Location: New Forest , United Kingdom
  • Date: 2012-9-11 to 2012-9-13
• Publication Date: 2012-9

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 199-210
• Monograph Title: Computers in Railways XIII. Computer System Design and Operation in the Railway and Other Transit Systems

Subject/Index Terms

• TRT Terms: Algorithms; Flaw detection; Inspection; Maintenance; Railroad rails; Ultrasonic detectors
• Uncontrolled Terms: Support vector machines
• Subject Areas: Maintenance and Preservation; Railroads; I61: Equipment and Maintenance Methods;

Filing Info

• Accession Number: 01486912
• Record Type: Publication
• ISBN: 9781845646165
• Files: TRIS
• Created Date: Jul 18 2013 1:47PM