A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data
In actual industrial scenarios, collecting a complete dataset with all fault categories under the same conditions is challenging, leading to a loss in fault category knowledge in single-source domains. Deep learning domain adaptation methods face difficulties in multi-source scenarios due to insuffi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Actuators |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-0825/14/1/24 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589460149108736 |
|---|---|
| author | Juan Tian Shun Zhang Gang Xie Hui Shi |
| author_facet | Juan Tian Shun Zhang Gang Xie Hui Shi |
| author_sort | Juan Tian |
| collection | DOAJ |
| description | In actual industrial scenarios, collecting a complete dataset with all fault categories under the same conditions is challenging, leading to a loss in fault category knowledge in single-source domains. Deep learning domain adaptation methods face difficulties in multi-source scenarios due to insufficient labeled data and significant distribution differences, hindering domain-specific knowledge transfer and reducing fault diagnosis efficiency. To address these issues, the Dynamic Similarity-guided Multi-source Domain Adaptation Network (DS-MDAN) is proposed. This method leverages incomplete data from multiple-source domains to address distribution disparities in deep domain adaptation. It enhances diagnostic performance in the target domain by transferring knowledge across diverse domains. DS-MDAN uses convolution kernels of different scales to extract multi-scale feature information and achieves feature fusion through upsampling and operations like addition and concatenation. Adversarial training with domain and fault classifiers optimizes feature extraction for widely applicable representations. The similarity between source and target domain data is calculated based on features extracted by a shared-weight network, dynamically adjusting the contribution of different source domain data to minimize distribution differences. Finally, matched source and target domain samples are mapped to the same feature space for fault diagnosis. Experimental validation on various bearing fault datasets shows that DS-MDAN improves performance in multiple fault diagnosis tasks, increasing accuracy and demonstrating good generalization capabilities. |
| format | Article |
| id | doaj-art-2e474d7ad0cd4173a6c09ed6fdf37c1a |
| institution | Kabale University |
| issn | 2076-0825 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Actuators |
| spelling | doaj-art-2e474d7ad0cd4173a6c09ed6fdf37c1a2025-01-24T13:15:12ZengMDPI AGActuators2076-08252025-01-011412410.3390/act14010024A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete DataJuan Tian0Shun Zhang1Gang Xie2Hui Shi3School of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaSchool of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaSchool of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaSchool of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaIn actual industrial scenarios, collecting a complete dataset with all fault categories under the same conditions is challenging, leading to a loss in fault category knowledge in single-source domains. Deep learning domain adaptation methods face difficulties in multi-source scenarios due to insufficient labeled data and significant distribution differences, hindering domain-specific knowledge transfer and reducing fault diagnosis efficiency. To address these issues, the Dynamic Similarity-guided Multi-source Domain Adaptation Network (DS-MDAN) is proposed. This method leverages incomplete data from multiple-source domains to address distribution disparities in deep domain adaptation. It enhances diagnostic performance in the target domain by transferring knowledge across diverse domains. DS-MDAN uses convolution kernels of different scales to extract multi-scale feature information and achieves feature fusion through upsampling and operations like addition and concatenation. Adversarial training with domain and fault classifiers optimizes feature extraction for widely applicable representations. The similarity between source and target domain data is calculated based on features extracted by a shared-weight network, dynamically adjusting the contribution of different source domain data to minimize distribution differences. Finally, matched source and target domain samples are mapped to the same feature space for fault diagnosis. Experimental validation on various bearing fault datasets shows that DS-MDAN improves performance in multiple fault diagnosis tasks, increasing accuracy and demonstrating good generalization capabilities.https://www.mdpi.com/2076-0825/14/1/24multi-source domain adaptationfault diagnosisdynamic similarity measureincomplete datarotating machine |
| spellingShingle | Juan Tian Shun Zhang Gang Xie Hui Shi A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data Actuators multi-source domain adaptation fault diagnosis dynamic similarity measure incomplete data rotating machine |
| title | A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data |
| title_full | A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data |
| title_fullStr | A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data |
| title_full_unstemmed | A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data |
| title_short | A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data |
| title_sort | multi source domain adaptation method for bearing fault diagnosis with dynamically similarity guidance on incomplete data |
| topic | multi-source domain adaptation fault diagnosis dynamic similarity measure incomplete data rotating machine |
| url | https://www.mdpi.com/2076-0825/14/1/24 |
| work_keys_str_mv | AT juantian amultisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata AT shunzhang amultisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata AT gangxie amultisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata AT huishi amultisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata AT juantian multisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata AT shunzhang multisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata AT gangxie multisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata AT huishi multisourcedomainadaptationmethodforbearingfaultdiagnosiswithdynamicallysimilarityguidanceonincompletedata |