A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions
The diagnosis of bearing faults is an important guarantee for the healthy operation of mechanical equipment. Due to the time-varying working conditions of mechanical equipment, it is necessary to achieve bearing fault diagnosis under time-varying working conditions. However, the superposition of the...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/15/6730 |
| _version_ | 1797586022614171648 |
|---|---|
| author | Zheng Wang Xiaoyang Xu Yu Zhang Zhongyao Wang Yuting Li Zhidong Liu Yuxi Zhang |
| author_facet | Zheng Wang Xiaoyang Xu Yu Zhang Zhongyao Wang Yuting Li Zhidong Liu Yuxi Zhang |
| author_sort | Zheng Wang |
| collection | DOAJ |
| description | The diagnosis of bearing faults is an important guarantee for the healthy operation of mechanical equipment. Due to the time-varying working conditions of mechanical equipment, it is necessary to achieve bearing fault diagnosis under time-varying working conditions. However, the superposition of the two-dimensional working conditions of speed and acceleration brings great difficulties to diagnosis via data-driven models. The long short-term memory (LSTM) model based on the infinitesimal method is an effective method to solve this problem, but its performance still has certain limitations. On this basis, this article proposes a model for fault diagnosis under time-varying operating conditions that combines a residual network model (ResNet) and a gate recurrent unit (model) (GRU). Firstly, the samples were segmented, and feature extraction was performed using ResNet. We then used GRU to process the information. Finally, the classification results were output through the output network. This model could ignore the influence of acceleration and achieve high fault diagnosis accuracy under time-varying working conditions. In addition, we used t-SNE to reduce the dimensionality of the features and analyzed the role of each layer in the model. Experiments showed that this method had a better performance compared with existing bearing fault diagnosis methods. |
| first_indexed | 2024-03-11T00:17:24Z |
| format | Article |
| id | doaj.art-55645bfe437c42a18960b0515d0c03dc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T00:17:24Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-55645bfe437c42a18960b0515d0c03dc2023-11-18T23:33:42ZengMDPI AGSensors1424-82202023-07-012315673010.3390/s23156730A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working ConditionsZheng Wang0Xiaoyang Xu1Yu Zhang2Zhongyao Wang3Yuting Li4Zhidong Liu5Yuxi Zhang6School of Mechanical and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Mechanical and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Mechanical and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Mechanical and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Mechanical and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Mechanical and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Management Engineering, Shandong Jianzhu University, Jinan 250101, ChinaThe diagnosis of bearing faults is an important guarantee for the healthy operation of mechanical equipment. Due to the time-varying working conditions of mechanical equipment, it is necessary to achieve bearing fault diagnosis under time-varying working conditions. However, the superposition of the two-dimensional working conditions of speed and acceleration brings great difficulties to diagnosis via data-driven models. The long short-term memory (LSTM) model based on the infinitesimal method is an effective method to solve this problem, but its performance still has certain limitations. On this basis, this article proposes a model for fault diagnosis under time-varying operating conditions that combines a residual network model (ResNet) and a gate recurrent unit (model) (GRU). Firstly, the samples were segmented, and feature extraction was performed using ResNet. We then used GRU to process the information. Finally, the classification results were output through the output network. This model could ignore the influence of acceleration and achieve high fault diagnosis accuracy under time-varying working conditions. In addition, we used t-SNE to reduce the dimensionality of the features and analyzed the role of each layer in the model. Experiments showed that this method had a better performance compared with existing bearing fault diagnosis methods.https://www.mdpi.com/1424-8220/23/15/6730data-drivenfault diagnosisGRUResNettime-varying working condition |
| spellingShingle | Zheng Wang Xiaoyang Xu Yu Zhang Zhongyao Wang Yuting Li Zhidong Liu Yuxi Zhang A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions Sensors data-driven fault diagnosis GRU ResNet time-varying working condition |
| title | A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions |
| title_full | A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions |
| title_fullStr | A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions |
| title_full_unstemmed | A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions |
| title_short | A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions |
| title_sort | bearing fault diagnosis method based on a residual network and a gated recurrent unit under time varying working conditions |
| topic | data-driven fault diagnosis GRU ResNet time-varying working condition |
| url | https://www.mdpi.com/1424-8220/23/15/6730 |
| work_keys_str_mv | AT zhengwang abearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT xiaoyangxu abearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT yuzhang abearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT zhongyaowang abearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT yutingli abearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT zhidongliu abearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT yuxizhang abearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT zhengwang bearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT xiaoyangxu bearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT yuzhang bearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT zhongyaowang bearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT yutingli bearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT zhidongliu bearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions AT yuxizhang bearingfaultdiagnosismethodbasedonaresidualnetworkandagatedrecurrentunitundertimevaryingworkingconditions |