Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer
Aiming at rolling bearing fault diagnosis, the collected vibration signal contains complex noise interference, and one-dimensional information cannot be used to fully mine the data features of the problem. This paper proposes a rolling bearing fault diagnosis method based on SVD-GST combined with th...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-08-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/16/3515 |
_version_ | 1797584936692088832 |
---|---|
author | Fengyun Xie Gan Wang Haiyan Zhu Enguang Sun Qiuyang Fan Yang Wang |
author_facet | Fengyun Xie Gan Wang Haiyan Zhu Enguang Sun Qiuyang Fan Yang Wang |
author_sort | Fengyun Xie |
collection | DOAJ |
description | Aiming at rolling bearing fault diagnosis, the collected vibration signal contains complex noise interference, and one-dimensional information cannot be used to fully mine the data features of the problem. This paper proposes a rolling bearing fault diagnosis method based on SVD-GST combined with the Vision Transformer. Firstly, the one-dimensional vibration signal is preprocessed to reduce noise using singular value decomposition (SVD) to obtain a more accurate and useful signal. Then, the generalized S-transform (GST) is used to convert the processed one-dimensional vibration signal into a two-dimensional time–frequency image and make full use of the advantages of deep learning in image classification with higher recognition accuracy. In order to avoid the problem of limited sensory fields in CNN and the need for an RNN to compute step by step over time when processing sequence data, the use of a Vision Transformer model for pattern recognition classification is proposed. Finally, an experimental platform for the fault diagnosis of rolling bearings is built. The model is experimentally validated, achieving an average accuracy of 98.52% over multiple tests. Additionally, compared with the SVD-GST-2DCNN, STFT-CNN-LSTM, SVD-GST-LSTM, and GST-ViT fault diagnosis models, the proposed method has higher diagnostic accuracy and stability, providing a new method for rolling bearing fault diagnosis. |
first_indexed | 2024-03-10T23:59:43Z |
format | Article |
id | doaj.art-e406dae61932480eb1faedc637d4d336 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T23:59:43Z |
publishDate | 2023-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-e406dae61932480eb1faedc637d4d3362023-11-19T00:54:46ZengMDPI AGElectronics2079-92922023-08-011216351510.3390/electronics12163515Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision TransformerFengyun Xie0Gan Wang1Haiyan Zhu2Enguang Sun3Qiuyang Fan4Yang Wang5School of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaAiming at rolling bearing fault diagnosis, the collected vibration signal contains complex noise interference, and one-dimensional information cannot be used to fully mine the data features of the problem. This paper proposes a rolling bearing fault diagnosis method based on SVD-GST combined with the Vision Transformer. Firstly, the one-dimensional vibration signal is preprocessed to reduce noise using singular value decomposition (SVD) to obtain a more accurate and useful signal. Then, the generalized S-transform (GST) is used to convert the processed one-dimensional vibration signal into a two-dimensional time–frequency image and make full use of the advantages of deep learning in image classification with higher recognition accuracy. In order to avoid the problem of limited sensory fields in CNN and the need for an RNN to compute step by step over time when processing sequence data, the use of a Vision Transformer model for pattern recognition classification is proposed. Finally, an experimental platform for the fault diagnosis of rolling bearings is built. The model is experimentally validated, achieving an average accuracy of 98.52% over multiple tests. Additionally, compared with the SVD-GST-2DCNN, STFT-CNN-LSTM, SVD-GST-LSTM, and GST-ViT fault diagnosis models, the proposed method has higher diagnostic accuracy and stability, providing a new method for rolling bearing fault diagnosis.https://www.mdpi.com/2079-9292/12/16/3515singular value decompositiongeneralized S-transformVision Transformerrolling bearingfault diagnosis |
spellingShingle | Fengyun Xie Gan Wang Haiyan Zhu Enguang Sun Qiuyang Fan Yang Wang Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer Electronics singular value decomposition generalized S-transform Vision Transformer rolling bearing fault diagnosis |
title | Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer |
title_full | Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer |
title_fullStr | Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer |
title_full_unstemmed | Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer |
title_short | Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer |
title_sort | rolling bearing fault diagnosis based on svd gst combined with vision transformer |
topic | singular value decomposition generalized S-transform Vision Transformer rolling bearing fault diagnosis |
url | https://www.mdpi.com/2079-9292/12/16/3515 |
work_keys_str_mv | AT fengyunxie rollingbearingfaultdiagnosisbasedonsvdgstcombinedwithvisiontransformer AT ganwang rollingbearingfaultdiagnosisbasedonsvdgstcombinedwithvisiontransformer AT haiyanzhu rollingbearingfaultdiagnosisbasedonsvdgstcombinedwithvisiontransformer AT enguangsun rollingbearingfaultdiagnosisbasedonsvdgstcombinedwithvisiontransformer AT qiuyangfan rollingbearingfaultdiagnosisbasedonsvdgstcombinedwithvisiontransformer AT yangwang rollingbearingfaultdiagnosisbasedonsvdgstcombinedwithvisiontransformer |