Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANN
To address the problems of feature extraction, cost of obtaining labeled samples, and large differences in domain distribution in bearing fault diagnosis on variable operating conditions, an unsupervised domain-adaptive bearing fault diagnosis method based on migration learning using MSACNN-IJMMD-DA...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/13/7/618 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849246317369360384 |
|---|---|
| author | Xiaoxu Li Jiahao Wang Jianqiang Wang Jixuan Wang Qinghua Li Xuelian Yu Jiaming Chen |
| author_facet | Xiaoxu Li Jiahao Wang Jianqiang Wang Jixuan Wang Qinghua Li Xuelian Yu Jiaming Chen |
| author_sort | Xiaoxu Li |
| collection | DOAJ |
| description | To address the problems of feature extraction, cost of obtaining labeled samples, and large differences in domain distribution in bearing fault diagnosis on variable operating conditions, an unsupervised domain-adaptive bearing fault diagnosis method based on migration learning using MSACNN-IJMMD-DANN (multi-scale and attention-based convolutional neural network, MSACNN, improved joint maximum mean discrepancy, IJMMD, domain adversarial neural network, DANN) is proposed. Firstly, in order to extract fault-type features from the source domain and target domain, this paper establishes a MSACNN based on multi-scale and attention mechanisms. Secondly, to reduce the feature distribution difference between the source and target domains and address the issue of domain distribution differences, the joint maximum mean discrepancy and correlation alignment approaches are used to create the metric criterion. Then, the adversarial loss mechanism in DANN is introduced to reduce the interference of weakly correlated domain features for better fault diagnosis and identification. Finally, the method is validated using bearing datasets from Case Western Reserve University, Jiangnan University, and our laboratory. The experimental results demonstrated that the method achieved higher accuracy across different migration tasks, providing an effective solution for bearing fault diagnosis in industrial environments with varying operating conditions. |
| format | Article |
| id | doaj-art-59b0eb91f43a499c87f2f4988c8a29ce |
| institution | Kabale University |
| issn | 2075-1702 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-59b0eb91f43a499c87f2f4988c8a29ce2025-08-20T03:58:31ZengMDPI AGMachines2075-17022025-07-0113761810.3390/machines13070618Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANNXiaoxu Li0Jiahao Wang1Jianqiang Wang2Jixuan Wang3Qinghua Li4Xuelian Yu5Jiaming Chen6College of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaTo address the problems of feature extraction, cost of obtaining labeled samples, and large differences in domain distribution in bearing fault diagnosis on variable operating conditions, an unsupervised domain-adaptive bearing fault diagnosis method based on migration learning using MSACNN-IJMMD-DANN (multi-scale and attention-based convolutional neural network, MSACNN, improved joint maximum mean discrepancy, IJMMD, domain adversarial neural network, DANN) is proposed. Firstly, in order to extract fault-type features from the source domain and target domain, this paper establishes a MSACNN based on multi-scale and attention mechanisms. Secondly, to reduce the feature distribution difference between the source and target domains and address the issue of domain distribution differences, the joint maximum mean discrepancy and correlation alignment approaches are used to create the metric criterion. Then, the adversarial loss mechanism in DANN is introduced to reduce the interference of weakly correlated domain features for better fault diagnosis and identification. Finally, the method is validated using bearing datasets from Case Western Reserve University, Jiangnan University, and our laboratory. The experimental results demonstrated that the method achieved higher accuracy across different migration tasks, providing an effective solution for bearing fault diagnosis in industrial environments with varying operating conditions.https://www.mdpi.com/2075-1702/13/7/618fault diagnosistransfer learningmulti-scale convolutionattention mechanismJMMDunsupervised domain adaptation |
| spellingShingle | Xiaoxu Li Jiahao Wang Jianqiang Wang Jixuan Wang Qinghua Li Xuelian Yu Jiaming Chen Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANN Machines fault diagnosis transfer learning multi-scale convolution attention mechanism JMMD unsupervised domain adaptation |
| title | Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANN |
| title_full | Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANN |
| title_fullStr | Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANN |
| title_full_unstemmed | Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANN |
| title_short | Research on Unsupervised Domain Adaptive Bearing Fault Diagnosis Method Based on Migration Learning Using MSACNN-IJMMD-DANN |
| title_sort | research on unsupervised domain adaptive bearing fault diagnosis method based on migration learning using msacnn ijmmd dann |
| topic | fault diagnosis transfer learning multi-scale convolution attention mechanism JMMD unsupervised domain adaptation |
| url | https://www.mdpi.com/2075-1702/13/7/618 |
| work_keys_str_mv | AT xiaoxuli researchonunsuperviseddomainadaptivebearingfaultdiagnosismethodbasedonmigrationlearningusingmsacnnijmmddann AT jiahaowang researchonunsuperviseddomainadaptivebearingfaultdiagnosismethodbasedonmigrationlearningusingmsacnnijmmddann AT jianqiangwang researchonunsuperviseddomainadaptivebearingfaultdiagnosismethodbasedonmigrationlearningusingmsacnnijmmddann AT jixuanwang researchonunsuperviseddomainadaptivebearingfaultdiagnosismethodbasedonmigrationlearningusingmsacnnijmmddann AT qinghuali researchonunsuperviseddomainadaptivebearingfaultdiagnosismethodbasedonmigrationlearningusingmsacnnijmmddann AT xuelianyu researchonunsuperviseddomainadaptivebearingfaultdiagnosismethodbasedonmigrationlearningusingmsacnnijmmddann AT jiamingchen researchonunsuperviseddomainadaptivebearingfaultdiagnosismethodbasedonmigrationlearningusingmsacnnijmmddann |