Feature Extraction for Track Section Status Classification Based on UGW Signals

Track status classification is essential for the stability and safety of railway operations nowadays, when railway networks are becoming more and more complex and broad. In this situation, monitoring systems are already a key element in applications dedicated to evaluating the status of a certain tr...

Full description

Bibliographic Details
Main Authors: Lei Yuan, Yuan Yang, Álvaro Hernández, Lin Shi
Format: Article
Language:English
Published: MDPI AG 2018-04-01
Series:Sensors
Subjects:
Online Access:http://www.mdpi.com/1424-8220/18/4/1225
id doaj-a1a8f7782d1d46ad9d70f7264c1f168b
record_format Article
spelling doaj-a1a8f7782d1d46ad9d70f7264c1f168b2020-11-25T02:27:32ZengMDPI AGSensors1424-82202018-04-01184122510.3390/s18041225s18041225Feature Extraction for Track Section Status Classification Based on UGW SignalsLei Yuan0Yuan Yang1Álvaro Hernández2Lin Shi3Electronics Department, Xi’an University of Technology, Xi’an 710048, ChinaElectronics Department, Xi’an University of Technology, Xi’an 710048, ChinaElectronics Department, University of Alcala, Alcalá de Henares, Madrid 28805, SpainElectronics Department, Xi’an University of Technology, Xi’an 710048, ChinaTrack status classification is essential for the stability and safety of railway operations nowadays, when railway networks are becoming more and more complex and broad. In this situation, monitoring systems are already a key element in applications dedicated to evaluating the status of a certain track section, often determining whether it is free or occupied by a train. Different technologies have already been involved in the design of monitoring systems, including ultrasonic guided waves (UGW). This work proposes the use of the UGW signals captured by a track monitoring system to extract the features that are relevant for determining the corresponding track section status. For that purpose, three features of UGW signals have been considered: the root mean square value, the energy, and the main frequency components. Experimental results successfully validated how these features can be used to classify the track section status into free, occupied and broken. Furthermore, spatial and temporal dependencies among these features were analysed in order to show how they can improve the final classification performance. Finally, a preliminary high-level classification system based on deep learning networks has been envisaged for future works.http://www.mdpi.com/1424-8220/18/4/1225track status classificationultrasonic guided wave (UGW)feature extractiontemporal and spatial dependenciesdeep learning algorithm
collection DOAJ
language English
format Article
sources DOAJ
author Lei Yuan
Yuan Yang
Álvaro Hernández
Lin Shi
spellingShingle Lei Yuan
Yuan Yang
Álvaro Hernández
Lin Shi
Feature Extraction for Track Section Status Classification Based on UGW Signals
Sensors
track status classification
ultrasonic guided wave (UGW)
feature extraction
temporal and spatial dependencies
deep learning algorithm
author_facet Lei Yuan
Yuan Yang
Álvaro Hernández
Lin Shi
author_sort Lei Yuan
title Feature Extraction for Track Section Status Classification Based on UGW Signals
title_short Feature Extraction for Track Section Status Classification Based on UGW Signals
title_full Feature Extraction for Track Section Status Classification Based on UGW Signals
title_fullStr Feature Extraction for Track Section Status Classification Based on UGW Signals
title_full_unstemmed Feature Extraction for Track Section Status Classification Based on UGW Signals
title_sort feature extraction for track section status classification based on ugw signals
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2018-04-01
description Track status classification is essential for the stability and safety of railway operations nowadays, when railway networks are becoming more and more complex and broad. In this situation, monitoring systems are already a key element in applications dedicated to evaluating the status of a certain track section, often determining whether it is free or occupied by a train. Different technologies have already been involved in the design of monitoring systems, including ultrasonic guided waves (UGW). This work proposes the use of the UGW signals captured by a track monitoring system to extract the features that are relevant for determining the corresponding track section status. For that purpose, three features of UGW signals have been considered: the root mean square value, the energy, and the main frequency components. Experimental results successfully validated how these features can be used to classify the track section status into free, occupied and broken. Furthermore, spatial and temporal dependencies among these features were analysed in order to show how they can improve the final classification performance. Finally, a preliminary high-level classification system based on deep learning networks has been envisaged for future works.
topic track status classification
ultrasonic guided wave (UGW)
feature extraction
temporal and spatial dependencies
deep learning algorithm
url http://www.mdpi.com/1424-8220/18/4/1225
work_keys_str_mv AT leiyuan featureextractionfortracksectionstatusclassificationbasedonugwsignals
AT yuanyang featureextractionfortracksectionstatusclassificationbasedonugwsignals
AT alvarohernandez featureextractionfortracksectionstatusclassificationbasedonugwsignals
AT linshi featureextractionfortracksectionstatusclassificationbasedonugwsignals
_version_ 1724842520466161664