Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning
Addressing the problem that it is difficult to extract the features of vibration signal and diagnose the fault of rolling bearing, we propose a novel diagnosis method combining multisynchrosqueezing S transform and faster dictionary learning (MSSST-FDL). Firstly, MSSST is adopted to transform vibrat...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2021/8456991 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550943130910720 |
|---|---|
| author | Guodong Sun Ye Hu Bo Wu Hongyu Zhou |
| author_facet | Guodong Sun Ye Hu Bo Wu Hongyu Zhou |
| author_sort | Guodong Sun |
| collection | DOAJ |
| description | Addressing the problem that it is difficult to extract the features of vibration signal and diagnose the fault of rolling bearing, we propose a novel diagnosis method combining multisynchrosqueezing S transform and faster dictionary learning (MSSST-FDL). Firstly, MSSST is adopted to transform vibration signals into high-resolution time-frequency images. Then, the local binary pattern (LBP) operator is introduced to extract the low-dimensional texture features of time-frequency images, which improves the speed of fault recognition. Finally, nonnegative matrix factorization (NMF) with only one hyperparameter and nonnegative linear equation are used to solve the dictionary learning and feature coding, respectively. The feature coding is input into the classifier for training and recognition. Experiments show that our method performs well on the rolling bearing dataset of Case Western Reserve University (CWRU) and the Society for Machinery Failure Prevention Technology (MFPT). Further, the proposed method is applied to the loudspeaker pure-tone detection dataset, and the loudspeaker anomaly diagnosis is achieved. The diagnosis results verify that our method can meet the needs of practical engineering. |
| format | Article |
| id | doaj-art-e2022717de0c44eeb04887d81584bd60 |
| institution | Kabale University |
| issn | 1070-9622 1875-9203 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-e2022717de0c44eeb04887d81584bd602025-02-03T06:05:28ZengWileyShock and Vibration1070-96221875-92032021-01-01202110.1155/2021/84569918456991Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary LearningGuodong Sun0Ye Hu1Bo Wu2Hongyu Zhou3School of Mechanical Engineering, Hubei University of Technology, Wuhan, Hubei, ChinaSchool of Mechanical Engineering, Hubei University of Technology, Wuhan, Hubei, ChinaShanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, ChinaSchool of Mechanical Engineering, Hubei University of Technology, Wuhan, Hubei, ChinaAddressing the problem that it is difficult to extract the features of vibration signal and diagnose the fault of rolling bearing, we propose a novel diagnosis method combining multisynchrosqueezing S transform and faster dictionary learning (MSSST-FDL). Firstly, MSSST is adopted to transform vibration signals into high-resolution time-frequency images. Then, the local binary pattern (LBP) operator is introduced to extract the low-dimensional texture features of time-frequency images, which improves the speed of fault recognition. Finally, nonnegative matrix factorization (NMF) with only one hyperparameter and nonnegative linear equation are used to solve the dictionary learning and feature coding, respectively. The feature coding is input into the classifier for training and recognition. Experiments show that our method performs well on the rolling bearing dataset of Case Western Reserve University (CWRU) and the Society for Machinery Failure Prevention Technology (MFPT). Further, the proposed method is applied to the loudspeaker pure-tone detection dataset, and the loudspeaker anomaly diagnosis is achieved. The diagnosis results verify that our method can meet the needs of practical engineering.http://dx.doi.org/10.1155/2021/8456991 |
| spellingShingle | Guodong Sun Ye Hu Bo Wu Hongyu Zhou Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning Shock and Vibration |
| title | Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning |
| title_full | Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning |
| title_fullStr | Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning |
| title_full_unstemmed | Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning |
| title_short | Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning |
| title_sort | rolling bearing fault diagnosis method based on multisynchrosqueezing s transform and faster dictionary learning |
| url | http://dx.doi.org/10.1155/2021/8456991 |
| work_keys_str_mv | AT guodongsun rollingbearingfaultdiagnosismethodbasedonmultisynchrosqueezingstransformandfasterdictionarylearning AT yehu rollingbearingfaultdiagnosismethodbasedonmultisynchrosqueezingstransformandfasterdictionarylearning AT bowu rollingbearingfaultdiagnosismethodbasedonmultisynchrosqueezingstransformandfasterdictionarylearning AT hongyuzhou rollingbearingfaultdiagnosismethodbasedonmultisynchrosqueezingstransformandfasterdictionarylearning |