Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals

Mingjian Sun; Yan Wang; Xin Zhang; Yipeng Liu; Qiang Wei; Yi Shen; Naizhang Feng

doi:10.1109/I2MTC.2014.6860857

Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals

Mingjian Sun
, Yan Wang
, Xin Zhang
, Yipeng Liu
, Qiang Wei
, Yi Shen
, Naizhang Feng^*

^*Corresponding author for this work

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

Many rail accidents were caused by rail defects, therefore the detection of the rail defects is of vital importance. Using simulated and experimental measurements, the rail defect detection was carried out. The feature parameters were extracted both from time domain and time-frequency domain. Then the sequential backward selection method was applied to select the important feature parameters. After optimizing of the feature parameter set, support vector machine method was applied to recognize and classify the rail defects. It has been proved that the proposed algorithm of analyzing and processing the rail defect vibration signals is an effective and non-destructive detecting method of the rail defects.

Original language	English
Title of host publication	2014 IEEE International Instrumentation and Measurement Technology Conference
Subtitle of host publication	Instrumentation and Measurement for Sustainable Development, I2MTC 2014 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	819-823
Number of pages	5
ISBN (Print)	9781467363853
DOIs	https://doi.org/10.1109/I2MTC.2014.6860857
State	Published - 2014
Event	2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014 - Montevideo, Uruguay Duration: 12 May 2014 → 15 May 2014

Publication series

Name	Conference Record - IEEE Instrumentation and Measurement Technology Conference
ISSN (Print)	1091-5281

Conference

Conference	2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014
Country/Territory	Uruguay
City	Montevideo
Period	12/05/14 → 15/05/14

Keywords

feature selection and classification
high-speed rail defect
non-destructive detecting
support vector machine
vibration signals

Access to Document

10.1109/I2MTC.2014.6860857

Cite this

Sun, M., Wang, Y., Zhang, X., Liu, Y., Wei, Q., Shen, Y., & Feng, N. (2014). Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals. In 2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014 - Proceedings (pp. 819-823). Article 6860857 (Conference Record - IEEE Instrumentation and Measurement Technology Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/I2MTC.2014.6860857

Sun, Mingjian ; Wang, Yan ; Zhang, Xin et al. / Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals. 2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 819-823 (Conference Record - IEEE Instrumentation and Measurement Technology Conference).

@inproceedings{fd36e68c19ee4a55b77703dbb5cbfb72,

title = "Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals",

abstract = "Many rail accidents were caused by rail defects, therefore the detection of the rail defects is of vital importance. Using simulated and experimental measurements, the rail defect detection was carried out. The feature parameters were extracted both from time domain and time-frequency domain. Then the sequential backward selection method was applied to select the important feature parameters. After optimizing of the feature parameter set, support vector machine method was applied to recognize and classify the rail defects. It has been proved that the proposed algorithm of analyzing and processing the rail defect vibration signals is an effective and non-destructive detecting method of the rail defects.",

keywords = "feature selection and classification, high-speed rail defect, non-destructive detecting, support vector machine, vibration signals",

author = "Mingjian Sun and Yan Wang and Xin Zhang and Yipeng Liu and Qiang Wei and Yi Shen and Naizhang Feng",

year = "2014",

doi = "10.1109/I2MTC.2014.6860857",

language = "英语",

isbn = "9781467363853",

series = "Conference Record - IEEE Instrumentation and Measurement Technology Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "819--823",

booktitle = "2014 IEEE International Instrumentation and Measurement Technology Conference",

address = "美国",

note = "2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014 ; Conference date: 12-05-2014 Through 15-05-2014",

}

Sun, M , Wang, Y , Zhang, X, Liu, Y, Wei, Q, Shen, Y & Feng, N 2014, Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals. in 2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014 - Proceedings., 6860857, Conference Record - IEEE Instrumentation and Measurement Technology Conference, Institute of Electrical and Electronics Engineers Inc., pp. 819-823, 2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014, Montevideo, Uruguay, 12/05/14. https://doi.org/10.1109/I2MTC.2014.6860857

Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals. / Sun, Mingjian ; Wang, Yan ; Zhang, Xin et al.
2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. p. 819-823 6860857 (Conference Record - IEEE Instrumentation and Measurement Technology Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals

AU - Sun, Mingjian

AU - Wang, Yan

AU - Zhang, Xin

AU - Liu, Yipeng

AU - Wei, Qiang

AU - Shen, Yi

AU - Feng, Naizhang

PY - 2014

Y1 - 2014

N2 - Many rail accidents were caused by rail defects, therefore the detection of the rail defects is of vital importance. Using simulated and experimental measurements, the rail defect detection was carried out. The feature parameters were extracted both from time domain and time-frequency domain. Then the sequential backward selection method was applied to select the important feature parameters. After optimizing of the feature parameter set, support vector machine method was applied to recognize and classify the rail defects. It has been proved that the proposed algorithm of analyzing and processing the rail defect vibration signals is an effective and non-destructive detecting method of the rail defects.

AB - Many rail accidents were caused by rail defects, therefore the detection of the rail defects is of vital importance. Using simulated and experimental measurements, the rail defect detection was carried out. The feature parameters were extracted both from time domain and time-frequency domain. Then the sequential backward selection method was applied to select the important feature parameters. After optimizing of the feature parameter set, support vector machine method was applied to recognize and classify the rail defects. It has been proved that the proposed algorithm of analyzing and processing the rail defect vibration signals is an effective and non-destructive detecting method of the rail defects.

KW - feature selection and classification

KW - high-speed rail defect

KW - non-destructive detecting

KW - support vector machine

KW - vibration signals

UR - https://www.scopus.com/pages/publications/84905674452

U2 - 10.1109/I2MTC.2014.6860857

DO - 10.1109/I2MTC.2014.6860857

M3 - 会议稿件

AN - SCOPUS:84905674452

SN - 9781467363853

T3 - Conference Record - IEEE Instrumentation and Measurement Technology Conference

SP - 819

EP - 823

BT - 2014 IEEE International Instrumentation and Measurement Technology Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014

Y2 - 12 May 2014 through 15 May 2014

ER -

Sun M , Wang Y , Zhang X, Liu Y, Wei Q, Shen Y et al. Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals. In 2014 IEEE International Instrumentation and Measurement Technology Conference: Instrumentation and Measurement for Sustainable Development, I2MTC 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 819-823. 6860857. (Conference Record - IEEE Instrumentation and Measurement Technology Conference). doi: 10.1109/I2MTC.2014.6860857

Feature selection and classification algorithm for non-destructive detecting of high-speed rail defects based on vibration signals

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this