Track-monitoring from the dynamic response of an operational train

George Lederman, Siheng Chen, James Garrett, Jelena Kovacevic, Hae Young Noh, Jacobo Bielak

Research output: Contribution to journalArticle

Abstract

We explore a data-driven approach for monitoring rail infrastructure from the dynamic response of a train in revenue-service. Presently, track inspection is performed either visually or with dedicated track geometry cars. In this study, we examine a more economical approach where track inspection is performed by analyzing vibration data collected from an operational passenger train. The high frequency with which passenger trains travel each section of track means that faults can be detected sooner than with dedicated inspection vehicles, and the large number of passes over each section of track makes a data-driven approach statistically feasible. We have deployed a test-system on a light-rail vehicle and have been collecting data for the past two years. The collected data underscores two of the main challenges that arise in train-based track monitoring: the speed of the train at a given location varies from pass to pass and the position of the train is not known precisely. In this study, we explore which feature representations of the data best characterize the state of the tracks despite these sources of uncertainty (i.e., in the spatial domain or frequency domain), and we examine how consistently change detection approaches can identify track changes from the data. We show the accuracy of these different representations, or features, and different change detection approaches on two types of track changes, track replacement and tamping (a maintenance procedure to improve track geometry), and two types of data, simulated data and operational data from our test-system. The sensing, signal processing, and data analysis we propose in the study could facilitate safer trains and more cost-efficient maintenance in the future. Moreover, the proposed approach is quite general and could be extended to other parts of the infrastructure, including bridges.

Original languageEnglish (US)
Pages (from-to)1-16
Number of pages16
JournalMechanical Systems and Signal Processing
Volume87
DOIs
StatePublished - Mar 15 2017

Fingerprint

Dynamic response
Inspection
Rails
Monitoring
Railroad tracks
Geometry
Signal processing
Railroad cars
Costs
Uncertainty

Keywords

  • Change detection
  • Data acquisition
  • Position uncertainty
  • Rail maintenance
  • Signal processing
  • Vehicle-based inspection

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Civil and Structural Engineering
  • Aerospace Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

Track-monitoring from the dynamic response of an operational train. / Lederman, George; Chen, Siheng; Garrett, James; Kovacevic, Jelena; Noh, Hae Young; Bielak, Jacobo.

In: Mechanical Systems and Signal Processing, Vol. 87, 15.03.2017, p. 1-16.

Research output: Contribution to journalArticle

Lederman, George ; Chen, Siheng ; Garrett, James ; Kovacevic, Jelena ; Noh, Hae Young ; Bielak, Jacobo. / Track-monitoring from the dynamic response of an operational train. In: Mechanical Systems and Signal Processing. 2017 ; Vol. 87. pp. 1-16.
@article{535cf060352040ad82af18928a461a73,
title = "Track-monitoring from the dynamic response of an operational train",
abstract = "We explore a data-driven approach for monitoring rail infrastructure from the dynamic response of a train in revenue-service. Presently, track inspection is performed either visually or with dedicated track geometry cars. In this study, we examine a more economical approach where track inspection is performed by analyzing vibration data collected from an operational passenger train. The high frequency with which passenger trains travel each section of track means that faults can be detected sooner than with dedicated inspection vehicles, and the large number of passes over each section of track makes a data-driven approach statistically feasible. We have deployed a test-system on a light-rail vehicle and have been collecting data for the past two years. The collected data underscores two of the main challenges that arise in train-based track monitoring: the speed of the train at a given location varies from pass to pass and the position of the train is not known precisely. In this study, we explore which feature representations of the data best characterize the state of the tracks despite these sources of uncertainty (i.e., in the spatial domain or frequency domain), and we examine how consistently change detection approaches can identify track changes from the data. We show the accuracy of these different representations, or features, and different change detection approaches on two types of track changes, track replacement and tamping (a maintenance procedure to improve track geometry), and two types of data, simulated data and operational data from our test-system. The sensing, signal processing, and data analysis we propose in the study could facilitate safer trains and more cost-efficient maintenance in the future. Moreover, the proposed approach is quite general and could be extended to other parts of the infrastructure, including bridges.",
keywords = "Change detection, Data acquisition, Position uncertainty, Rail maintenance, Signal processing, Vehicle-based inspection",
author = "George Lederman and Siheng Chen and James Garrett and Jelena Kovacevic and Noh, {Hae Young} and Jacobo Bielak",
year = "2017",
month = "3",
day = "15",
doi = "10.1016/j.ymssp.2016.06.041",
language = "English (US)",
volume = "87",
pages = "1--16",
journal = "Mechanical Systems and Signal Processing",
issn = "0888-3270",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Track-monitoring from the dynamic response of an operational train

