Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural Network
An artificial-intelligence (AI)-based method for fault diagnosis is a strong candidate for industrial applications in the health management of rolling bearings. However, traditional fault diagnosis methods fail to improve the detection accuracy because they only extract a single feature and have lim...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/10/12/1145 |
| _version_ | 1797456639305973760 |
|---|---|
| author | Jiahui Tang Jimei Wu Bingbing Hu Jiajuan Qing |
| author_facet | Jiahui Tang Jimei Wu Bingbing Hu Jiajuan Qing |
| author_sort | Jiahui Tang |
| collection | DOAJ |
| description | An artificial-intelligence (AI)-based method for fault diagnosis is a strong candidate for industrial applications in the health management of rolling bearings. However, traditional fault diagnosis methods fail to improve the detection accuracy because they only extract a single feature and have limitations in feature representation. In addition, advanced object detection frameworks such as region-based convolutional neural networks have not yet been applied in fault diagnosis. To this end, a fault diagnosis model using a Time-Frequency Region-Based Convolutional Neural Network (TF-RCNN) is proposed in this paper. This method was mainly adopted to extract multiple regions that can characterize fault features from the Time-Frequency Representation (TFR). Specifically, an attention module was introduced so the model could focus on representative features. The existing classification strategy was also enhanced to perform multiple types of fault classification. Finally, an end-to-end rolling bearing fault diagnosis framework based on the TF-RCNN was developed with the aforementioned improvements. The effectiveness of this method was proven experimentally on artificial faults and real faults. The superiority of the proposed method is demonstrated using a comparison with the typical object detection method and an advanced fault diagnosis method. |
| first_indexed | 2024-03-09T16:09:47Z |
| format | Article |
| id | doaj.art-28572c7d57f84dcf98b8ac4a4193b469 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-09T16:09:47Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-28572c7d57f84dcf98b8ac4a4193b4692023-11-24T16:16:23ZengMDPI AGMachines2075-17022022-12-011012114510.3390/machines10121145Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural NetworkJiahui Tang0Jimei Wu1Bingbing Hu2Jiajuan Qing3School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaFaculty of Printing, Packing and Digital Media Engineering, Xi’an University of Technology, Xi’an 710054, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaAn artificial-intelligence (AI)-based method for fault diagnosis is a strong candidate for industrial applications in the health management of rolling bearings. However, traditional fault diagnosis methods fail to improve the detection accuracy because they only extract a single feature and have limitations in feature representation. In addition, advanced object detection frameworks such as region-based convolutional neural networks have not yet been applied in fault diagnosis. To this end, a fault diagnosis model using a Time-Frequency Region-Based Convolutional Neural Network (TF-RCNN) is proposed in this paper. This method was mainly adopted to extract multiple regions that can characterize fault features from the Time-Frequency Representation (TFR). Specifically, an attention module was introduced so the model could focus on representative features. The existing classification strategy was also enhanced to perform multiple types of fault classification. Finally, an end-to-end rolling bearing fault diagnosis framework based on the TF-RCNN was developed with the aforementioned improvements. The effectiveness of this method was proven experimentally on artificial faults and real faults. The superiority of the proposed method is demonstrated using a comparison with the typical object detection method and an advanced fault diagnosis method.https://www.mdpi.com/2075-1702/10/12/1145fault diagnosisTF-RCNNtime-frequency representationrolling bearing |
| spellingShingle | Jiahui Tang Jimei Wu Bingbing Hu Jiajuan Qing Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural Network Machines fault diagnosis TF-RCNN time-frequency representation rolling bearing |
| title | Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural Network |
| title_full | Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural Network |
| title_fullStr | Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural Network |
| title_full_unstemmed | Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural Network |
| title_short | Towards a Fault Diagnosis Method for Rolling Bearings with Time-Frequency Region-Based Convolutional Neural Network |
| title_sort | towards a fault diagnosis method for rolling bearings with time frequency region based convolutional neural network |
| topic | fault diagnosis TF-RCNN time-frequency representation rolling bearing |
| url | https://www.mdpi.com/2075-1702/10/12/1145 |
| work_keys_str_mv | AT jiahuitang towardsafaultdiagnosismethodforrollingbearingswithtimefrequencyregionbasedconvolutionalneuralnetwork AT jimeiwu towardsafaultdiagnosismethodforrollingbearingswithtimefrequencyregionbasedconvolutionalneuralnetwork AT bingbinghu towardsafaultdiagnosismethodforrollingbearingswithtimefrequencyregionbasedconvolutionalneuralnetwork AT jiajuanqing towardsafaultdiagnosismethodforrollingbearingswithtimefrequencyregionbasedconvolutionalneuralnetwork |