Multidomain Feature Fusion Network for Fault Diagnosis of Rolling Machinery
Mechanical vibration constitutes a valuable cue for performing fault diagnosis as it is directly related to the transient regime of rolling machinery. This study establishes a multidomain feature fusion network (MFFN) to extract and fuse multidomain features through a novel multistream architecture....
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2022/5478274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558393041092608 |
|---|---|
| author | Dewei Yang Kefa Zhou Feng Qi Kai Dong |
| author_facet | Dewei Yang Kefa Zhou Feng Qi Kai Dong |
| author_sort | Dewei Yang |
| collection | DOAJ |
| description | Mechanical vibration constitutes a valuable cue for performing fault diagnosis as it is directly related to the transient regime of rolling machinery. This study establishes a multidomain feature fusion network (MFFN) to extract and fuse multidomain features through a novel multistream architecture. Three primary features are simultaneously extracted from the time, frequency, and time-frequency domains. Then, highly representative features are extracted via three convolutional branches in one- or two-dimensional spaces. A novel squeeze-connection-excitation (SCE) module is proposed to adaptively fuse features in the three domains. The advantage offered by the proposed method is that it can leverage cues from the raw vibration signal, resulting in accurate fault diagnosis. Experimental results comprehensively demonstrate and analyze the high accuracy and generalization achieved by this MFFN-based fault diagnosis method. |
| format | Article |
| id | doaj-art-796f1bbce463413bb456f0b8692e5bf1 |
| institution | Kabale University |
| issn | 1875-9203 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-796f1bbce463413bb456f0b8692e5bf12025-02-03T01:32:33ZengWileyShock and Vibration1875-92032022-01-01202210.1155/2022/5478274Multidomain Feature Fusion Network for Fault Diagnosis of Rolling MachineryDewei Yang0Kefa Zhou1Feng Qi2Kai Dong3Nanjing Hydraulic Research InstituteNanjing Hydraulic Research InstituteNanjing Hydraulic Research InstituteNanjing Hydraulic Research InstituteMechanical vibration constitutes a valuable cue for performing fault diagnosis as it is directly related to the transient regime of rolling machinery. This study establishes a multidomain feature fusion network (MFFN) to extract and fuse multidomain features through a novel multistream architecture. Three primary features are simultaneously extracted from the time, frequency, and time-frequency domains. Then, highly representative features are extracted via three convolutional branches in one- or two-dimensional spaces. A novel squeeze-connection-excitation (SCE) module is proposed to adaptively fuse features in the three domains. The advantage offered by the proposed method is that it can leverage cues from the raw vibration signal, resulting in accurate fault diagnosis. Experimental results comprehensively demonstrate and analyze the high accuracy and generalization achieved by this MFFN-based fault diagnosis method.http://dx.doi.org/10.1155/2022/5478274 |
| spellingShingle | Dewei Yang Kefa Zhou Feng Qi Kai Dong Multidomain Feature Fusion Network for Fault Diagnosis of Rolling Machinery Shock and Vibration |
| title | Multidomain Feature Fusion Network for Fault Diagnosis of Rolling Machinery |
| title_full | Multidomain Feature Fusion Network for Fault Diagnosis of Rolling Machinery |
| title_fullStr | Multidomain Feature Fusion Network for Fault Diagnosis of Rolling Machinery |
| title_full_unstemmed | Multidomain Feature Fusion Network for Fault Diagnosis of Rolling Machinery |
| title_short | Multidomain Feature Fusion Network for Fault Diagnosis of Rolling Machinery |
| title_sort | multidomain feature fusion network for fault diagnosis of rolling machinery |
| url | http://dx.doi.org/10.1155/2022/5478274 |
| work_keys_str_mv | AT deweiyang multidomainfeaturefusionnetworkforfaultdiagnosisofrollingmachinery AT kefazhou multidomainfeaturefusionnetworkforfaultdiagnosisofrollingmachinery AT fengqi multidomainfeaturefusionnetworkforfaultdiagnosisofrollingmachinery AT kaidong multidomainfeaturefusionnetworkforfaultdiagnosisofrollingmachinery |