Feature extraction for bearing fault diagnosis using composite multiscale entropy

Shuen De Wu, Chiu Wen Wu, Shiou Gwo Lin, Chun Chieh Wang, Kung Yen Lee

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

1 Citation (Scopus)

Abstract

Multiscale entropy (MSE) is a popular algorithm to measure the complexity of a time series for multiple scales. However, the conventional MSE algorithm yields imprecise estimation of entropy for a time series with large time scale factors. In this paper, a composite multiscale entropy (CMSE) method is proposed to overcome this drawback. In the CMSE algorithm, with scale factors of τ, we calculate the sample entropies (SampEns) of all coarse-grained series and then define the mean of τ SampEns as the entropy values. This proposed algorithm is then applied to two different kinds of simulated noise signals and a set of real vibration data. These results demonstrate that the proposed CMSE provides more precise entropy calculation than the convectional MSE. Furthermore, as a feature extractor for a bearing faulty signal, CMSE provides a higher distinguishability, compared with MSE.

Original languageEnglish
Title of host publication2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics
Subtitle of host publicationMechatronics for Human Wellbeing, AIM 2013
Pages1615-1618
Number of pages4
DOIs
Publication statusPublished - 2013 Sep 16
Event2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013 - Wollongong, NSW, Australia
Duration: 2013 Jul 92013 Jul 12

Publication series

Name2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013

Other

Other2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013
CountryAustralia
CityWollongong, NSW
Period13/7/913/7/12

Fingerprint

Bearings (structural)
Failure analysis
Feature extraction
Entropy
Composite materials
Time series

ASJC Scopus subject areas

  • Artificial Intelligence
  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Wu, S. D., Wu, C. W., Lin, S. G., Wang, C. C., & Lee, K. Y. (2013). Feature extraction for bearing fault diagnosis using composite multiscale entropy. In 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013 (pp. 1615-1618). [6584327] (2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013). https://doi.org/10.1109/AIM.2013.6584327

Feature extraction for bearing fault diagnosis using composite multiscale entropy. / Wu, Shuen De; Wu, Chiu Wen; Lin, Shiou Gwo; Wang, Chun Chieh; Lee, Kung Yen.

2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013. 2013. p. 1615-1618 6584327 (2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013).

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

Wu, SD, Wu, CW, Lin, SG, Wang, CC & Lee, KY 2013, Feature extraction for bearing fault diagnosis using composite multiscale entropy. in 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013., 6584327, 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013, pp. 1615-1618, 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013, Wollongong, NSW, Australia, 13/7/9. https://doi.org/10.1109/AIM.2013.6584327
Wu SD, Wu CW, Lin SG, Wang CC, Lee KY. Feature extraction for bearing fault diagnosis using composite multiscale entropy. In 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013. 2013. p. 1615-1618. 6584327. (2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013). https://doi.org/10.1109/AIM.2013.6584327
Wu, Shuen De ; Wu, Chiu Wen ; Lin, Shiou Gwo ; Wang, Chun Chieh ; Lee, Kung Yen. / Feature extraction for bearing fault diagnosis using composite multiscale entropy. 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013. 2013. pp. 1615-1618 (2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013).
@inproceedings{0187bfb55e8247b981f9074993dbc41a,
title = "Feature extraction for bearing fault diagnosis using composite multiscale entropy",
abstract = "Multiscale entropy (MSE) is a popular algorithm to measure the complexity of a time series for multiple scales. However, the conventional MSE algorithm yields imprecise estimation of entropy for a time series with large time scale factors. In this paper, a composite multiscale entropy (CMSE) method is proposed to overcome this drawback. In the CMSE algorithm, with scale factors of τ, we calculate the sample entropies (SampEns) of all coarse-grained series and then define the mean of τ SampEns as the entropy values. This proposed algorithm is then applied to two different kinds of simulated noise signals and a set of real vibration data. These results demonstrate that the proposed CMSE provides more precise entropy calculation than the convectional MSE. Furthermore, as a feature extractor for a bearing faulty signal, CMSE provides a higher distinguishability, compared with MSE.",
author = "Wu, {Shuen De} and Wu, {Chiu Wen} and Lin, {Shiou Gwo} and Wang, {Chun Chieh} and Lee, {Kung Yen}",
year = "2013",
month = "9",
day = "16",
doi = "10.1109/AIM.2013.6584327",
language = "English",
isbn = "9781467353199",
series = "2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013",
pages = "1615--1618",
booktitle = "2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics",

}

TY - GEN

T1 - Feature extraction for bearing fault diagnosis using composite multiscale entropy

AU - Wu, Shuen De

AU - Wu, Chiu Wen

AU - Lin, Shiou Gwo

AU - Wang, Chun Chieh

AU - Lee, Kung Yen

PY - 2013/9/16

Y1 - 2013/9/16

N2 - Multiscale entropy (MSE) is a popular algorithm to measure the complexity of a time series for multiple scales. However, the conventional MSE algorithm yields imprecise estimation of entropy for a time series with large time scale factors. In this paper, a composite multiscale entropy (CMSE) method is proposed to overcome this drawback. In the CMSE algorithm, with scale factors of τ, we calculate the sample entropies (SampEns) of all coarse-grained series and then define the mean of τ SampEns as the entropy values. This proposed algorithm is then applied to two different kinds of simulated noise signals and a set of real vibration data. These results demonstrate that the proposed CMSE provides more precise entropy calculation than the convectional MSE. Furthermore, as a feature extractor for a bearing faulty signal, CMSE provides a higher distinguishability, compared with MSE.

AB - Multiscale entropy (MSE) is a popular algorithm to measure the complexity of a time series for multiple scales. However, the conventional MSE algorithm yields imprecise estimation of entropy for a time series with large time scale factors. In this paper, a composite multiscale entropy (CMSE) method is proposed to overcome this drawback. In the CMSE algorithm, with scale factors of τ, we calculate the sample entropies (SampEns) of all coarse-grained series and then define the mean of τ SampEns as the entropy values. This proposed algorithm is then applied to two different kinds of simulated noise signals and a set of real vibration data. These results demonstrate that the proposed CMSE provides more precise entropy calculation than the convectional MSE. Furthermore, as a feature extractor for a bearing faulty signal, CMSE provides a higher distinguishability, compared with MSE.

UR - http://www.scopus.com/inward/record.url?scp=84883720164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883720164&partnerID=8YFLogxK

U2 - 10.1109/AIM.2013.6584327

DO - 10.1109/AIM.2013.6584327

M3 - Conference contribution

AN - SCOPUS:84883720164

SN - 9781467353199

T3 - 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics: Mechatronics for Human Wellbeing, AIM 2013

SP - 1615

EP - 1618

BT - 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics

ER -