A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating Conditions
In the actual industrial scenarios, most existing fault diagnosis approaches are faced with two challenges, insufficient labeled training data and distribution divergences between training and testing datasets. For the above issues, a new transferable fault diagnosis approach of rotating machinery b...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2021/7383255 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560868377755648 |
|---|---|
| author | Fei Dong Xiao Yu Xinguo Shi Ke Liu Zhaoli Wu Wanli Yu |
| author_facet | Fei Dong Xiao Yu Xinguo Shi Ke Liu Zhaoli Wu Wanli Yu |
| author_sort | Fei Dong |
| collection | DOAJ |
| description | In the actual industrial scenarios, most existing fault diagnosis approaches are faced with two challenges, insufficient labeled training data and distribution divergences between training and testing datasets. For the above issues, a new transferable fault diagnosis approach of rotating machinery based on deep autoencoder and dominant features selection is proposed in this article. First, maximal overlap discrete wavelet packet transform is applied for signals processing and mix-domains statistical feature extraction. Second, dominant features selection by importance score and differences between domains is proposed to select dominant features with high fault-discriminative ability and domain invariance. Then, selected dominant features are used for pretraining deep autoencoder (source model), which helps in enhancing the fault representative ability of deep features. The parameters of the source model are transferred to the target model, and normal state features from target domain are adopted for fine-tuning the target model. Finally, the target model is applied for fault patterns classification. Motor and bearing fault datasets are used for a series of experiments, and the results verify that the proposed methods have better cross-domain diagnosis performance than comparative models. |
| format | Article |
| id | doaj-art-524f7352e53946aa84a70ce2a4d699ab |
| institution | Kabale University |
| issn | 1875-9203 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-524f7352e53946aa84a70ce2a4d699ab2025-02-03T01:26:26ZengWileyShock and Vibration1875-92032021-01-01202110.1155/2021/7383255A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating ConditionsFei Dong0Xiao Yu1Xinguo Shi2Ke Liu3Zhaoli Wu4Wanli Yu5School of InternetIOT Perception Mine Research CenterCenter of Information TechnologyCenter of Information TechnologyJiangsu Collaborative Innovation Center for Building Energy Saving and Construction TechnologyInstitute of Electrodynamics and MicroelectronicsIn the actual industrial scenarios, most existing fault diagnosis approaches are faced with two challenges, insufficient labeled training data and distribution divergences between training and testing datasets. For the above issues, a new transferable fault diagnosis approach of rotating machinery based on deep autoencoder and dominant features selection is proposed in this article. First, maximal overlap discrete wavelet packet transform is applied for signals processing and mix-domains statistical feature extraction. Second, dominant features selection by importance score and differences between domains is proposed to select dominant features with high fault-discriminative ability and domain invariance. Then, selected dominant features are used for pretraining deep autoencoder (source model), which helps in enhancing the fault representative ability of deep features. The parameters of the source model are transferred to the target model, and normal state features from target domain are adopted for fine-tuning the target model. Finally, the target model is applied for fault patterns classification. Motor and bearing fault datasets are used for a series of experiments, and the results verify that the proposed methods have better cross-domain diagnosis performance than comparative models.http://dx.doi.org/10.1155/2021/7383255 |
| spellingShingle | Fei Dong Xiao Yu Xinguo Shi Ke Liu Zhaoli Wu Wanli Yu A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating Conditions Shock and Vibration |
| title | A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating Conditions |
| title_full | A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating Conditions |
| title_fullStr | A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating Conditions |
| title_full_unstemmed | A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating Conditions |
| title_short | A New Transferable Fault Diagnosis Approach of Rotating Machinery Based on Deep Autoencoder and Dominant Features Selection under Different Operating Conditions |
| title_sort | new transferable fault diagnosis approach of rotating machinery based on deep autoencoder and dominant features selection under different operating conditions |
| url | http://dx.doi.org/10.1155/2021/7383255 |
| work_keys_str_mv | AT feidong anewtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT xiaoyu anewtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT xinguoshi anewtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT keliu anewtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT zhaoliwu anewtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT wanliyu anewtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT feidong newtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT xiaoyu newtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT xinguoshi newtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT keliu newtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT zhaoliwu newtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions AT wanliyu newtransferablefaultdiagnosisapproachofrotatingmachinerybasedondeepautoencoderanddominantfeaturesselectionunderdifferentoperatingconditions |