Classification of impact signals from insulated rail joints using spectral analysis

Andrew Yuen, Dingyang Zheng, Peter Mutton, Wenyi Yan

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

Abstract

Insulated Rail Joints (IRJs) are a railway track component that generates impact noise and requires close maintenance. Instrumented Revenue Vehicles (IRVs) developed by the Institute of Railway Technology at Monash University measure the interaction between the vehicle and track. Impact signals were measured and post-processed from vibration sensors located on the side-frame at IRJ locations. Wavelet analysis was used to interrogate the non-stationary impact signals. Wavelet energy was used as the wavelet feature extraction techniques in the frequency domain. The wavelet energy impact signatures were clustered using multi-signal discrete wavelet transform clustering. These clusters classified the empty and loaded conditions of the wagon from the vibration response. Frequency identifications were created from the clustering and the severity of the impacts in the frequency domain could be determined from the cluster numbers.

Original languageEnglish
Title of host publicationNotes on Numerical Fluid Mechanics and Multidisciplinary Design
Place of PublicationCham Switzerland
PublisherSpringer
Pages771-780
Number of pages10
DOIs
Publication statusPublished - 1 Jan 2018
EventInternational Workshop on Railway Noise (IWRN) 2016 - Terrigal, Australia
Duration: 12 Sep 201616 Sep 2016
Conference number: 12th

Publication series

NameNotes on Numerical Fluid Mechanics and Multidisciplinary Design
Volume139
ISSN (Print)1612-2909

Conference

ConferenceInternational Workshop on Railway Noise (IWRN) 2016
Abbreviated titleIWRN 2016
CountryAustralia
CityTerrigal
Period12/09/1616/09/16

Cite this

Yuen, A., Zheng, D., Mutton, P., & Yan, W. (2018). Classification of impact signals from insulated rail joints using spectral analysis. In Notes on Numerical Fluid Mechanics and Multidisciplinary Design (pp. 771-780). (Notes on Numerical Fluid Mechanics and Multidisciplinary Design; Vol. 139). Cham Switzerland: Springer. https://doi.org/10.1007/978-3-319-73411-8_61
Yuen, Andrew ; Zheng, Dingyang ; Mutton, Peter ; Yan, Wenyi. / Classification of impact signals from insulated rail joints using spectral analysis. Notes on Numerical Fluid Mechanics and Multidisciplinary Design. Cham Switzerland : Springer, 2018. pp. 771-780 (Notes on Numerical Fluid Mechanics and Multidisciplinary Design).
@inproceedings{bbe29589a6ed4ba0b38625ea6b415507,
title = "Classification of impact signals from insulated rail joints using spectral analysis",
abstract = "Insulated Rail Joints (IRJs) are a railway track component that generates impact noise and requires close maintenance. Instrumented Revenue Vehicles (IRVs) developed by the Institute of Railway Technology at Monash University measure the interaction between the vehicle and track. Impact signals were measured and post-processed from vibration sensors located on the side-frame at IRJ locations. Wavelet analysis was used to interrogate the non-stationary impact signals. Wavelet energy was used as the wavelet feature extraction techniques in the frequency domain. The wavelet energy impact signatures were clustered using multi-signal discrete wavelet transform clustering. These clusters classified the empty and loaded conditions of the wagon from the vibration response. Frequency identifications were created from the clustering and the severity of the impacts in the frequency domain could be determined from the cluster numbers.",
author = "Andrew Yuen and Dingyang Zheng and Peter Mutton and Wenyi Yan",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-73411-8_61",
language = "English",
series = "Notes on Numerical Fluid Mechanics and Multidisciplinary Design",
publisher = "Springer",
pages = "771--780",
booktitle = "Notes on Numerical Fluid Mechanics and Multidisciplinary Design",

}

Yuen, A, Zheng, D, Mutton, P & Yan, W 2018, Classification of impact signals from insulated rail joints using spectral analysis. in Notes on Numerical Fluid Mechanics and Multidisciplinary Design. Notes on Numerical Fluid Mechanics and Multidisciplinary Design, vol. 139, Springer, Cham Switzerland, pp. 771-780, International Workshop on Railway Noise (IWRN) 2016, Terrigal, Australia, 12/09/16. https://doi.org/10.1007/978-3-319-73411-8_61

Classification of impact signals from insulated rail joints using spectral analysis. / Yuen, Andrew; Zheng, Dingyang; Mutton, Peter; Yan, Wenyi.

Notes on Numerical Fluid Mechanics and Multidisciplinary Design. Cham Switzerland : Springer, 2018. p. 771-780 (Notes on Numerical Fluid Mechanics and Multidisciplinary Design; Vol. 139).

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

TY - GEN

T1 - Classification of impact signals from insulated rail joints using spectral analysis

AU - Yuen, Andrew

AU - Zheng, Dingyang

AU - Mutton, Peter

AU - Yan, Wenyi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Insulated Rail Joints (IRJs) are a railway track component that generates impact noise and requires close maintenance. Instrumented Revenue Vehicles (IRVs) developed by the Institute of Railway Technology at Monash University measure the interaction between the vehicle and track. Impact signals were measured and post-processed from vibration sensors located on the side-frame at IRJ locations. Wavelet analysis was used to interrogate the non-stationary impact signals. Wavelet energy was used as the wavelet feature extraction techniques in the frequency domain. The wavelet energy impact signatures were clustered using multi-signal discrete wavelet transform clustering. These clusters classified the empty and loaded conditions of the wagon from the vibration response. Frequency identifications were created from the clustering and the severity of the impacts in the frequency domain could be determined from the cluster numbers.

AB - Insulated Rail Joints (IRJs) are a railway track component that generates impact noise and requires close maintenance. Instrumented Revenue Vehicles (IRVs) developed by the Institute of Railway Technology at Monash University measure the interaction between the vehicle and track. Impact signals were measured and post-processed from vibration sensors located on the side-frame at IRJ locations. Wavelet analysis was used to interrogate the non-stationary impact signals. Wavelet energy was used as the wavelet feature extraction techniques in the frequency domain. The wavelet energy impact signatures were clustered using multi-signal discrete wavelet transform clustering. These clusters classified the empty and loaded conditions of the wagon from the vibration response. Frequency identifications were created from the clustering and the severity of the impacts in the frequency domain could be determined from the cluster numbers.

UR - http://www.scopus.com/inward/record.url?scp=85047433374&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-73411-8_61

DO - 10.1007/978-3-319-73411-8_61

M3 - Conference Paper

T3 - Notes on Numerical Fluid Mechanics and Multidisciplinary Design

SP - 771

EP - 780

BT - Notes on Numerical Fluid Mechanics and Multidisciplinary Design

PB - Springer

CY - Cham Switzerland

ER -

Yuen A, Zheng D, Mutton P, Yan W. Classification of impact signals from insulated rail joints using spectral analysis. In Notes on Numerical Fluid Mechanics and Multidisciplinary Design. Cham Switzerland: Springer. 2018. p. 771-780. (Notes on Numerical Fluid Mechanics and Multidisciplinary Design). https://doi.org/10.1007/978-3-319-73411-8_61