A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing
To enhance the performance of deep auto-encoder (AE) under complex working conditions, a novel deep auto-encoder network method for rolling bearing fault diagnosis is proposed in this paper. First, multiscale analysis is adopted to extract the multiscale features from the raw vibration signals of ro...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2020-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2020/8891905 |
| id |
doaj-d0795c043070468ea50d9c9225013f68 |
|---|---|
| record_format |
Article |
| spelling |
doaj-d0795c043070468ea50d9c9225013f682020-11-25T03:41:08ZengHindawi LimitedShock and Vibration1070-96221875-92032020-01-01202010.1155/2020/88919058891905A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling BearingJinyu Tong0Jin Luo1Haiyang Pan2Jinde Zheng3Qing Zhang4College of Mechanics and Materials, Hohai University, Nanjing 211100, ChinaSchool of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui 243002, ChinaSchool of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui 243002, ChinaSchool of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui 243002, ChinaCollege of Mechanics and Materials, Hohai University, Nanjing 211100, ChinaTo enhance the performance of deep auto-encoder (AE) under complex working conditions, a novel deep auto-encoder network method for rolling bearing fault diagnosis is proposed in this paper. First, multiscale analysis is adopted to extract the multiscale features from the raw vibration signals of rolling bearing. Second, the sparse penalty term and contractive penalty term are used simultaneously to regularize the loss function of auto-encoder to enhance the feature learning ability of networks. Finally, the cuckoo search algorithm (CS) is used to find the optimal hyperparameters automatically. The proposed method is applied to the experimental data analysis. The results indicate that the proposed method could more effectively distinguish fault categories and severities of rolling bearings under different working conditions than other methods.http://dx.doi.org/10.1155/2020/8891905 |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Jinyu Tong Jin Luo Haiyang Pan Jinde Zheng Qing Zhang |
| spellingShingle |
Jinyu Tong Jin Luo Haiyang Pan Jinde Zheng Qing Zhang A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing Shock and Vibration |
| author_facet |
Jinyu Tong Jin Luo Haiyang Pan Jinde Zheng Qing Zhang |
| author_sort |
Jinyu Tong |
| title |
A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing |
| title_short |
A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing |
| title_full |
A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing |
| title_fullStr |
A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing |
| title_full_unstemmed |
A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing |
| title_sort |
novel cuckoo search optimized deep auto-encoder network-based fault diagnosis method for rolling bearing |
| publisher |
Hindawi Limited |
| series |
Shock and Vibration |
| issn |
1070-9622 1875-9203 |
| publishDate |
2020-01-01 |
| description |
To enhance the performance of deep auto-encoder (AE) under complex working conditions, a novel deep auto-encoder network method for rolling bearing fault diagnosis is proposed in this paper. First, multiscale analysis is adopted to extract the multiscale features from the raw vibration signals of rolling bearing. Second, the sparse penalty term and contractive penalty term are used simultaneously to regularize the loss function of auto-encoder to enhance the feature learning ability of networks. Finally, the cuckoo search algorithm (CS) is used to find the optimal hyperparameters automatically. The proposed method is applied to the experimental data analysis. The results indicate that the proposed method could more effectively distinguish fault categories and severities of rolling bearings under different working conditions than other methods. |
| url |
http://dx.doi.org/10.1155/2020/8891905 |
| work_keys_str_mv |
AT jinyutong anovelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT jinluo anovelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT haiyangpan anovelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT jindezheng anovelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT qingzhang anovelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT jinyutong novelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT jinluo novelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT haiyangpan novelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT jindezheng novelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing AT qingzhang novelcuckoosearchoptimizeddeepautoencodernetworkbasedfaultdiagnosismethodforrollingbearing |
| _version_ |
1715146475459051520 |