Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest
Railway switches and crossings (S&Cs) are critical, high-value assets in railway networks. A single failure of such an asset could result in severe network disturbance and considerable economical losses. Squats are common rail surface defects of S&Cs and need to be detected and estimated at...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/17/6357 |
| _version_ | 1797493237315796992 |
|---|---|
| author | Yang Zuo Florian Thiery Praneeth Chandran Johan Odelius Matti Rantatalo |
| author_facet | Yang Zuo Florian Thiery Praneeth Chandran Johan Odelius Matti Rantatalo |
| author_sort | Yang Zuo |
| collection | DOAJ |
| description | Railway switches and crossings (S&Cs) are critical, high-value assets in railway networks. A single failure of such an asset could result in severe network disturbance and considerable economical losses. Squats are common rail surface defects of S&Cs and need to be detected and estimated at an early stage to minimise maintenance costs and increase the reliability of S&Cs. For practicality, installation of wired or wireless sensors along the S&C may not be reliable due to the risk of damages of power and signal cables or sensors. To cope with these issues, this study presents a method for collecting and processing vibration data from an accelerometer installed at the point machine to extract features related to the squat defects of the S&C. An unsupervised anomaly-detection method using the isolation forest algorithm is applied to generate anomaly scores from the features. Important features are ranked and selected. This paper describes the procedure of parameter tuning and presents the achieved anomaly scores. The results show that the proposed method is effective and that the generated anomaly scores indicate the health status of an S&C regarding squat defects. |
| first_indexed | 2024-03-10T01:17:08Z |
| format | Article |
| id | doaj.art-744ee8a9e98e4a0a88076b484d65f07a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T01:17:08Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-744ee8a9e98e4a0a88076b484d65f07a2023-11-23T14:07:07ZengMDPI AGSensors1424-82202022-08-012217635710.3390/s22176357Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation ForestYang Zuo0Florian Thiery1Praneeth Chandran2Johan Odelius3Matti Rantatalo4Division of Operation and Maintenance Engineering, Luleå University of Technology, 97187 Luleå, SwedenDivision of Operation and Maintenance Engineering, Luleå University of Technology, 97187 Luleå, SwedenDivision of Operation and Maintenance Engineering, Luleå University of Technology, 97187 Luleå, SwedenDivision of Operation and Maintenance Engineering, Luleå University of Technology, 97187 Luleå, SwedenDivision of Operation and Maintenance Engineering, Luleå University of Technology, 97187 Luleå, SwedenRailway switches and crossings (S&Cs) are critical, high-value assets in railway networks. A single failure of such an asset could result in severe network disturbance and considerable economical losses. Squats are common rail surface defects of S&Cs and need to be detected and estimated at an early stage to minimise maintenance costs and increase the reliability of S&Cs. For practicality, installation of wired or wireless sensors along the S&C may not be reliable due to the risk of damages of power and signal cables or sensors. To cope with these issues, this study presents a method for collecting and processing vibration data from an accelerometer installed at the point machine to extract features related to the squat defects of the S&C. An unsupervised anomaly-detection method using the isolation forest algorithm is applied to generate anomaly scores from the features. Important features are ranked and selected. This paper describes the procedure of parameter tuning and presents the achieved anomaly scores. The results show that the proposed method is effective and that the generated anomaly scores indicate the health status of an S&C regarding squat defects.https://www.mdpi.com/1424-8220/22/17/6357railway switch and crossingvibrationsquatanomaly detectionunsupervised machine learninganomaly score |
| spellingShingle | Yang Zuo Florian Thiery Praneeth Chandran Johan Odelius Matti Rantatalo Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest Sensors railway switch and crossing vibration squat anomaly detection unsupervised machine learning anomaly score |
| title | Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest |
| title_full | Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest |
| title_fullStr | Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest |
| title_full_unstemmed | Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest |
| title_short | Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest |
| title_sort | squat detection of railway switches and crossings using wavelets and isolation forest |
| topic | railway switch and crossing vibration squat anomaly detection unsupervised machine learning anomaly score |
| url | https://www.mdpi.com/1424-8220/22/17/6357 |
| work_keys_str_mv | AT yangzuo squatdetectionofrailwayswitchesandcrossingsusingwaveletsandisolationforest AT florianthiery squatdetectionofrailwayswitchesandcrossingsusingwaveletsandisolationforest AT praneethchandran squatdetectionofrailwayswitchesandcrossingsusingwaveletsandisolationforest AT johanodelius squatdetectionofrailwayswitchesandcrossingsusingwaveletsandisolationforest AT mattirantatalo squatdetectionofrailwayswitchesandcrossingsusingwaveletsandisolationforest |