An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery
Deep learning-based fault diagnosis usually requires a rich supply of data, but fault samples are scarce in practice, posing a considerable challenge for existing diagnosis approaches to achieve highly accurate fault detection in real applications. This paper proposes an imbalanced fault diagnosis o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8749 |
| _version_ | 1797464045205323776 |
|---|---|
| author | Long Zhang Yangyuan Liu Jianmin Zhou Muxu Luo Shengxin Pu Xiaotong Yang |
| author_facet | Long Zhang Yangyuan Liu Jianmin Zhou Muxu Luo Shengxin Pu Xiaotong Yang |
| author_sort | Long Zhang |
| collection | DOAJ |
| description | Deep learning-based fault diagnosis usually requires a rich supply of data, but fault samples are scarce in practice, posing a considerable challenge for existing diagnosis approaches to achieve highly accurate fault detection in real applications. This paper proposes an imbalanced fault diagnosis of rotatory machinery that combines time-frequency feature oversampling (TFFO) with a convolutional neural network (CNN). First, the sliding segmentation sampling method is employed to primarily increase the number of fault samples in the form of one-dimensional signals. Immediately after, the signals are converted into two-dimensional time-frequency feature maps by continuous wavelet transform (CWT). Subsequently, the minority samples are expanded again using the synthetic minority oversampling technique (SMOTE) to realize TFFO. After such two-fold data expansion, a balanced data set is obtained and imported to an improved 2dCNN based on the LeNet-5 to implement fault diagnosis. In order to verify the proposed method, two experiments involving single and compound faults are conducted on locomotive wheel-set bearings and a gearbox, resulting in several datasets with different imbalanced degrees and various signal-to-noise ratios. The results demonstrate the advantages of the proposed method in terms of classification accuracy and stability as well as noise robustness in imbalanced fault diagnosis, and the fault classification accuracy is over 97%. |
| first_indexed | 2024-03-09T18:01:22Z |
| format | Article |
| id | doaj.art-bf80468aaa444075a08b5bd17ad657bf |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:01:22Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bf80468aaa444075a08b5bd17ad657bf2023-11-24T09:55:16ZengMDPI AGSensors1424-82202022-11-012222874910.3390/s22228749An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating MachineryLong Zhang0Yangyuan Liu1Jianmin Zhou2Muxu Luo3Shengxin Pu4Xiaotong Yang5School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaDeep learning-based fault diagnosis usually requires a rich supply of data, but fault samples are scarce in practice, posing a considerable challenge for existing diagnosis approaches to achieve highly accurate fault detection in real applications. This paper proposes an imbalanced fault diagnosis of rotatory machinery that combines time-frequency feature oversampling (TFFO) with a convolutional neural network (CNN). First, the sliding segmentation sampling method is employed to primarily increase the number of fault samples in the form of one-dimensional signals. Immediately after, the signals are converted into two-dimensional time-frequency feature maps by continuous wavelet transform (CWT). Subsequently, the minority samples are expanded again using the synthetic minority oversampling technique (SMOTE) to realize TFFO. After such two-fold data expansion, a balanced data set is obtained and imported to an improved 2dCNN based on the LeNet-5 to implement fault diagnosis. In order to verify the proposed method, two experiments involving single and compound faults are conducted on locomotive wheel-set bearings and a gearbox, resulting in several datasets with different imbalanced degrees and various signal-to-noise ratios. The results demonstrate the advantages of the proposed method in terms of classification accuracy and stability as well as noise robustness in imbalanced fault diagnosis, and the fault classification accuracy is over 97%.https://www.mdpi.com/1424-8220/22/22/8749imbalanced datadata expansioncontinuous wavelet transformsynthetic minority oversampling techniqueconvolution neural network |
| spellingShingle | Long Zhang Yangyuan Liu Jianmin Zhou Muxu Luo Shengxin Pu Xiaotong Yang An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery Sensors imbalanced data data expansion continuous wavelet transform synthetic minority oversampling technique convolution neural network |
| title | An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery |
| title_full | An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery |
| title_fullStr | An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery |
| title_full_unstemmed | An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery |
| title_short | An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery |
| title_sort | imbalanced fault diagnosis method based on tffo and cnn for rotating machinery |
| topic | imbalanced data data expansion continuous wavelet transform synthetic minority oversampling technique convolution neural network |
| url | https://www.mdpi.com/1424-8220/22/22/8749 |
| work_keys_str_mv | AT longzhang animbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT yangyuanliu animbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT jianminzhou animbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT muxuluo animbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT shengxinpu animbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT xiaotongyang animbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT longzhang imbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT yangyuanliu imbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT jianminzhou imbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT muxuluo imbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT shengxinpu imbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery AT xiaotongyang imbalancedfaultdiagnosismethodbasedontffoandcnnforrotatingmachinery |