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

S. Moustakidis*, V. Kappatos, P. Karlsson, C. Selcuk, K. Hrissagis, T. H. Gan

*Kontaktforfatter for dette arbejde

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Resumé

This paper presents an automated long range ultrasonic (LRU) flaw detection system based on an effective pattern recognition approach. The method comprises three stages: 1) multiple feature extraction techniques were applied for better representation of the signals in time and frequency domain, 2) feature selection was employed next for feature ranking, according to discrimination power, and finally 3) the classification task was accomplished by means of a kernel-based support vector machine (SVM). For the training and validation of the algorithm, an extensive experimental investigation was carried out on the foot section of a 4.30m long rail (CEN 56). Different depths of transversal slots have been induced in the foot at 3m from the excitation point. The results show that the proposed method is able to effectively detect flaws.

OriginalsprogEngelsk
TitelComputers in Railways XIII
ForlagWIT Press
Publikationsdato2012
Sider199-210
DOI
StatusUdgivet - 2012
Udgivet eksterntJa
NavnW I T Transactions on the Built Environment
Vol/bind127
ISSN1746-4498

Fingeraftryk

Support vector machines
Rails
Feature extraction
Ultrasonics
Defects
Pattern recognition

Citer dette

Moustakidis, S., Kappatos, V., Karlsson, P., Selcuk, C., Hrissagis, K., & Gan, T. H. (2012). An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm. I Computers in Railways XIII (s. 199-210). WIT Press. W I T Transactions on the Built Environment, Bind. 127 https://doi.org/10.2495/CR120181
Moustakidis, S. ; Kappatos, V. ; Karlsson, P. ; Selcuk, C. ; Hrissagis, K. ; Gan, T. H. / An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm. Computers in Railways XIII. WIT Press, 2012. s. 199-210 (W I T Transactions on the Built Environment, Bind 127).
@inproceedings{dbc3708322cd47d69aef293be55c3744,
title = "An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm",
abstract = "This paper presents an automated long range ultrasonic (LRU) flaw detection system based on an effective pattern recognition approach. The method comprises three stages: 1) multiple feature extraction techniques were applied for better representation of the signals in time and frequency domain, 2) feature selection was employed next for feature ranking, according to discrimination power, and finally 3) the classification task was accomplished by means of a kernel-based support vector machine (SVM). For the training and validation of the algorithm, an extensive experimental investigation was carried out on the foot section of a 4.30m long rail (CEN 56). Different depths of transversal slots have been induced in the foot at 3m from the excitation point. The results show that the proposed method is able to effectively detect flaws.",
keywords = "Detection, Flaw, Long range ultrasonic, Support vector machine",
author = "S. Moustakidis and V. Kappatos and P. Karlsson and C. Selcuk and K. Hrissagis and Gan, {T. H.}",
year = "2012",
doi = "10.2495/CR120181",
language = "English",
series = "W I T Transactions on the Built Environment",
publisher = "WIT Press",
pages = "199--210",
booktitle = "Computers in Railways XIII",

}

Moustakidis, S, Kappatos, V, Karlsson, P, Selcuk, C, Hrissagis, K & Gan, TH 2012, An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm. i Computers in Railways XIII. WIT Press, W I T Transactions on the Built Environment, bind 127, s. 199-210. https://doi.org/10.2495/CR120181

An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm. / Moustakidis, S.; Kappatos, V.; Karlsson, P.; Selcuk, C.; Hrissagis, K.; Gan, T. H.

Computers in Railways XIII. WIT Press, 2012. s. 199-210 (W I T Transactions on the Built Environment, Bind 127).

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

TY - GEN

T1 - An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm

AU - Moustakidis, S.

AU - Kappatos, V.

AU - Karlsson, P.

AU - Selcuk, C.

AU - Hrissagis, K.

AU - Gan, T. H.

PY - 2012

Y1 - 2012

N2 - This paper presents an automated long range ultrasonic (LRU) flaw detection system based on an effective pattern recognition approach. The method comprises three stages: 1) multiple feature extraction techniques were applied for better representation of the signals in time and frequency domain, 2) feature selection was employed next for feature ranking, according to discrimination power, and finally 3) the classification task was accomplished by means of a kernel-based support vector machine (SVM). For the training and validation of the algorithm, an extensive experimental investigation was carried out on the foot section of a 4.30m long rail (CEN 56). Different depths of transversal slots have been induced in the foot at 3m from the excitation point. The results show that the proposed method is able to effectively detect flaws.

AB - This paper presents an automated long range ultrasonic (LRU) flaw detection system based on an effective pattern recognition approach. The method comprises three stages: 1) multiple feature extraction techniques were applied for better representation of the signals in time and frequency domain, 2) feature selection was employed next for feature ranking, according to discrimination power, and finally 3) the classification task was accomplished by means of a kernel-based support vector machine (SVM). For the training and validation of the algorithm, an extensive experimental investigation was carried out on the foot section of a 4.30m long rail (CEN 56). Different depths of transversal slots have been induced in the foot at 3m from the excitation point. The results show that the proposed method is able to effectively detect flaws.

KW - Detection

KW - Flaw

KW - Long range ultrasonic

KW - Support vector machine

U2 - 10.2495/CR120181

DO - 10.2495/CR120181

M3 - Article in proceedings

AN - SCOPUS:84870591776

T3 - W I T Transactions on the Built Environment

SP - 199

EP - 210

BT - Computers in Railways XIII

PB - WIT Press

ER -

Moustakidis S, Kappatos V, Karlsson P, Selcuk C, Hrissagis K, Gan TH. An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm. I Computers in Railways XIII. WIT Press. 2012. s. 199-210. (W I T Transactions on the Built Environment, Bind 127). https://doi.org/10.2495/CR120181