VFQB: A Novel Deep Learning Model for Rolling Bearing Fault Diagnosis
In rolling bearing fault diagnosis, weak features are often masked by complex environmental conditions, blurring the original fault signals and reducing diagnostic accuracy. To address this issue, we propose the VMD/FFT-Quadratic-BiGRU diagnostic model. First, the original vibration signals are proc...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/9/2678 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850136431330066432 |
|---|---|
| author | Zhiru Xiao Yanfang Xu Junjie Cui |
| author_facet | Zhiru Xiao Yanfang Xu Junjie Cui |
| author_sort | Zhiru Xiao |
| collection | DOAJ |
| description | In rolling bearing fault diagnosis, weak features are often masked by complex environmental conditions, blurring the original fault signals and reducing diagnostic accuracy. To address this issue, we propose the VMD/FFT-Quadratic-BiGRU diagnostic model. First, the original vibration signals are processed with variational mode decomposition (VMD) and fast Fourier transform (FFT) and then stacked as quadratic neural network inputs. Next, a Bidirectional Gated Recurrent Unit (BiGRU) module is introduced to capture the temporal characteristics of the feature signals. An attention mechanism is then applied to assign weights to the hidden layers of the BiGRU network. Finally, fault diagnosis is performed using a fully connected layer and softmax classifier. Experimental results demonstrate that this model significantly enhances the ability to capture weak fault features in complex environments. The fault diagnosis accuracy reaches 100% on both datasets, showing improvements of 2.68% and 1.58% over models without the quadratic network. Additionally, comparisons with other models in noisy environments show that the proposed model exhibits superior noise suppression capabilities, further highlighting its robustness and diagnostic accuracy. |
| format | Article |
| id | doaj-art-d3746f1dc00a45dbb9dc110c2d0d3dd3 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-d3746f1dc00a45dbb9dc110c2d0d3dd32025-08-20T02:31:08ZengMDPI AGSensors1424-82202025-04-01259267810.3390/s25092678VFQB: A Novel Deep Learning Model for Rolling Bearing Fault DiagnosisZhiru Xiao0Yanfang Xu1Junjie Cui2College of Mechatronic Engineering, North University of China, Taiyuan 030051, ChinaCollege of Mechatronic Engineering, North University of China, Taiyuan 030051, ChinaCollege of Mechatronic Engineering, North University of China, Taiyuan 030051, ChinaIn rolling bearing fault diagnosis, weak features are often masked by complex environmental conditions, blurring the original fault signals and reducing diagnostic accuracy. To address this issue, we propose the VMD/FFT-Quadratic-BiGRU diagnostic model. First, the original vibration signals are processed with variational mode decomposition (VMD) and fast Fourier transform (FFT) and then stacked as quadratic neural network inputs. Next, a Bidirectional Gated Recurrent Unit (BiGRU) module is introduced to capture the temporal characteristics of the feature signals. An attention mechanism is then applied to assign weights to the hidden layers of the BiGRU network. Finally, fault diagnosis is performed using a fully connected layer and softmax classifier. Experimental results demonstrate that this model significantly enhances the ability to capture weak fault features in complex environments. The fault diagnosis accuracy reaches 100% on both datasets, showing improvements of 2.68% and 1.58% over models without the quadratic network. Additionally, comparisons with other models in noisy environments show that the proposed model exhibits superior noise suppression capabilities, further highlighting its robustness and diagnostic accuracy.https://www.mdpi.com/1424-8220/25/9/2678fault diagnosisvariational mode decompositionfast Fourier transformbidirectional gated recurrent unitquadratic neural network |
| spellingShingle | Zhiru Xiao Yanfang Xu Junjie Cui VFQB: A Novel Deep Learning Model for Rolling Bearing Fault Diagnosis Sensors fault diagnosis variational mode decomposition fast Fourier transform bidirectional gated recurrent unit quadratic neural network |
| title | VFQB: A Novel Deep Learning Model for Rolling Bearing Fault Diagnosis |
| title_full | VFQB: A Novel Deep Learning Model for Rolling Bearing Fault Diagnosis |
| title_fullStr | VFQB: A Novel Deep Learning Model for Rolling Bearing Fault Diagnosis |
| title_full_unstemmed | VFQB: A Novel Deep Learning Model for Rolling Bearing Fault Diagnosis |
| title_short | VFQB: A Novel Deep Learning Model for Rolling Bearing Fault Diagnosis |
| title_sort | vfqb a novel deep learning model for rolling bearing fault diagnosis |
| topic | fault diagnosis variational mode decomposition fast Fourier transform bidirectional gated recurrent unit quadratic neural network |
| url | https://www.mdpi.com/1424-8220/25/9/2678 |
| work_keys_str_mv | AT zhiruxiao vfqbanoveldeeplearningmodelforrollingbearingfaultdiagnosis AT yanfangxu vfqbanoveldeeplearningmodelforrollingbearingfaultdiagnosis AT junjiecui vfqbanoveldeeplearningmodelforrollingbearingfaultdiagnosis |