Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation Classification
Because of the cyclic symmetric structure of rolling bearings, its vibration signals are regular when the rolling bearing is working in a normal state. But when the rolling bearing fails, whether the outer race fault or the inner race fault, the symmetry of the rolling bearing is broken and the faul...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/10/12/730 |
| _version_ | 1811184950167207936 |
|---|---|
| author | Mingtao Ge Jie Wang Yicun Xu Fangfang Zhang Ke Bai Xiangyang Ren |
| author_facet | Mingtao Ge Jie Wang Yicun Xu Fangfang Zhang Ke Bai Xiangyang Ren |
| author_sort | Mingtao Ge |
| collection | DOAJ |
| description | Because of the cyclic symmetric structure of rolling bearings, its vibration signals are regular when the rolling bearing is working in a normal state. But when the rolling bearing fails, whether the outer race fault or the inner race fault, the symmetry of the rolling bearing is broken and the fault destroys the rolling bearing’s stable working state. Whenever the bearing passes through the fault point, it will send out vibration signals representing the fault characteristics. These signals are often non-linear, non-stationary, and full of Gaussian noise which are quite different from normal signals. According to this, the sub-modal obtained by empirical wavelet transform (EWT), secondary decomposition is tested by the Gaussian distribution hypothesis test. It is regarded that sub-modal following Gaussian distribution is Gaussian noise which is filtered during signal reconstruction. Then by taking advantage of the ambiguity function superiority in non-stationary signal processing and combining correlation coefficient, an ambiguity correlation classifier is constructed. After training, the classifier can recognize vibration signals of rolling bearings under different working conditions, so that the purpose of identifying rolling bearing faults can be achieved. Finally, the method effect was verified by experiments. |
| first_indexed | 2024-04-11T13:21:58Z |
| format | Article |
| id | doaj.art-fc6f407491aa45c68983ed5f767cf257 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-11T13:21:58Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-fc6f407491aa45c68983ed5f767cf2572022-12-22T04:22:11ZengMDPI AGSymmetry2073-89942018-12-01101273010.3390/sym10120730sym10120730Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation ClassificationMingtao Ge0Jie Wang1Yicun Xu2Fangfang Zhang3Ke Bai4Xiangyang Ren5School of Electrical Engineering, Zhengzhou University, Zhengzhou 50001, ChinaSchool of Electrical Engineering, Zhengzhou University, Zhengzhou 50001, ChinaSchool of Mechanical Engineering, Zhengzhou University, Zhengzhou 50001, ChinaSchool of Electrical Engineering, Zhengzhou University, Zhengzhou 50001, ChinaSchool of Electrical Engineering, Zhengzhou University, Zhengzhou 50001, ChinaSchool of Electrical Engineering, Zhengzhou University, Zhengzhou 50001, ChinaBecause of the cyclic symmetric structure of rolling bearings, its vibration signals are regular when the rolling bearing is working in a normal state. But when the rolling bearing fails, whether the outer race fault or the inner race fault, the symmetry of the rolling bearing is broken and the fault destroys the rolling bearing’s stable working state. Whenever the bearing passes through the fault point, it will send out vibration signals representing the fault characteristics. These signals are often non-linear, non-stationary, and full of Gaussian noise which are quite different from normal signals. According to this, the sub-modal obtained by empirical wavelet transform (EWT), secondary decomposition is tested by the Gaussian distribution hypothesis test. It is regarded that sub-modal following Gaussian distribution is Gaussian noise which is filtered during signal reconstruction. Then by taking advantage of the ambiguity function superiority in non-stationary signal processing and combining correlation coefficient, an ambiguity correlation classifier is constructed. After training, the classifier can recognize vibration signals of rolling bearings under different working conditions, so that the purpose of identifying rolling bearing faults can be achieved. Finally, the method effect was verified by experiments.https://www.mdpi.com/2073-8994/10/12/730rolling bearingsfault diagnosisempirical wavelet transformGaussian noiseambiguity function |
| spellingShingle | Mingtao Ge Jie Wang Yicun Xu Fangfang Zhang Ke Bai Xiangyang Ren Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation Classification Symmetry rolling bearings fault diagnosis empirical wavelet transform Gaussian noise ambiguity function |
| title | Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation Classification |
| title_full | Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation Classification |
| title_fullStr | Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation Classification |
| title_full_unstemmed | Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation Classification |
| title_short | Rolling Bearing Fault Diagnosis Based on EWT Sub-Modal Hypothesis Test and Ambiguity Correlation Classification |
| title_sort | rolling bearing fault diagnosis based on ewt sub modal hypothesis test and ambiguity correlation classification |
| topic | rolling bearings fault diagnosis empirical wavelet transform Gaussian noise ambiguity function |
| url | https://www.mdpi.com/2073-8994/10/12/730 |
| work_keys_str_mv | AT mingtaoge rollingbearingfaultdiagnosisbasedonewtsubmodalhypothesistestandambiguitycorrelationclassification AT jiewang rollingbearingfaultdiagnosisbasedonewtsubmodalhypothesistestandambiguitycorrelationclassification AT yicunxu rollingbearingfaultdiagnosisbasedonewtsubmodalhypothesistestandambiguitycorrelationclassification AT fangfangzhang rollingbearingfaultdiagnosisbasedonewtsubmodalhypothesistestandambiguitycorrelationclassification AT kebai rollingbearingfaultdiagnosisbasedonewtsubmodalhypothesistestandambiguitycorrelationclassification AT xiangyangren rollingbearingfaultdiagnosisbasedonewtsubmodalhypothesistestandambiguitycorrelationclassification |