Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis
Fault of rolling bearing signal is a common problem encountered in the production of life. Identifying the fault signal helps to locate the fault location and type quickly, react to the fault in time, and reduce the losses caused by the failure in production. In order to accurately identify the faul...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2023.1180595/full |
| _version_ | 1797852937114877952 |
|---|---|
| author | Nina Zhou Li Wang |
| author_facet | Nina Zhou Li Wang |
| author_sort | Nina Zhou |
| collection | DOAJ |
| description | Fault of rolling bearing signal is a common problem encountered in the production of life. Identifying the fault signal helps to locate the fault location and type quickly, react to the fault in time, and reduce the losses caused by the failure in production. In order to accurately identify the fault signal, this paper presents a triple feature extraction and classification method based on multi-scale dispersion entropy (MDE) and multi-scale permutation entropy (MPE), extracts the features of the signal of rolling bearing when it is working, and uses the classification algorithm to determine whether there is a fault in the bearing and the type of fault. Scale 2 of MDE is combined with scale 1 and scale 2 of MPE as the three features required for the experiment. As a comparison of recognition results, multi-scale entropy (MSE)is introduced. Ten scales of the three entropy are calculated, and all combinations of three feature extraction are obtained. K nearest neighbor algorithm is used for three feature recognition. The result shows that the combination recognition rate proposed in this paper reaches 96.2%, which is the best among all combinations. |
| first_indexed | 2024-04-09T19:42:23Z |
| format | Article |
| id | doaj.art-b200f799333f41f88582e8ed62e009a9 |
| institution | Directory Open Access Journal |
| issn | 2296-424X |
| language | English |
| last_indexed | 2024-04-09T19:42:23Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj.art-b200f799333f41f88582e8ed62e009a92023-04-04T05:13:11ZengFrontiers Media S.A.Frontiers in Physics2296-424X2023-04-011110.3389/fphy.2023.11805951180595Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosisNina Zhou0Li Wang1School of Electronic and Electrical Engineering, Baoji University of Arts and Sciences, Baoji, ChinaSchool of Physical Education, Baoji University of Arts and Sciences, Baoji, ChinaFault of rolling bearing signal is a common problem encountered in the production of life. Identifying the fault signal helps to locate the fault location and type quickly, react to the fault in time, and reduce the losses caused by the failure in production. In order to accurately identify the fault signal, this paper presents a triple feature extraction and classification method based on multi-scale dispersion entropy (MDE) and multi-scale permutation entropy (MPE), extracts the features of the signal of rolling bearing when it is working, and uses the classification algorithm to determine whether there is a fault in the bearing and the type of fault. Scale 2 of MDE is combined with scale 1 and scale 2 of MPE as the three features required for the experiment. As a comparison of recognition results, multi-scale entropy (MSE)is introduced. Ten scales of the three entropy are calculated, and all combinations of three feature extraction are obtained. K nearest neighbor algorithm is used for three feature recognition. The result shows that the combination recognition rate proposed in this paper reaches 96.2%, which is the best among all combinations.https://www.frontiersin.org/articles/10.3389/fphy.2023.1180595/fullrolling bearing signaltriple feature extractionmulti-scale dispersion entropymulti-scale permutation entropyfault diagnosis |
| spellingShingle | Nina Zhou Li Wang Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis Frontiers in Physics rolling bearing signal triple feature extraction multi-scale dispersion entropy multi-scale permutation entropy fault diagnosis |
| title | Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis |
| title_full | Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis |
| title_fullStr | Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis |
| title_full_unstemmed | Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis |
| title_short | Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis |
| title_sort | triple feature extraction method based on multi scale dispersion entropy and multi scale permutation entropy in sound based fault diagnosis |
| topic | rolling bearing signal triple feature extraction multi-scale dispersion entropy multi-scale permutation entropy fault diagnosis |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2023.1180595/full |
| work_keys_str_mv | AT ninazhou triplefeatureextractionmethodbasedonmultiscaledispersionentropyandmultiscalepermutationentropyinsoundbasedfaultdiagnosis AT liwang triplefeatureextractionmethodbasedonmultiscaledispersionentropyandmultiscalepermutationentropyinsoundbasedfaultdiagnosis |