Abstract
This paper develops a defect-based risk analysis methodology for estimating rail failure risk. The methodology relies on an evolution model addressing the severity level of rail surface defect, called squat. The risk of rail failure is assessed by analyzing squat failure probability using a probabilistic analysis of the squat cracks. For this purpose, a Bayesian inference method is employed to capture a robust model of squat failure probability when the squat becomes severe. Moreover, an experimental correlation between squat visual length and squat crack depth is obtained in order to define four severity categories. Relying on the failure probability and the severity categories of the squats, risk of future failure is categorized in three different scenarios (optimistic, average and pessimistic). To show the practicality and efficiency of the proposed methodology, a real example is illustrated.
Original language | English |
---|---|
Title of host publication | IFAC-PapersOnLine |
Subtitle of host publication | Proceedings of the 14th IFAC Symposium on Control in Transportation Systems (CTS 2016) |
Editors | Tankut Acarman |
Place of Publication | Laxenburg, Austria |
Publisher | Elsevier |
Pages | 73-77 |
Volume | 49-3 |
DOIs | |
Publication status | Published - 2016 |
Event | 14th IFAC Symposium on Control in Transportation Systems - ITU Faculty of Architecture, Istanbul, Turkey Duration: 18 May 2016 → 20 May 2016 http://www.cts2016.org/en/ |
Publication series
Name | IFAC-PapersOnLine |
---|---|
Publisher | IFAC-Elsevier |
Number | 3 |
Volume | 49 |
ISSN (Print) | 2405-8963 |
Conference
Conference | 14th IFAC Symposium on Control in Transportation Systems |
---|---|
Abbreviated title | CTS 2016 |
Country/Territory | Turkey |
City | Istanbul |
Period | 18/05/16 → 20/05/16 |
Internet address |
Keywords
- imbalance data
- semi-supervised learning
- rail image data
- rail defect detection