Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning Model
Because the gearbox in transmission systems is prone to failure and the fault signal is not obvious, the fault end cannot be located. In this paper, a gearbox fault diagnosis method grounded on improved complete ensemble empirical mode decomposition with adaptive noise, a multiscale permutation entr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/6/2565 |
| _version_ | 1797242153037987840 |
|---|---|
| author | Hongfeng Gao Tiexin Xu Renlong Li Chaozhi Cai |
| author_facet | Hongfeng Gao Tiexin Xu Renlong Li Chaozhi Cai |
| author_sort | Hongfeng Gao |
| collection | DOAJ |
| description | Because the gearbox in transmission systems is prone to failure and the fault signal is not obvious, the fault end cannot be located. In this paper, a gearbox fault diagnosis method grounded on improved complete ensemble empirical mode decomposition with adaptive noise, a multiscale permutation entropy and adaptive wavelet thresholding (ICEEMDAN-MPE-AWT) denoising method and an SE-ResNeXt50 transfer learning model are proposed. Initially, the vibration signal is denoised by ICEEMDAN-MPE-AWT, the denoised vibration signal is then converted into a Gram angle field (GAF) diagram, and then the parameters are transferred by the fine-tuning transfer learning strategy. Finally, a GAF diagram is input into the model for training to achieve fault extraction and classification. In this paper, the open gear dataset of Southeast University is used for experimental research. The experimental results show that when using the ICEEMDAN-MPE-AWT and when the signal-to-noise ratio (SNR) of the experimental data is −4 dB, the average accuracy of the GASF+TSE-ResNeXt50 and the GASF+TSE-ResNeXt18 can reach 98.8% and 97.5%, respectively. When the SNR is 6 dB, the accuracy of the above two models reaches 100% and 99.3%, respectively. Moreover, when compared to alternative approaches, the noise reduction method in this paper can better remove noise interference so that the model can better extract fault features. Therefore, the method proposed in this article shows significant improvement in noise reduction and fault classification accuracy compared to other methods. |
| first_indexed | 2024-04-24T18:34:41Z |
| format | Article |
| id | doaj.art-9f06c0cffdce465fa1f8fb67d956495a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-24T18:34:41Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9f06c0cffdce465fa1f8fb67d956495a2024-03-27T13:20:06ZengMDPI AGApplied Sciences2076-34172024-03-01146256510.3390/app14062565Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning ModelHongfeng Gao0Tiexin Xu1Renlong Li2Chaozhi Cai3Handan Branch of Hebei Special Equipment Supervision and Inspection Institute, Handan 056000, ChinaSchool of Mechanical and Equipment Engineering, Hebei University of Engineering, Handan 056038, ChinaSchool of Mechanical and Equipment Engineering, Hebei University of Engineering, Handan 056038, ChinaSchool of Mechanical and Equipment Engineering, Hebei University of Engineering, Handan 056038, ChinaBecause the gearbox in transmission systems is prone to failure and the fault signal is not obvious, the fault end cannot be located. In this paper, a gearbox fault diagnosis method grounded on improved complete ensemble empirical mode decomposition with adaptive noise, a multiscale permutation entropy and adaptive wavelet thresholding (ICEEMDAN-MPE-AWT) denoising method and an SE-ResNeXt50 transfer learning model are proposed. Initially, the vibration signal is denoised by ICEEMDAN-MPE-AWT, the denoised vibration signal is then converted into a Gram angle field (GAF) diagram, and then the parameters are transferred by the fine-tuning transfer learning strategy. Finally, a GAF diagram is input into the model for training to achieve fault extraction and classification. In this paper, the open gear dataset of Southeast University is used for experimental research. The experimental results show that when using the ICEEMDAN-MPE-AWT and when the signal-to-noise ratio (SNR) of the experimental data is −4 dB, the average accuracy of the GASF+TSE-ResNeXt50 and the GASF+TSE-ResNeXt18 can reach 98.8% and 97.5%, respectively. When the SNR is 6 dB, the accuracy of the above two models reaches 100% and 99.3%, respectively. Moreover, when compared to alternative approaches, the noise reduction method in this paper can better remove noise interference so that the model can better extract fault features. Therefore, the method proposed in this article shows significant improvement in noise reduction and fault classification accuracy compared to other methods.https://www.mdpi.com/2076-3417/14/6/2565gearboxfault diagnosistransfer learningICEEMDANMPEAWT |
| spellingShingle | Hongfeng Gao Tiexin Xu Renlong Li Chaozhi Cai Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning Model Applied Sciences gearbox fault diagnosis transfer learning ICEEMDAN MPE AWT |
| title | Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning Model |
| title_full | Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning Model |
| title_fullStr | Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning Model |
| title_full_unstemmed | Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning Model |
| title_short | Gearbox Fault Diagnosis Based on ICEEMDAN-MPE-AWT and SE-ResNeXt50 Transfer Learning Model |
| title_sort | gearbox fault diagnosis based on iceemdan mpe awt and se resnext50 transfer learning model |
| topic | gearbox fault diagnosis transfer learning ICEEMDAN MPE AWT |
| url | https://www.mdpi.com/2076-3417/14/6/2565 |
| work_keys_str_mv | AT hongfenggao gearboxfaultdiagnosisbasedoniceemdanmpeawtandseresnext50transferlearningmodel AT tiexinxu gearboxfaultdiagnosisbasedoniceemdanmpeawtandseresnext50transferlearningmodel AT renlongli gearboxfaultdiagnosisbasedoniceemdanmpeawtandseresnext50transferlearningmodel AT chaozhicai gearboxfaultdiagnosisbasedoniceemdanmpeawtandseresnext50transferlearningmodel |