Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering

M. Farajzadeh-Zanjani, R. Razavi-Far, M. Saif, J. Zarei, Vasile Palade

Research output: Contribution to conferencePaper

14 Citations (Scopus)

Abstract

In this paper, a supervised fuzzy-neighborhood density-based clustering approach is proposed for the fault diagnosis of induction motors' bearings. The proposed approach makes use of the labeled data regarding the actual classes of faulty and fault-free cases, in order to train the fuzzy-neighborhood density-based clustering algorithm in a supervised manner, by resorting to an invasive weed optimization algorithm that aims to minimize an error-based objective function. The proposed classifier can properly classify multi-class data with complex and variously shaped decision boundaries among the different classes of faults and the fault-free state, and is robust against noise. This is due mainly to the fact that the classifier is constructed using the fuzzy-neighborhood density based clustering method, which is not sensitive to the geometrical shape of clusters in the feature space.
Original languageEnglish
Pages935 - 940
DOIs
Publication statusPublished - 2015
Event2015 IEEE 14th International Conference on Machine Learning and Applications - Miami, United States
Duration: 9 Dec 201511 Dec 2015

Conference

Conference2015 IEEE 14th International Conference on Machine Learning and Applications
Abbreviated titleICMLA
CountryUnited States
CityMiami
Period9/12/1511/12/15

Fingerprint

Bearings (structural)
Induction motors
Classifiers
Defects
Clustering algorithms
Failure analysis

Bibliographical note

© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

  • bearing defects
  • fault diagnosis
  • fuzzy-neighborhood density-based clustering
  • induction motors

Cite this

Farajzadeh-Zanjani, M., Razavi-Far, R., Saif, M., Zarei, J., & Palade, V. (2015). Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering. 935 - 940. Paper presented at 2015 IEEE 14th International Conference on Machine Learning and Applications, Miami, United States. https://doi.org/10.1109/ICMLA.2015.114

Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering. / Farajzadeh-Zanjani, M.; Razavi-Far, R.; Saif, M.; Zarei, J.; Palade, Vasile.

2015. 935 - 940 Paper presented at 2015 IEEE 14th International Conference on Machine Learning and Applications, Miami, United States.

Research output: Contribution to conferencePaper

Farajzadeh-Zanjani, M, Razavi-Far, R, Saif, M, Zarei, J & Palade, V 2015, 'Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering' Paper presented at 2015 IEEE 14th International Conference on Machine Learning and Applications, Miami, United States, 9/12/15 - 11/12/15, pp. 935 - 940. https://doi.org/10.1109/ICMLA.2015.114
Farajzadeh-Zanjani M, Razavi-Far R, Saif M, Zarei J, Palade V. Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering. 2015. Paper presented at 2015 IEEE 14th International Conference on Machine Learning and Applications, Miami, United States. https://doi.org/10.1109/ICMLA.2015.114
Farajzadeh-Zanjani, M. ; Razavi-Far, R. ; Saif, M. ; Zarei, J. ; Palade, Vasile. / Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering. Paper presented at 2015 IEEE 14th International Conference on Machine Learning and Applications, Miami, United States.
@conference{4e1ccf243a8e41549429aca86a23ea40,
title = "Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering",
abstract = "In this paper, a supervised fuzzy-neighborhood density-based clustering approach is proposed for the fault diagnosis of induction motors' bearings. The proposed approach makes use of the labeled data regarding the actual classes of faulty and fault-free cases, in order to train the fuzzy-neighborhood density-based clustering algorithm in a supervised manner, by resorting to an invasive weed optimization algorithm that aims to minimize an error-based objective function. The proposed classifier can properly classify multi-class data with complex and variously shaped decision boundaries among the different classes of faults and the fault-free state, and is robust against noise. This is due mainly to the fact that the classifier is constructed using the fuzzy-neighborhood density based clustering method, which is not sensitive to the geometrical shape of clusters in the feature space.",
keywords = "bearing defects, fault diagnosis, fuzzy-neighborhood density-based clustering, induction motors",
author = "M. Farajzadeh-Zanjani and R. Razavi-Far and M. Saif and J. Zarei and Vasile Palade",
note = "{\circledC} 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA ; Conference date: 09-12-2015 Through 11-12-2015",
year = "2015",
doi = "10.1109/ICMLA.2015.114",
language = "English",
pages = "935 -- 940",

}

TY - CONF

T1 - Diagnosis of bearing defects in induction motors by fuzzy-neighborhood density-based clustering

AU - Farajzadeh-Zanjani, M.

AU - Razavi-Far, R.

AU - Saif, M.

AU - Zarei, J.

AU - Palade, Vasile

N1 - © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2015

Y1 - 2015

N2 - In this paper, a supervised fuzzy-neighborhood density-based clustering approach is proposed for the fault diagnosis of induction motors' bearings. The proposed approach makes use of the labeled data regarding the actual classes of faulty and fault-free cases, in order to train the fuzzy-neighborhood density-based clustering algorithm in a supervised manner, by resorting to an invasive weed optimization algorithm that aims to minimize an error-based objective function. The proposed classifier can properly classify multi-class data with complex and variously shaped decision boundaries among the different classes of faults and the fault-free state, and is robust against noise. This is due mainly to the fact that the classifier is constructed using the fuzzy-neighborhood density based clustering method, which is not sensitive to the geometrical shape of clusters in the feature space.

AB - In this paper, a supervised fuzzy-neighborhood density-based clustering approach is proposed for the fault diagnosis of induction motors' bearings. The proposed approach makes use of the labeled data regarding the actual classes of faulty and fault-free cases, in order to train the fuzzy-neighborhood density-based clustering algorithm in a supervised manner, by resorting to an invasive weed optimization algorithm that aims to minimize an error-based objective function. The proposed classifier can properly classify multi-class data with complex and variously shaped decision boundaries among the different classes of faults and the fault-free state, and is robust against noise. This is due mainly to the fact that the classifier is constructed using the fuzzy-neighborhood density based clustering method, which is not sensitive to the geometrical shape of clusters in the feature space.

KW - bearing defects

KW - fault diagnosis

KW - fuzzy-neighborhood density-based clustering

KW - induction motors

U2 - 10.1109/ICMLA.2015.114

DO - 10.1109/ICMLA.2015.114

M3 - Paper

SP - 935

EP - 940

ER -