Automatic feature selection and failure diagnosis for bearing faults

Haw Ching Yang, Hao Tieng, Shih Fang Chen

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

Abstract

This study develops a novel dual-stage diagnosis scheme for accelerating bearing failure diagnosis. The schema integrates the intelligent methods, i.e., genetic algorithm, k-nearest neighbors, and neural network, in the featuring and modeling stages to automatically select the significant features from various feature candidates for modeling bearing failure modes. After applying the scheme to classify two cases of bearing faults, the mean training time for model diagnosis is reduced to 8.1% that of using a neural network model. In this work, case 1 indicates that training and testing accuracies of seven failure modes are 98.8% and 94.5%, respectively; in addition, case 2 shows that the training and testing accuracies are 96.2% and 91.8% while using the top seven features.

Original languageEnglish
Title of host publicationSICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts
PublisherSociety of Instrument and Control Engineers (SICE)
Pages235-239
Number of pages5
ISBN (Print)9784907764395
Publication statusPublished - 2011 Jan 1
Event50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 - Tokyo, Japan
Duration: 2011 Sep 132011 Sep 18

Publication series

NameProceedings of the SICE Annual Conference

Other

Other50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011
CountryJapan
CityTokyo
Period11-09-1311-09-18

Fingerprint

Bearings (structural)
Feature extraction
Failure modes
Neural networks
Testing
Genetic algorithms

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Yang, H. C., Tieng, H., & Chen, S. F. (2011). Automatic feature selection and failure diagnosis for bearing faults. In SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts (pp. 235-239). [6060609] (Proceedings of the SICE Annual Conference). Society of Instrument and Control Engineers (SICE).
Yang, Haw Ching ; Tieng, Hao ; Chen, Shih Fang. / Automatic feature selection and failure diagnosis for bearing faults. SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts. Society of Instrument and Control Engineers (SICE), 2011. pp. 235-239 (Proceedings of the SICE Annual Conference).
@inproceedings{e42c6d9c298d440bb98e82c66e07a2d2,
title = "Automatic feature selection and failure diagnosis for bearing faults",
abstract = "This study develops a novel dual-stage diagnosis scheme for accelerating bearing failure diagnosis. The schema integrates the intelligent methods, i.e., genetic algorithm, k-nearest neighbors, and neural network, in the featuring and modeling stages to automatically select the significant features from various feature candidates for modeling bearing failure modes. After applying the scheme to classify two cases of bearing faults, the mean training time for model diagnosis is reduced to 8.1{\%} that of using a neural network model. In this work, case 1 indicates that training and testing accuracies of seven failure modes are 98.8{\%} and 94.5{\%}, respectively; in addition, case 2 shows that the training and testing accuracies are 96.2{\%} and 91.8{\%} while using the top seven features.",
author = "Yang, {Haw Ching} and Hao Tieng and Chen, {Shih Fang}",
year = "2011",
month = "1",
day = "1",
language = "English",
isbn = "9784907764395",
series = "Proceedings of the SICE Annual Conference",
publisher = "Society of Instrument and Control Engineers (SICE)",
pages = "235--239",
booktitle = "SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts",

}

Yang, HC, Tieng, H & Chen, SF 2011, Automatic feature selection and failure diagnosis for bearing faults. in SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts., 6060609, Proceedings of the SICE Annual Conference, Society of Instrument and Control Engineers (SICE), pp. 235-239, 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011, Tokyo, Japan, 11-09-13.

Automatic feature selection and failure diagnosis for bearing faults. / Yang, Haw Ching; Tieng, Hao; Chen, Shih Fang.

SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts. Society of Instrument and Control Engineers (SICE), 2011. p. 235-239 6060609 (Proceedings of the SICE Annual Conference).

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

TY - GEN

T1 - Automatic feature selection and failure diagnosis for bearing faults

AU - Yang, Haw Ching

AU - Tieng, Hao

AU - Chen, Shih Fang

PY - 2011/1/1

Y1 - 2011/1/1

N2 - This study develops a novel dual-stage diagnosis scheme for accelerating bearing failure diagnosis. The schema integrates the intelligent methods, i.e., genetic algorithm, k-nearest neighbors, and neural network, in the featuring and modeling stages to automatically select the significant features from various feature candidates for modeling bearing failure modes. After applying the scheme to classify two cases of bearing faults, the mean training time for model diagnosis is reduced to 8.1% that of using a neural network model. In this work, case 1 indicates that training and testing accuracies of seven failure modes are 98.8% and 94.5%, respectively; in addition, case 2 shows that the training and testing accuracies are 96.2% and 91.8% while using the top seven features.

AB - This study develops a novel dual-stage diagnosis scheme for accelerating bearing failure diagnosis. The schema integrates the intelligent methods, i.e., genetic algorithm, k-nearest neighbors, and neural network, in the featuring and modeling stages to automatically select the significant features from various feature candidates for modeling bearing failure modes. After applying the scheme to classify two cases of bearing faults, the mean training time for model diagnosis is reduced to 8.1% that of using a neural network model. In this work, case 1 indicates that training and testing accuracies of seven failure modes are 98.8% and 94.5%, respectively; in addition, case 2 shows that the training and testing accuracies are 96.2% and 91.8% while using the top seven features.

UR - http://www.scopus.com/inward/record.url?scp=81255178797&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81255178797&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:81255178797

SN - 9784907764395

T3 - Proceedings of the SICE Annual Conference

SP - 235

EP - 239

BT - SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts

PB - Society of Instrument and Control Engineers (SICE)

ER -

Yang HC, Tieng H, Chen SF. Automatic feature selection and failure diagnosis for bearing faults. In SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts. Society of Instrument and Control Engineers (SICE). 2011. p. 235-239. 6060609. (Proceedings of the SICE Annual Conference).