Abstract
Recent train accidents have reaffirmed the need for developing a rail defect detection system moreeffective than that currently used. One of the most promising techniques in rail inspection is the use ofultrasonic guided waves and noncontact probes. A rail inspection prototype based on these conceptsand devoted to the automatic damage detection of defects in rail head is the focus of this paper. Theprototype includes an algorithm based on wavelet transform and outlier analysis. The discrete wavelettransform is utilized to denoise ultrasonic signals and to generate a set of relevant damage sensitivedata. These data are combined into a damage index vector fed to an unsupervised learning algorithmbased on outlier analysis that determines the anomalous conditions of the rail. The first part of thepaper shows the prototype in action on a railroad track mock-up built at the University of California,San Diego. The mock-up contained surface and internal defects. The results from three experimentsare presented. The importance of feature selection to maximize the sensitivity of the inspection systemis demonstrated here. The second part of the paper shows the results of field testing conducted in southeast Pennsylvania under the auspices of the U.S. Federal Railroad Administration
Lingua originale | English |
---|---|
pagine (da-a) | 1-13 |
Numero di pagine | 13 |
Rivista | Advances in Civil Engineering |
Volume | vol. 2010 Issue 1 |
Stato di pubblicazione | Published - 2010 |
All Science Journal Classification (ASJC) codes
- ???subjectarea.asjc.2200.2205???