A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP
In view of the problem of difficulties in extracting low-dimensional sensitive features from rolling bearing vibration signals, a rolling bearing fault feature extraction method based on logistic regression optimization variation mode decomposition(VMD) and uniform manifold approximation and project...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2023-06-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2023.06.019 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841547008444203008 |
|---|---|
| author | Liu Junli Miao Bingrong Zhang Ying Li Yongjian Huang Zhong |
| author_facet | Liu Junli Miao Bingrong Zhang Ying Li Yongjian Huang Zhong |
| author_sort | Liu Junli |
| collection | DOAJ |
| description | In view of the problem of difficulties in extracting low-dimensional sensitive features from rolling bearing vibration signals, a rolling bearing fault feature extraction method based on logistic regression optimization variation mode decomposition(VMD) and uniform manifold approximation and projection(UMAP) is proposed. Firstly,the method divides the original data into samples by the moving window method, and completes the construction of the training set as well as the test set. Secondly, a part of the training set is randomly selected for VMD with different number of modal decompositions, and features are extracted for each layer of sub-signals to complete the construction of multiple feature sets. Then, the complex correlation coefficients between each feature and the label in each feature set are calculated by logistic regression to determine the number of modal decompositions and highly correlated features, which are applied to the training set and the test set to obtain the high-dimensional feature data set. Finally, UMAP is used to obtain low-dimensional features with high discriminative power to complete the final feature set construction. Using the recognition accuracy of three commonly used intelligent algorithm and the ratio of intra-class cosine distance and inter-class cosine distance in the tested feature set as evaluation indexes, the results show that the method not only achieves effectively extract features of various bearing failures, but also has good noise immunity, which is of certain reference value for the feature extraction in the practical bearing fault diagnosis. |
| format | Article |
| id | doaj-art-183f87e513224285ba601956902cfbfa |
| institution | Kabale University |
| issn | 1004-2539 |
| language | zho |
| publishDate | 2023-06-01 |
| publisher | Editorial Office of Journal of Mechanical Transmission |
| record_format | Article |
| series | Jixie chuandong |
| spelling | doaj-art-183f87e513224285ba601956902cfbfa2025-01-10T14:58:18ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392023-06-014713013838804179A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAPLiu JunliMiao BingrongZhang YingLi YongjianHuang ZhongIn view of the problem of difficulties in extracting low-dimensional sensitive features from rolling bearing vibration signals, a rolling bearing fault feature extraction method based on logistic regression optimization variation mode decomposition(VMD) and uniform manifold approximation and projection(UMAP) is proposed. Firstly,the method divides the original data into samples by the moving window method, and completes the construction of the training set as well as the test set. Secondly, a part of the training set is randomly selected for VMD with different number of modal decompositions, and features are extracted for each layer of sub-signals to complete the construction of multiple feature sets. Then, the complex correlation coefficients between each feature and the label in each feature set are calculated by logistic regression to determine the number of modal decompositions and highly correlated features, which are applied to the training set and the test set to obtain the high-dimensional feature data set. Finally, UMAP is used to obtain low-dimensional features with high discriminative power to complete the final feature set construction. Using the recognition accuracy of three commonly used intelligent algorithm and the ratio of intra-class cosine distance and inter-class cosine distance in the tested feature set as evaluation indexes, the results show that the method not only achieves effectively extract features of various bearing failures, but also has good noise immunity, which is of certain reference value for the feature extraction in the practical bearing fault diagnosis.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2023.06.019Fault diagnosisRolling bearingVMDLogistic regressionUMAP |
| spellingShingle | Liu Junli Miao Bingrong Zhang Ying Li Yongjian Huang Zhong A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP Jixie chuandong Fault diagnosis Rolling bearing VMD Logistic regression UMAP |
| title | A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP |
| title_full | A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP |
| title_fullStr | A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP |
| title_full_unstemmed | A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP |
| title_short | A Fault Feature Extraction Method of Rolling Bearings Based on Optimized VMD and UMAP |
| title_sort | fault feature extraction method of rolling bearings based on optimized vmd and umap |
| topic | Fault diagnosis Rolling bearing VMD Logistic regression UMAP |
| url | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2023.06.019 |
| work_keys_str_mv | AT liujunli afaultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT miaobingrong afaultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT zhangying afaultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT liyongjian afaultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT huangzhong afaultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT liujunli faultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT miaobingrong faultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT zhangying faultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT liyongjian faultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap AT huangzhong faultfeatureextractionmethodofrollingbearingsbasedonoptimizedvmdandumap |