One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis
This paper proposes a novel algorithm for bearing fault diagnosis using sparse wavelet decomposition for feature extraction combined with a multi-scale one dimensional convolutional neural network (1-D CNN). The proposed algorithm consists of three stages. The first stage determines bearing fault fr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9858121/ |
| _version_ | 1798036709334581248 |
|---|---|
| author | Xiaofan Liu Jason Centeno Juan Alvarado Lizhe Tan |
| author_facet | Xiaofan Liu Jason Centeno Juan Alvarado Lizhe Tan |
| author_sort | Xiaofan Liu |
| collection | DOAJ |
| description | This paper proposes a novel algorithm for bearing fault diagnosis using sparse wavelet decomposition for feature extraction combined with a multi-scale one dimensional convolutional neural network (1-D CNN). The proposed algorithm consists of three stages. The first stage determines bearing fault frequency bands according to bearing physical parameters and constructs a sparse wavelet decomposition structure. The second stage decomposes a raw bearing signal into multi-resolution signals based on a decomposition structure achieved at the second stage. Finally, the decomposed multi-resolution signal features are fed into the sub-neural networks according to the multi-scale 1-D CNN (MSCNN) network, and then the outputs of the final convolutional/polling layers are concatenated into a single channel which is further used as the input to a fully connected layer. In comparison with the other bearing fault diagnosis methods, our proposed algorithm can achieve a higher classification accuracy of 99.85% using the Case Western Reserve University (CWRU) bearing dataset. The proposed algorithm is successfully validated via our designed experiments. |
| first_indexed | 2024-04-11T21:16:41Z |
| format | Article |
| id | doaj.art-68b70c7cc3474455a1bab48133c80647 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T21:16:41Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-68b70c7cc3474455a1bab48133c806472022-12-22T04:02:47ZengIEEEIEEE Access2169-35362022-01-0110869988700710.1109/ACCESS.2022.31993819858121One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault DiagnosisXiaofan Liu0https://orcid.org/0000-0001-7958-0981Jason Centeno1Juan Alvarado2Lizhe Tan3https://orcid.org/0000-0002-7152-9038Department of Electrical and Computer Engineering, Purdue University Northwest, Hammond, IN, USADepartment of Electrical and Computer Engineering, Purdue University Northwest, Hammond, IN, USADepartment of Electrical and Computer Engineering, Purdue University Northwest, Hammond, IN, USADepartment of Electrical and Computer Engineering, Purdue University Northwest, Hammond, IN, USAThis paper proposes a novel algorithm for bearing fault diagnosis using sparse wavelet decomposition for feature extraction combined with a multi-scale one dimensional convolutional neural network (1-D CNN). The proposed algorithm consists of three stages. The first stage determines bearing fault frequency bands according to bearing physical parameters and constructs a sparse wavelet decomposition structure. The second stage decomposes a raw bearing signal into multi-resolution signals based on a decomposition structure achieved at the second stage. Finally, the decomposed multi-resolution signal features are fed into the sub-neural networks according to the multi-scale 1-D CNN (MSCNN) network, and then the outputs of the final convolutional/polling layers are concatenated into a single channel which is further used as the input to a fully connected layer. In comparison with the other bearing fault diagnosis methods, our proposed algorithm can achieve a higher classification accuracy of 99.85% using the Case Western Reserve University (CWRU) bearing dataset. The proposed algorithm is successfully validated via our designed experiments.https://ieeexplore.ieee.org/document/9858121/1-D CNNssparse wavelet decompositionmulti-scale neural networkbearing fault diagnosis |
| spellingShingle | Xiaofan Liu Jason Centeno Juan Alvarado Lizhe Tan One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis IEEE Access 1-D CNNs sparse wavelet decomposition multi-scale neural network bearing fault diagnosis |
| title | One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis |
| title_full | One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis |
| title_fullStr | One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis |
| title_full_unstemmed | One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis |
| title_short | One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis |
| title_sort | one dimensional convolutional neural networks using sparse wavelet decomposition for bearing fault diagnosis |
| topic | 1-D CNNs sparse wavelet decomposition multi-scale neural network bearing fault diagnosis |
| url | https://ieeexplore.ieee.org/document/9858121/ |
| work_keys_str_mv | AT xiaofanliu onedimensionalconvolutionalneuralnetworksusingsparsewaveletdecompositionforbearingfaultdiagnosis AT jasoncenteno onedimensionalconvolutionalneuralnetworksusingsparsewaveletdecompositionforbearingfaultdiagnosis AT juanalvarado onedimensionalconvolutionalneuralnetworksusingsparsewaveletdecompositionforbearingfaultdiagnosis AT lizhetan onedimensionalconvolutionalneuralnetworksusingsparsewaveletdecompositionforbearingfaultdiagnosis |