Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature Analysis
This paper presents a comprehensive multifault diagnosis methodology for incipient rolling element bearing failures. This is done by combining a wavelet packet transform- (WPT-) based kurtogram and a new vector median-based feature analysis technique. The proposed approach first extracts useful feat...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2015/320508 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551845430558720 |
|---|---|
| author | Phuong H. Nguyen Jong-Myon Kim |
| author_facet | Phuong H. Nguyen Jong-Myon Kim |
| author_sort | Phuong H. Nguyen |
| collection | DOAJ |
| description | This paper presents a comprehensive multifault diagnosis methodology for incipient rolling element bearing failures. This is done by combining a wavelet packet transform- (WPT-) based kurtogram and a new vector median-based feature analysis technique. The proposed approach first extracts useful features that are characteristic of the bearing health condition from the time domain, frequency domain, and envelope power spectrum of incoming acoustic emission (AE) signals by using a WPT-based kurtogram. Then, an enhanced feature analysis approach based on the linear discriminant analysis (LDA) technique is used to select the most discriminant bearing fault features from the original feature set. These selected fault features are used by a Naïve Bayes (NB) classifier to classify the bearing fault conditions. The performance of the proposed methodology is tested and validated under various bearing fault conditions on an experimental test rig and compared with conventional state-of-the-art approaches. The proposed bearing fault diagnosis methodology yields average classification accuracies of 91.11%, 96.67%, 98.89%, 99.44%, and 98.61% at rotational speeds of 300, 350, 400, 450, and 500 rpm, respectively. |
| format | Article |
| id | doaj-art-e9fd9193bdc74546ba120acc352b639d |
| institution | Kabale University |
| issn | 1070-9622 1875-9203 |
| language | English |
| publishDate | 2015-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-e9fd9193bdc74546ba120acc352b639d2025-02-03T06:00:30ZengWileyShock and Vibration1070-96221875-92032015-01-01201510.1155/2015/320508320508Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature AnalysisPhuong H. Nguyen0Jong-Myon Kim1School of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 680-749, Republic of KoreaSchool of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 680-749, Republic of KoreaThis paper presents a comprehensive multifault diagnosis methodology for incipient rolling element bearing failures. This is done by combining a wavelet packet transform- (WPT-) based kurtogram and a new vector median-based feature analysis technique. The proposed approach first extracts useful features that are characteristic of the bearing health condition from the time domain, frequency domain, and envelope power spectrum of incoming acoustic emission (AE) signals by using a WPT-based kurtogram. Then, an enhanced feature analysis approach based on the linear discriminant analysis (LDA) technique is used to select the most discriminant bearing fault features from the original feature set. These selected fault features are used by a Naïve Bayes (NB) classifier to classify the bearing fault conditions. The performance of the proposed methodology is tested and validated under various bearing fault conditions on an experimental test rig and compared with conventional state-of-the-art approaches. The proposed bearing fault diagnosis methodology yields average classification accuracies of 91.11%, 96.67%, 98.89%, 99.44%, and 98.61% at rotational speeds of 300, 350, 400, 450, and 500 rpm, respectively.http://dx.doi.org/10.1155/2015/320508 |
| spellingShingle | Phuong H. Nguyen Jong-Myon Kim Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature Analysis Shock and Vibration |
| title | Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature Analysis |
| title_full | Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature Analysis |
| title_fullStr | Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature Analysis |
| title_full_unstemmed | Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature Analysis |
| title_short | Multifault Diagnosis of Rolling Element Bearings Using a Wavelet Kurtogram and Vector Median-Based Feature Analysis |
| title_sort | multifault diagnosis of rolling element bearings using a wavelet kurtogram and vector median based feature analysis |
| url | http://dx.doi.org/10.1155/2015/320508 |
| work_keys_str_mv | AT phuonghnguyen multifaultdiagnosisofrollingelementbearingsusingawaveletkurtogramandvectormedianbasedfeatureanalysis AT jongmyonkim multifaultdiagnosisofrollingelementbearingsusingawaveletkurtogramandvectormedianbasedfeatureanalysis |