Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks

M. Delgado; G. Cirrincione; A. Garcia; J. A. Ortega; H. Henao

doi:10.1109/IECON.2012.6389596

Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks

M. Delgado^*
, G. Cirrincione
, A. Garcia
, J. A. Ortega
, H. Henao

^*Corresponding author for this work

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

14 Citations (Scopus)

Abstract

Bearing faults are the commonest form of malfunction associated with electrical machines. So far, the research has been carried out mainly in the detection of localized faults, but the diagnosis of distributed faults is still under development. In this context, this work presents a new scheme for detecting and classifying both kinds of faults. This work deals with a new diagnosis monitoring scheme, which is based on statistical-time features calculated from vibration signal, curvilinear component analysis for compression and visualization of the features behavior and a hierarchical neural network structure for classification. The obtained results from different operation conditions validate the effectiveness and feasibility of the proposed methodology.

Original language	English
Title of host publication	Proceedings, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society
Pages	3854-3861
Number of pages	8
DOIs	https://doi.org/10.1109/IECON.2012.6389596
Publication status	Published - 2012
Externally published	Yes
Event	38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012 - Montreal, QC, Canada Duration: 25 Oct 2012 → 28 Oct 2012

Publication series

Name	IECON Proceedings (Industrial Electronics Conference)

Conference

Conference	38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012
Country/Territory	Canada
City	Montreal, QC
Period	25/10/12 → 28/10/12

Keywords

Bearing balls
Classification algorithms
Fault detection
Feature extraction
Neural networks
Time domain analysis
Vibrations

Access to Document

10.1109/IECON.2012.6389596

Cite this

Delgado, M., Cirrincione, G., Garcia, A., Ortega, J. A., & Henao, H. (2012). Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks. In Proceedings, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society (pp. 3854-3861). Article 6389596 (IECON Proceedings (Industrial Electronics Conference)). https://doi.org/10.1109/IECON.2012.6389596

@inproceedings{51e05b0568d046398a2dc8380672db78,

title = "Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks",

abstract = "Bearing faults are the commonest form of malfunction associated with electrical machines. So far, the research has been carried out mainly in the detection of localized faults, but the diagnosis of distributed faults is still under development. In this context, this work presents a new scheme for detecting and classifying both kinds of faults. This work deals with a new diagnosis monitoring scheme, which is based on statistical-time features calculated from vibration signal, curvilinear component analysis for compression and visualization of the features behavior and a hierarchical neural network structure for classification. The obtained results from different operation conditions validate the effectiveness and feasibility of the proposed methodology.",

keywords = "Bearing balls, Classification algorithms, Fault detection, Feature extraction, Neural networks, Time domain analysis, Vibrations",

author = "M. Delgado and G. Cirrincione and A. Garcia and Ortega, \{J. A.\} and H. Henao",

year = "2012",

doi = "10.1109/IECON.2012.6389596",

language = "English",

isbn = "9781467324212",

series = "IECON Proceedings (Industrial Electronics Conference)",

pages = "3854--3861",

booktitle = "Proceedings, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society",

note = "38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012 ; Conference date: 25-10-2012 Through 28-10-2012",

}

Delgado, M, Cirrincione, G, Garcia, A, Ortega, JA & Henao, H 2012, Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks. in Proceedings, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society., 6389596, IECON Proceedings (Industrial Electronics Conference), pp. 3854-3861, 38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012, Montreal, QC, Canada, 25/10/12. https://doi.org/10.1109/IECON.2012.6389596

Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks. / Delgado, M.; Cirrincione, G.; Garcia, A. et al.
Proceedings, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society. 2012. p. 3854-3861 6389596 (IECON Proceedings (Industrial Electronics Conference)).

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

TY - GEN

T1 - Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks

AU - Delgado, M.

AU - Cirrincione, G.

AU - Garcia, A.

AU - Ortega, J. A.

AU - Henao, H.

PY - 2012

Y1 - 2012

N2 - Bearing faults are the commonest form of malfunction associated with electrical machines. So far, the research has been carried out mainly in the detection of localized faults, but the diagnosis of distributed faults is still under development. In this context, this work presents a new scheme for detecting and classifying both kinds of faults. This work deals with a new diagnosis monitoring scheme, which is based on statistical-time features calculated from vibration signal, curvilinear component analysis for compression and visualization of the features behavior and a hierarchical neural network structure for classification. The obtained results from different operation conditions validate the effectiveness and feasibility of the proposed methodology.

AB - Bearing faults are the commonest form of malfunction associated with electrical machines. So far, the research has been carried out mainly in the detection of localized faults, but the diagnosis of distributed faults is still under development. In this context, this work presents a new scheme for detecting and classifying both kinds of faults. This work deals with a new diagnosis monitoring scheme, which is based on statistical-time features calculated from vibration signal, curvilinear component analysis for compression and visualization of the features behavior and a hierarchical neural network structure for classification. The obtained results from different operation conditions validate the effectiveness and feasibility of the proposed methodology.

KW - Bearing balls

KW - Classification algorithms

KW - Fault detection

KW - Feature extraction

KW - Neural networks

KW - Time domain analysis

KW - Vibrations

UR - https://www.scopus.com/pages/publications/84872904520

U2 - 10.1109/IECON.2012.6389596

DO - 10.1109/IECON.2012.6389596

M3 - Conference contribution

AN - SCOPUS:84872904520

SN - 9781467324212

T3 - IECON Proceedings (Industrial Electronics Conference)

SP - 3854

EP - 3861

BT - Proceedings, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society

T2 - 38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012

Y2 - 25 October 2012 through 28 October 2012

ER -

Delgado M, Cirrincione G, Garcia A, Ortega JA, Henao H. Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks. In Proceedings, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society. 2012. p. 3854-3861. 6389596. (IECON Proceedings (Industrial Electronics Conference)). doi: 10.1109/IECON.2012.6389596

Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this