AU - Lederman, George

AU - Chen, Siheng

AU - Garrett, James

AU - Kovacevic, Jelena

AU - Noh, Hae Young

AU - Bielak, Jacobo

PY - 2017/3/15

Y1 - 2017/3/15

N2 - We explore a data-driven approach for monitoring rail infrastructure from the dynamic response of a train in revenue-service. Presently, track inspection is performed either visually or with dedicated track geometry cars. In this study, we examine a more economical approach where track inspection is performed by analyzing vibration data collected from an operational passenger train. The high frequency with which passenger trains travel each section of track means that faults can be detected sooner than with dedicated inspection vehicles, and the large number of passes over each section of track makes a data-driven approach statistically feasible. We have deployed a test-system on a light-rail vehicle and have been collecting data for the past two years. The collected data underscores two of the main challenges that arise in train-based track monitoring: the speed of the train at a given location varies from pass to pass and the position of the train is not known precisely. In this study, we explore which feature representations of the data best characterize the state of the tracks despite these sources of uncertainty (i.e., in the spatial domain or frequency domain), and we examine how consistently change detection approaches can identify track changes from the data. We show the accuracy of these different representations, or features, and different change detection approaches on two types of track changes, track replacement and tamping (a maintenance procedure to improve track geometry), and two types of data, simulated data and operational data from our test-system. The sensing, signal processing, and data analysis we propose in the study could facilitate safer trains and more cost-efficient maintenance in the future. Moreover, the proposed approach is quite general and could be extended to other parts of the infrastructure, including bridges.

AB - We explore a data-driven approach for monitoring rail infrastructure from the dynamic response of a train in revenue-service. Presently, track inspection is performed either visually or with dedicated track geometry cars. In this study, we examine a more economical approach where track inspection is performed by analyzing vibration data collected from an operational passenger train. The high frequency with which passenger trains travel each section of track means that faults can be detected sooner than with dedicated inspection vehicles, and the large number of passes over each section of track makes a data-driven approach statistically feasible. We have deployed a test-system on a light-rail vehicle and have been collecting data for the past two years. The collected data underscores two of the main challenges that arise in train-based track monitoring: the speed of the train at a given location varies from pass to pass and the position of the train is not known precisely. In this study, we explore which feature representations of the data best characterize the state of the tracks despite these sources of uncertainty (i.e., in the spatial domain or frequency domain), and we examine how consistently change detection approaches can identify track changes from the data. We show the accuracy of these different representations, or features, and different change detection approaches on two types of track changes, track replacement and tamping (a maintenance procedure to improve track geometry), and two types of data, simulated data and operational data from our test-system. The sensing, signal processing, and data analysis we propose in the study could facilitate safer trains and more cost-efficient maintenance in the future. Moreover, the proposed approach is quite general and could be extended to other parts of the infrastructure, including bridges.

KW - Change detection

KW - Data acquisition

KW - Position uncertainty

KW - Rail maintenance

KW - Signal processing

KW - Vehicle-based inspection

UR - http://www.scopus.com/inward/record.url?scp=84996995607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996995607&partnerID=8YFLogxK

U2 - 10.1016/j.ymssp.2016.06.041

DO - 10.1016/j.ymssp.2016.06.041

M3 - Article

VL - 87

SP - 1

EP - 16

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

SN - 0888-3270

ER -