Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor Information
Single-signal-driven fault diagnosis has been widely applied in motor fault diagnosis, but it cannot meet the diagnostic requirements of complex motor systems. This study proposes a motor fault diagnosis method using attention mechanism (AM) and hybrid CNN-MLP by multi-sensor information. Firstly, F...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10227288/ |
| _version_ | 1797683291244986368 |
|---|---|
| author | Yi Zhou Qianming Shang Cong Guan |
| author_facet | Yi Zhou Qianming Shang Cong Guan |
| author_sort | Yi Zhou |
| collection | DOAJ |
| description | Single-signal-driven fault diagnosis has been widely applied in motor fault diagnosis, but it cannot meet the diagnostic requirements of complex motor systems. This study proposes a motor fault diagnosis method using attention mechanism (AM) and hybrid CNN-MLP by multi-sensor information. Firstly, Fast Fourier transform and continuous wavelet transform are performed on different signals to obtain the corresponding frequency domain feature information and wavelet time-frequency map images. A hybrid CNN-MLPAM model is used to extract features from spectral feature information and wavelet time-frequency images, respectively, and is trained to obtain preliminary classification results. Finally, a dynamic weight distribution vector is used to obtain the final diagnosis. The proposed method is verified by current, and vibration signals. The results show that the method can dynamically evaluate the sensitivity of different detection signals to different faults. The proposed method is more accurate and stable in fault diagnosis than the traditional method that relies solely on vibration signals. Under the consideration of time cost and diagnostic accuracy, the proposed CNN-MLPAM has higher diagnostic performance compared with CNN-RNNAM and CNN-ELMAM. |
| first_indexed | 2024-03-12T00:12:23Z |
| format | Article |
| id | doaj.art-b6e14c5472234092968281a5316955e1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:12:23Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b6e14c5472234092968281a5316955e12023-09-15T23:00:22ZengIEEEIEEE Access2169-35362023-01-0111984029841410.1109/ACCESS.2023.330777010227288Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor InformationYi Zhou0https://orcid.org/0009-0009-1104-917XQianming Shang1Cong Guan2https://orcid.org/0000-0002-5963-9381School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan, ChinaSchool of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan, ChinaSchool of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan, ChinaSingle-signal-driven fault diagnosis has been widely applied in motor fault diagnosis, but it cannot meet the diagnostic requirements of complex motor systems. This study proposes a motor fault diagnosis method using attention mechanism (AM) and hybrid CNN-MLP by multi-sensor information. Firstly, Fast Fourier transform and continuous wavelet transform are performed on different signals to obtain the corresponding frequency domain feature information and wavelet time-frequency map images. A hybrid CNN-MLPAM model is used to extract features from spectral feature information and wavelet time-frequency images, respectively, and is trained to obtain preliminary classification results. Finally, a dynamic weight distribution vector is used to obtain the final diagnosis. The proposed method is verified by current, and vibration signals. The results show that the method can dynamically evaluate the sensitivity of different detection signals to different faults. The proposed method is more accurate and stable in fault diagnosis than the traditional method that relies solely on vibration signals. Under the consideration of time cost and diagnostic accuracy, the proposed CNN-MLPAM has higher diagnostic performance compared with CNN-RNNAM and CNN-ELMAM.https://ieeexplore.ieee.org/document/10227288/Fault diagnosis of motordeep learningattention mechanismmulti-sensor information |
| spellingShingle | Yi Zhou Qianming Shang Cong Guan Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor Information IEEE Access Fault diagnosis of motor deep learning attention mechanism multi-sensor information |
| title | Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor Information |
| title_full | Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor Information |
| title_fullStr | Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor Information |
| title_full_unstemmed | Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor Information |
| title_short | Three-Phase Asynchronous Motor Fault Diagnosis Using Attention Mechanism and Hybrid CNN-MLP By Multi-Sensor Information |
| title_sort | three phase asynchronous motor fault diagnosis using attention mechanism and hybrid cnn mlp by multi sensor information |
| topic | Fault diagnosis of motor deep learning attention mechanism multi-sensor information |
| url | https://ieeexplore.ieee.org/document/10227288/ |
| work_keys_str_mv | AT yizhou threephaseasynchronousmotorfaultdiagnosisusingattentionmechanismandhybridcnnmlpbymultisensorinformation AT qianmingshang threephaseasynchronousmotorfaultdiagnosisusingattentionmechanismandhybridcnnmlpbymultisensorinformation AT congguan threephaseasynchronousmotorfaultdiagnosisusingattentionmechanismandhybridcnnmlpbymultisensorinformation |