Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network
To address the problems of low recognition accuracy, slow convergence speed and weak generalization ability of traditional LeNet-5 network used in rolling-element bearing fault diagnosis, a rolling-element bearing fault diagnosis method using improved 2D LeNet-5 network is put forward. The following...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/6/1693 |
| _version_ | 1811184700997238784 |
|---|---|
| author | Lanjun Wan Yiwei Chen Hongyang Li Changyun Li |
| author_facet | Lanjun Wan Yiwei Chen Hongyang Li Changyun Li |
| author_sort | Lanjun Wan |
| collection | DOAJ |
| description | To address the problems of low recognition accuracy, slow convergence speed and weak generalization ability of traditional LeNet-5 network used in rolling-element bearing fault diagnosis, a rolling-element bearing fault diagnosis method using improved 2D LeNet-5 network is put forward. The following improvements to the traditional LeNet-5 network are made: the convolution and pooling layers are reasonably designed and the size and number of convolution kernels are carefully adjusted to improve fault classification capability; the batch normalization (BN) is adopted after each convolution layer to improve convergence speed; the dropout operation is performed after each full-connection layer except the last layer to enhance generalization ability. To further improve the efficiency and effectiveness of fault diagnosis, on the basis of improved 2D LeNet-5 network, an end-to-end rolling-element bearing fault diagnosis method based on the improved 1D LeNet-5 network is proposed, which can directly perform 1D convolution and pooling operations on raw vibration signals without any preprocessing. The results show that the improved 2D LeNet-5 network and improved 1D LeNet-5 network achieve a significant performance improvement than traditional LeNet-5 network, the improved 1D LeNet-5 network provides a higher fault diagnosis accuracy with a less training time in most cases, and the improved 2D LeNet-5 network performs better than improved 1D LeNet-5 network under small training samples and strong noise environment. |
| first_indexed | 2024-04-11T13:17:53Z |
| format | Article |
| id | doaj.art-3700d9d830b44011853e3c1517dc2b67 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:17:53Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3700d9d830b44011853e3c1517dc2b672022-12-22T04:22:20ZengMDPI AGSensors1424-82202020-03-01206169310.3390/s20061693s20061693Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 NetworkLanjun Wan0Yiwei Chen1Hongyang Li2Changyun Li3School of Computer, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Computer, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Computer, Hunan University of Technology, Zhuzhou 412007, ChinaHunan Key Laboratory of Intelligent Information Perception and Processing Technology, Hunan University of Technology, Zhuzhou 412007, ChinaTo address the problems of low recognition accuracy, slow convergence speed and weak generalization ability of traditional LeNet-5 network used in rolling-element bearing fault diagnosis, a rolling-element bearing fault diagnosis method using improved 2D LeNet-5 network is put forward. The following improvements to the traditional LeNet-5 network are made: the convolution and pooling layers are reasonably designed and the size and number of convolution kernels are carefully adjusted to improve fault classification capability; the batch normalization (BN) is adopted after each convolution layer to improve convergence speed; the dropout operation is performed after each full-connection layer except the last layer to enhance generalization ability. To further improve the efficiency and effectiveness of fault diagnosis, on the basis of improved 2D LeNet-5 network, an end-to-end rolling-element bearing fault diagnosis method based on the improved 1D LeNet-5 network is proposed, which can directly perform 1D convolution and pooling operations on raw vibration signals without any preprocessing. The results show that the improved 2D LeNet-5 network and improved 1D LeNet-5 network achieve a significant performance improvement than traditional LeNet-5 network, the improved 1D LeNet-5 network provides a higher fault diagnosis accuracy with a less training time in most cases, and the improved 2D LeNet-5 network performs better than improved 1D LeNet-5 network under small training samples and strong noise environment.https://www.mdpi.com/1424-8220/20/6/1693convolution neural networklenet-5 networkfault diagnosisrolling-element bearingvibration signals |
| spellingShingle | Lanjun Wan Yiwei Chen Hongyang Li Changyun Li Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network Sensors convolution neural network lenet-5 network fault diagnosis rolling-element bearing vibration signals |
| title | Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network |
| title_full | Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network |
| title_fullStr | Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network |
| title_full_unstemmed | Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network |
| title_short | Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network |
| title_sort | rolling element bearing fault diagnosis using improved lenet 5 network |
| topic | convolution neural network lenet-5 network fault diagnosis rolling-element bearing vibration signals |
| url | https://www.mdpi.com/1424-8220/20/6/1693 |
| work_keys_str_mv | AT lanjunwan rollingelementbearingfaultdiagnosisusingimprovedlenet5network AT yiweichen rollingelementbearingfaultdiagnosisusingimprovedlenet5network AT hongyangli rollingelementbearingfaultdiagnosisusingimprovedlenet5network AT changyunli rollingelementbearingfaultdiagnosisusingimprovedlenet5network |