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...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
Springer, Singapore
2022
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/35518/ http://umpir.ump.edu.my/id/eprint/35518/1/im3f-Performance%20Evaluation%20of%20BPSO%20%26%20PCA%20as%20Feature%20Reduction%20Techniques%20for%20Bearing%20Fault%20Diagnosis-2021.pdf |
| _version_ | 1848824798687264768 |
|---|---|
| author | Faysal, Atik Ngui, Wai Keng M. H., Lim |
| author_facet | Faysal, Atik Ngui, Wai Keng M. H., Lim |
| author_sort | Faysal, Atik |
| building | UMP Institutional Repository |
| collection | Online Access |
| 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. |
| first_indexed | 2025-11-15T03:18:45Z |
| format | Conference or Workshop Item |
| id | ump-35518 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:18:45Z |
| publishDate | 2022 |
| publisher | Springer, Singapore |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-355182022-11-03T03:27:44Z http://umpir.ump.edu.my/id/eprint/35518/ Performance Evaluation of BPSO & PCA as Feature Reduction Techniques for Bearing Fault Diagnosis Faysal, Atik Ngui, Wai Keng M. H., Lim 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, Singapore 2022 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/35518/1/im3f-Performance%20Evaluation%20of%20BPSO%20%26%20PCA%20as%20Feature%20Reduction%20Techniques%20for%20Bearing%20Fault%20Diagnosis-2021.pdf Faysal, Atik and Ngui, Wai Keng and M. H., Lim (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 , 6 August 2020 , Virtual Conference, Universiti Malaysia Pahang, Malaysia. pp. 605-615., 730. (Published) https://doi.org/10.1007/978-981-33-4597-3_55 |
| spellingShingle | TJ Mechanical engineering and machinery Faysal, Atik Ngui, Wai Keng M. H., Lim Performance Evaluation of BPSO & PCA as Feature Reduction Techniques for Bearing Fault Diagnosis |
| title | 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_short | 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 |
| topic | TJ Mechanical engineering and machinery |
| url | http://umpir.ump.edu.my/id/eprint/35518/ http://umpir.ump.edu.my/id/eprint/35518/ http://umpir.ump.edu.my/id/eprint/35518/1/im3f-Performance%20Evaluation%20of%20BPSO%20%26%20PCA%20as%20Feature%20Reduction%20Techniques%20for%20Bearing%20Fault%20Diagnosis-2021.pdf |