Cover Image

Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis

Vibration-based signal processing is the most popular and effective approach for fault diagnosis of bearing. In this paper, time-frequency domain analysis, i.e. empirical mode decomposition (EMD) was applied to the raw vibration signal. Intrinsic mode function (IMF) containing the characteristics of...

Full description

Saved in:
Bibliographic Details
Main Authors: Faysal, Atik, Keng, Ngui Wai, Lim, Meng Hee
Format: Book Section
Published: Springer Science and Business Media Deutschland GmbH 2022
Subjects:
TJ Mechanical engineering and machinery
Online Access:http://eprints.utm.my/id/eprint/100528/
http://dx.doi.org/10.1007/978-981-33-4597-3_55
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.100528
record_format eprints
spelling my.utm.1005282023-04-14T02:47:28Z http://eprints.utm.my/id/eprint/100528/ Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis Faysal, Atik Keng, Ngui Wai Lim, Meng Hee TJ Mechanical engineering and machinery Vibration-based signal processing is the most popular and effective approach for fault diagnosis of bearing. In this paper, time-frequency domain analysis, i.e. empirical mode decomposition (EMD) was applied to the raw vibration signal. Intrinsic mode function (IMF) containing the characteristics of vibration data was analysed to obtain 90 statistical features. Two feature reduction algorithms, namely principal components analysis (PCA) and binary particle swarm optimiser (BPSO) were applied individually for feature reduction. The reduced feature subsets were 12 and 35 for PCA and BPSO, respectively. K-Nearest Neighbours (K-NN) was used as an intelligent method for fault diagnosis. K-NN was applied to the entire feature set and individually on the selected feature subset of PCA and BPSO. The reduced feature subset with PCA performed the finest in all the measurements taken. For BPSO, although it effectively reduced the feature dimension and classification time, the testing accuracy was slightly lower. Comparing the output accuracy of the K-NN classifier for the selected methods demonstrated the effectiveness of PCA and BPSO as efficacious feature reduction techniques. Springer Science and Business Media Deutschland GmbH 2022 Book Section PeerReviewed Faysal, Atik and Keng, Ngui Wai and Lim, Meng Hee (2022) Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis. In: Recent Trends in Mechatronics Towards Industry 4.0 Selected Articles from iM3F 2020, Malaysia. Lecture Notes in Electrical Engineering, 730 (NA). Springer Science and Business Media Deutschland GmbH, Singapore, pp. 605-615. ISBN 978-981334596-6 http://dx.doi.org/10.1007/978-981-33-4597-3_55 DOI:10.1007/978-981-33-4597-3_55
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic TJ Mechanical engineering and machinery
spellingShingle TJ Mechanical engineering and machinery
Faysal, Atik
Keng, Ngui Wai
Lim, Meng Hee
Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis
description Vibration-based signal processing is the most popular and effective approach for fault diagnosis of bearing. In this paper, time-frequency domain analysis, i.e. empirical mode decomposition (EMD) was applied to the raw vibration signal. Intrinsic mode function (IMF) containing the characteristics of vibration data was analysed to obtain 90 statistical features. Two feature reduction algorithms, namely principal components analysis (PCA) and binary particle swarm optimiser (BPSO) were applied individually for feature reduction. The reduced feature subsets were 12 and 35 for PCA and BPSO, respectively. K-Nearest Neighbours (K-NN) was used as an intelligent method for fault diagnosis. K-NN was applied to the entire feature set and individually on the selected feature subset of PCA and BPSO. The reduced feature subset with PCA performed the finest in all the measurements taken. For BPSO, although it effectively reduced the feature dimension and classification time, the testing accuracy was slightly lower. Comparing the output accuracy of the K-NN classifier for the selected methods demonstrated the effectiveness of PCA and BPSO as efficacious feature reduction techniques.
format Book Section
author Faysal, Atik
Keng, Ngui Wai
Lim, Meng Hee
author_facet Faysal, Atik
Keng, Ngui Wai
Lim, Meng Hee
author_sort Faysal, Atik
title Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis
title_short Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis
title_full Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis
title_fullStr Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis
title_full_unstemmed Performance evaluation of BPSO & PCA as feature reduction techniques for bearing fault diagnosis
title_sort performance evaluation of bpso & pca as feature reduction techniques for bearing fault diagnosis
publisher Springer Science and Business Media Deutschland GmbH
publishDate 2022
url http://eprints.utm.my/id/eprint/100528/
http://dx.doi.org/10.1007/978-981-33-4597-3_55
_version_ 1764222579773538304
score 13.211869

Similar Items