A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES
Aiming at the problem of graphical feature representation of one-dimensional mechanical vibration signals, a bearing fault diagnosis method based on symmetric polar coordinates and residual network migration learning is proposed, which combines the powerful image classification and recognition abili...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Strength
2022-01-01
|
| Series: | Jixie qiangdu |
| Subjects: | |
| Online Access: | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2022.03.005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536011988893696 |
|---|---|
| author | WU DingHai WANG HuaiGuang SONG Bin ZHANG YunQiang |
| author_facet | WU DingHai WANG HuaiGuang SONG Bin ZHANG YunQiang |
| author_sort | WU DingHai |
| collection | DOAJ |
| description | Aiming at the problem of graphical feature representation of one-dimensional mechanical vibration signals, a bearing fault diagnosis method based on symmetric polar coordinates and residual network migration learning is proposed, which combines the powerful image classification and recognition ability of convolution neural network. Therefore, a bearing fault diagnosis method based on symmetric polar coordinates and residual network transfer learning is proposed in this paper. In order to highlight the fault characteristics of bearing vibration signals and take into account the calculation efficiency, the proposed method uses the symmetric polar coordinate method to convert the one-dimensional mechanical vibration signal into a mirror-symmetric snowflake map quickly and the transformation parameters and data sampling length are optimized synchronously by NSGA-II to obtain the image features with better distinguishability. Then, the transfer learning of residual network is used to train and classify. The bearing dataset of Case Western Reserve University which includes different rotational speeds and load is used to verify this method and a good recognition effect has been achieved. |
| format | Article |
| id | doaj-art-515a71ed9fd94b14939184fa8359f49f |
| institution | Kabale University |
| issn | 1001-9669 |
| language | zho |
| publishDate | 2022-01-01 |
| publisher | Editorial Office of Journal of Mechanical Strength |
| record_format | Article |
| series | Jixie qiangdu |
| spelling | doaj-art-515a71ed9fd94b14939184fa8359f49f2025-01-15T02:24:10ZzhoEditorial Office of Journal of Mechanical StrengthJixie qiangdu1001-96692022-01-014454154629912742A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATESWU DingHaiWANG HuaiGuangSONG BinZHANG YunQiangAiming at the problem of graphical feature representation of one-dimensional mechanical vibration signals, a bearing fault diagnosis method based on symmetric polar coordinates and residual network migration learning is proposed, which combines the powerful image classification and recognition ability of convolution neural network. Therefore, a bearing fault diagnosis method based on symmetric polar coordinates and residual network transfer learning is proposed in this paper. In order to highlight the fault characteristics of bearing vibration signals and take into account the calculation efficiency, the proposed method uses the symmetric polar coordinate method to convert the one-dimensional mechanical vibration signal into a mirror-symmetric snowflake map quickly and the transformation parameters and data sampling length are optimized synchronously by NSGA-II to obtain the image features with better distinguishability. Then, the transfer learning of residual network is used to train and classify. The bearing dataset of Case Western Reserve University which includes different rotational speeds and load is used to verify this method and a good recognition effect has been achieved.http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2022.03.005Fault diagnosisSymmetric polar coordinatesFeature extractionTransfer learningResidual network |
| spellingShingle | WU DingHai WANG HuaiGuang SONG Bin ZHANG YunQiang A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES Jixie qiangdu Fault diagnosis Symmetric polar coordinates Feature extraction Transfer learning Residual network |
| title | A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES |
| title_full | A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES |
| title_fullStr | A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES |
| title_full_unstemmed | A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES |
| title_short | A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES |
| title_sort | bearing deep learning transfer diagnosis method based on optimization of symmetric polar coordinates |
| topic | Fault diagnosis Symmetric polar coordinates Feature extraction Transfer learning Residual network |
| url | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2022.03.005 |
| work_keys_str_mv | AT wudinghai abearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates AT wanghuaiguang abearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates AT songbin abearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates AT zhangyunqiang abearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates AT wudinghai bearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates AT wanghuaiguang bearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates AT songbin bearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates AT zhangyunqiang bearingdeeplearningtransferdiagnosismethodbasedonoptimizationofsymmetricpolarcoordinates |