Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning
Deep learning techniques have been widely used to achieve promising results for fault diagnosis. In many real-world fault diagnosis applications, labeled training data (source domain) and unlabeled test data (target domain) have different distributions due to the frequent changes of working conditio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2020/4676701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832556357172068352 |
|---|---|
| author | Jing An Ping Ai Dakun Liu |
| author_facet | Jing An Ping Ai Dakun Liu |
| author_sort | Jing An |
| collection | DOAJ |
| description | Deep learning techniques have been widely used to achieve promising results for fault diagnosis. In many real-world fault diagnosis applications, labeled training data (source domain) and unlabeled test data (target domain) have different distributions due to the frequent changes of working conditions, leading to performance degradation. This study proposes an end-to-end unsupervised domain adaptation bearing fault diagnosis model that combines domain alignment and discriminative feature learning on the basis of a 1D convolutional neural network. Joint training with classification loss, center-based discriminative loss, and correlation alignment loss between the two domains can adapt learned representations in the source domain for application to the target domain. Such joint training can also guarantee domain-invariant features with good intraclass compactness and interclass separability. Meanwhile, the extracted features can efficiently improve the cross-domain testing performance. Experimental results on the Case Western Reserve University bearing datasets confirm the superiority of the proposed method over many existing methods. |
| format | Article |
| id | doaj-art-bf4e380fb2f34e688cfd6c1ff3e5d741 |
| institution | Kabale University |
| issn | 1070-9622 1875-9203 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-bf4e380fb2f34e688cfd6c1ff3e5d7412025-02-03T05:45:46ZengWileyShock and Vibration1070-96221875-92032020-01-01202010.1155/2020/46767014676701Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature LearningJing An0Ping Ai1Dakun Liu2School of Mechanical Engineer, Yancheng Institute of Technology, Yancheng 224051, ChinaCollege of Computer and Information Engineering, Hohai University, Nanjing 211100, ChinaSchool of Mechanical Engineer, Yancheng Institute of Technology, Yancheng 224051, ChinaDeep learning techniques have been widely used to achieve promising results for fault diagnosis. In many real-world fault diagnosis applications, labeled training data (source domain) and unlabeled test data (target domain) have different distributions due to the frequent changes of working conditions, leading to performance degradation. This study proposes an end-to-end unsupervised domain adaptation bearing fault diagnosis model that combines domain alignment and discriminative feature learning on the basis of a 1D convolutional neural network. Joint training with classification loss, center-based discriminative loss, and correlation alignment loss between the two domains can adapt learned representations in the source domain for application to the target domain. Such joint training can also guarantee domain-invariant features with good intraclass compactness and interclass separability. Meanwhile, the extracted features can efficiently improve the cross-domain testing performance. Experimental results on the Case Western Reserve University bearing datasets confirm the superiority of the proposed method over many existing methods.http://dx.doi.org/10.1155/2020/4676701 |
| spellingShingle | Jing An Ping Ai Dakun Liu Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning Shock and Vibration |
| title | Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning |
| title_full | Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning |
| title_fullStr | Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning |
| title_full_unstemmed | Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning |
| title_short | Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning |
| title_sort | deep domain adaptation model for bearing fault diagnosis with domain alignment and discriminative feature learning |
| url | http://dx.doi.org/10.1155/2020/4676701 |
| work_keys_str_mv | AT jingan deepdomainadaptationmodelforbearingfaultdiagnosiswithdomainalignmentanddiscriminativefeaturelearning AT pingai deepdomainadaptationmodelforbearingfaultdiagnosiswithdomainalignmentanddiscriminativefeaturelearning AT dakunliu deepdomainadaptationmodelforbearingfaultdiagnosiswithdomainalignmentanddiscriminativefeaturelearning |