A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA
This paper proposes a new method for bearing fault diagnosis using wavelet packet transform (WPT)-based signal representation and informative factor linear discriminant analysis (IF-LDA). Time–frequency domain approaches for analyzing bearing vibration signals have gained wide acceptance due to thei...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/12/1080 |
| _version_ | 1827574253305724928 |
|---|---|
| author | Andrei S. Maliuk Zahoor Ahmad Jong-Myon Kim |
| author_facet | Andrei S. Maliuk Zahoor Ahmad Jong-Myon Kim |
| author_sort | Andrei S. Maliuk |
| collection | DOAJ |
| description | This paper proposes a new method for bearing fault diagnosis using wavelet packet transform (WPT)-based signal representation and informative factor linear discriminant analysis (IF-LDA). Time–frequency domain approaches for analyzing bearing vibration signals have gained wide acceptance due to their effectiveness in extracting information related to bearing health. WPT is a prominent method in this category, offering a balanced approach between short-time Fourier transform and empirical mode decomposition. However, the existing methods for bearing fault diagnosis often overlook the limitations of WPT regarding its dependence on the mother wavelet parameters for feature extraction. This work addresses this issue by introducing a novel signal representation method that employs WPT with a new rule for selecting the mother wavelet based on the power spectrum energy-to-entropy ratio of the reconstructed coefficients and a combination of the nodes from different WPT trees. Furthermore, an IF-LDA feature preprocessing technique is proposed, resulting in a highly sensitive set of features for bearing condition assessment. The k-nearest neighbors algorithm is employed as the classifier, and the proposed method is evaluated using datasets from Paderborn and Case Western Reserve universities. The performance of the proposed method demonstrates its effectiveness in bearing fault diagnosis, surpassing existing techniques in terms of fault identification and diagnosis performance. |
| first_indexed | 2024-03-08T20:34:32Z |
| format | Article |
| id | doaj.art-17178a88b5644d96bf01b17f24ddd0d7 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-08T20:34:32Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-17178a88b5644d96bf01b17f24ddd0d72023-12-22T14:22:00ZengMDPI AGMachines2075-17022023-12-011112108010.3390/machines11121080A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDAAndrei S. Maliuk0Zahoor Ahmad1Jong-Myon Kim2Department of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaDepartment of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaPrognosis and Diagnostics Technologies Co., Ltd., Ulsan 44610, Republic of KoreaThis paper proposes a new method for bearing fault diagnosis using wavelet packet transform (WPT)-based signal representation and informative factor linear discriminant analysis (IF-LDA). Time–frequency domain approaches for analyzing bearing vibration signals have gained wide acceptance due to their effectiveness in extracting information related to bearing health. WPT is a prominent method in this category, offering a balanced approach between short-time Fourier transform and empirical mode decomposition. However, the existing methods for bearing fault diagnosis often overlook the limitations of WPT regarding its dependence on the mother wavelet parameters for feature extraction. This work addresses this issue by introducing a novel signal representation method that employs WPT with a new rule for selecting the mother wavelet based on the power spectrum energy-to-entropy ratio of the reconstructed coefficients and a combination of the nodes from different WPT trees. Furthermore, an IF-LDA feature preprocessing technique is proposed, resulting in a highly sensitive set of features for bearing condition assessment. The k-nearest neighbors algorithm is employed as the classifier, and the proposed method is evaluated using datasets from Paderborn and Case Western Reserve universities. The performance of the proposed method demonstrates its effectiveness in bearing fault diagnosis, surpassing existing techniques in terms of fault identification and diagnosis performance.https://www.mdpi.com/2075-1702/11/12/1080bearing fault diagnosistime–frequency signal analysisfeature selectionwavelet packet transformmother wavelet |
| spellingShingle | Andrei S. Maliuk Zahoor Ahmad Jong-Myon Kim A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA Machines bearing fault diagnosis time–frequency signal analysis feature selection wavelet packet transform mother wavelet |
| title | A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA |
| title_full | A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA |
| title_fullStr | A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA |
| title_full_unstemmed | A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA |
| title_short | A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA |
| title_sort | technique for bearing fault diagnosis using novel wavelet packet transform based signal representation and informative factor lda |
| topic | bearing fault diagnosis time–frequency signal analysis feature selection wavelet packet transform mother wavelet |
| url | https://www.mdpi.com/2075-1702/11/12/1080 |
| work_keys_str_mv | AT andreismaliuk atechniqueforbearingfaultdiagnosisusingnovelwaveletpackettransformbasedsignalrepresentationandinformativefactorlda AT zahoorahmad atechniqueforbearingfaultdiagnosisusingnovelwaveletpackettransformbasedsignalrepresentationandinformativefactorlda AT jongmyonkim atechniqueforbearingfaultdiagnosisusingnovelwaveletpackettransformbasedsignalrepresentationandinformativefactorlda AT andreismaliuk techniqueforbearingfaultdiagnosisusingnovelwaveletpackettransformbasedsignalrepresentationandinformativefactorlda AT zahoorahmad techniqueforbearingfaultdiagnosisusingnovelwaveletpackettransformbasedsignalrepresentationandinformativefactorlda AT jongmyonkim techniqueforbearingfaultdiagnosisusingnovelwaveletpackettransformbasedsignalrepresentationandinformativefactorlda |