A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples
To solve the fault diagnosis difficulty of bearings with small data samples, a novel multi-information fusion vision transformer (ViT) model based on time–frequency representation (TFR) maps is proposed in this paper. The original vibration signal is decomposed into different scale sub-signals by th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/2/277 |
| _version_ | 1827756740930699264 |
|---|---|
| author | Zengbing Xu Xinyu Tang Zhigang Wang |
| author_facet | Zengbing Xu Xinyu Tang Zhigang Wang |
| author_sort | Zengbing Xu |
| collection | DOAJ |
| description | To solve the fault diagnosis difficulty of bearings with small data samples, a novel multi-information fusion vision transformer (ViT) model based on time–frequency representation (TFR) maps is proposed in this paper. The original vibration signal is decomposed into different scale sub-signals by the discrete wavelet transforms (DWTs), and the continuous wavelet transforms (CWTs) are used to transform these different scale sub-signals into time–frequency representation (TFR) maps, which are concatenated to input to the ViT model to diagnose the bearing fault. Through the multifaceted experiment analysis on the fault diagnosis of bearings with small data samples, the diagnosis results demonstrate that the proposed multi-information fusion ViT model can diagnose the fault of bearings with small data samples, with strong generalization and robustness; its average diagnosis accuracy achieved 99.85%, and it was superior to the other fault diagnosis methods, such as the multi-information fusion CNN, ViT model based on one-dimensional vibration signal, and ViT model based on the TFR of the original vibration signal. |
| first_indexed | 2024-03-11T08:31:30Z |
| format | Article |
| id | doaj.art-631dd18a081d4f6e8959f5462ceac261 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-11T08:31:30Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-631dd18a081d4f6e8959f5462ceac2612023-11-16T21:46:20ZengMDPI AGMachines2075-17022023-02-0111227710.3390/machines11020277A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data SamplesZengbing Xu0Xinyu Tang1Zhigang Wang2Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaTo solve the fault diagnosis difficulty of bearings with small data samples, a novel multi-information fusion vision transformer (ViT) model based on time–frequency representation (TFR) maps is proposed in this paper. The original vibration signal is decomposed into different scale sub-signals by the discrete wavelet transforms (DWTs), and the continuous wavelet transforms (CWTs) are used to transform these different scale sub-signals into time–frequency representation (TFR) maps, which are concatenated to input to the ViT model to diagnose the bearing fault. Through the multifaceted experiment analysis on the fault diagnosis of bearings with small data samples, the diagnosis results demonstrate that the proposed multi-information fusion ViT model can diagnose the fault of bearings with small data samples, with strong generalization and robustness; its average diagnosis accuracy achieved 99.85%, and it was superior to the other fault diagnosis methods, such as the multi-information fusion CNN, ViT model based on one-dimensional vibration signal, and ViT model based on the TFR of the original vibration signal.https://www.mdpi.com/2075-1702/11/2/277information fusionvision transformerfault diagnosissmall data samples |
| spellingShingle | Zengbing Xu Xinyu Tang Zhigang Wang A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples Machines information fusion vision transformer fault diagnosis small data samples |
| title | A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples |
| title_full | A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples |
| title_fullStr | A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples |
| title_full_unstemmed | A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples |
| title_short | A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples |
| title_sort | multi information fusion vit model and its application to the fault diagnosis of bearing with small data samples |
| topic | information fusion vision transformer fault diagnosis small data samples |
| url | https://www.mdpi.com/2075-1702/11/2/277 |
| work_keys_str_mv | AT zengbingxu amultiinformationfusionvitmodelanditsapplicationtothefaultdiagnosisofbearingwithsmalldatasamples AT xinyutang amultiinformationfusionvitmodelanditsapplicationtothefaultdiagnosisofbearingwithsmalldatasamples AT zhigangwang amultiinformationfusionvitmodelanditsapplicationtothefaultdiagnosisofbearingwithsmalldatasamples AT zengbingxu multiinformationfusionvitmodelanditsapplicationtothefaultdiagnosisofbearingwithsmalldatasamples AT xinyutang multiinformationfusionvitmodelanditsapplicationtothefaultdiagnosisofbearingwithsmalldatasamples AT zhigangwang multiinformationfusionvitmodelanditsapplicationtothefaultdiagnosisofbearingwithsmalldatasamples |