Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network
Accurate fault diagnosis is essential for the safe operation of rotating machinery. Recently, traditional deep learning-based fault diagnosis have achieved promising results. However, most of these methods focus only on supervised learning and tend to use small convolution kernels non-effectively to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/4/1290 |
| _version_ | 1827342743792254976 |
|---|---|
| author | Zhunan Shen Xiangwei Kong Liu Cheng Rengen Wang Yunpeng Zhu |
| author_facet | Zhunan Shen Xiangwei Kong Liu Cheng Rengen Wang Yunpeng Zhu |
| author_sort | Zhunan Shen |
| collection | DOAJ |
| description | Accurate fault diagnosis is essential for the safe operation of rotating machinery. Recently, traditional deep learning-based fault diagnosis have achieved promising results. However, most of these methods focus only on supervised learning and tend to use small convolution kernels non-effectively to extract features that are not controllable and have poor interpretability. To this end, this study proposes an innovative semi-supervised learning method for bearing fault diagnosis. Firstly, multi-scale dilated convolution squeeze-and-excitation residual blocks are designed to exact local and global features. Secondly, a classifier generative adversarial network is employed to achieve multi-task learning. Both unsupervised and supervised learning are performed simultaneously to improve the generalization ability. Finally, supervised learning is applied to fine-tune the final model, which can extract multi-scale features and be further improved by implicit data augmentation. Experiments on two datasets were carried out, and the results verified the superiority of the proposed method. |
| first_indexed | 2024-03-07T22:13:59Z |
| format | Article |
| id | doaj.art-73fa3bdb06bd44ada88a3097b5d5d798 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-07T22:13:59Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-73fa3bdb06bd44ada88a3097b5d5d7982024-02-23T15:34:05ZengMDPI AGSensors1424-82202024-02-01244129010.3390/s24041290Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial NetworkZhunan Shen0Xiangwei Kong1Liu Cheng2Rengen Wang3Yunpeng Zhu4School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, ChinaSchool of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, ChinaSchool of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, ChinaDahua Technology Co., Ltd., Hangzhou 310053, ChinaSchool of Engineering and Materials Science, Queen Mary University of London, London E1 4NS, UKAccurate fault diagnosis is essential for the safe operation of rotating machinery. Recently, traditional deep learning-based fault diagnosis have achieved promising results. However, most of these methods focus only on supervised learning and tend to use small convolution kernels non-effectively to extract features that are not controllable and have poor interpretability. To this end, this study proposes an innovative semi-supervised learning method for bearing fault diagnosis. Firstly, multi-scale dilated convolution squeeze-and-excitation residual blocks are designed to exact local and global features. Secondly, a classifier generative adversarial network is employed to achieve multi-task learning. Both unsupervised and supervised learning are performed simultaneously to improve the generalization ability. Finally, supervised learning is applied to fine-tune the final model, which can extract multi-scale features and be further improved by implicit data augmentation. Experiments on two datasets were carried out, and the results verified the superiority of the proposed method.https://www.mdpi.com/1424-8220/24/4/1290rolling bearingintelligent fault diagnosisadversarial generative networkmulti-task learningsemi-supervised learning |
| spellingShingle | Zhunan Shen Xiangwei Kong Liu Cheng Rengen Wang Yunpeng Zhu Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network Sensors rolling bearing intelligent fault diagnosis adversarial generative network multi-task learning semi-supervised learning |
| title | Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network |
| title_full | Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network |
| title_fullStr | Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network |
| title_full_unstemmed | Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network |
| title_short | Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network |
| title_sort | fault diagnosis of the rolling bearing by a multi task deep learning method based on a classifier generative adversarial network |
| topic | rolling bearing intelligent fault diagnosis adversarial generative network multi-task learning semi-supervised learning |
| url | https://www.mdpi.com/1424-8220/24/4/1290 |
| work_keys_str_mv | AT zhunanshen faultdiagnosisoftherollingbearingbyamultitaskdeeplearningmethodbasedonaclassifiergenerativeadversarialnetwork AT xiangweikong faultdiagnosisoftherollingbearingbyamultitaskdeeplearningmethodbasedonaclassifiergenerativeadversarialnetwork AT liucheng faultdiagnosisoftherollingbearingbyamultitaskdeeplearningmethodbasedonaclassifiergenerativeadversarialnetwork AT rengenwang faultdiagnosisoftherollingbearingbyamultitaskdeeplearningmethodbasedonaclassifiergenerativeadversarialnetwork AT yunpengzhu faultdiagnosisoftherollingbearingbyamultitaskdeeplearningmethodbasedonaclassifiergenerativeadversarialnetwork |