Fault Diagnosis of Rolling Bearings in Agricultural Machines Using SVD-EDS-GST and ResViT

Fengyun Xie (), Yang Wang, Gan Wang, Enguang Sun, Qiuyang Fan and Minghua Song
Additional contact information
Fengyun Xie: School of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China
Yang Wang: School of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China
Gan Wang: School of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China
Enguang Sun: School of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China
Qiuyang Fan: School of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China
Minghua Song: School of Mechanical Electrical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China

Agriculture, 2024, vol. 14, issue 8, 1-16

Abstract: In the complex and harsh environment of agriculture, rolling bearings, as the key transmission components in agricultural machinery, are very prone to failure, so research on the intelligent fault diagnosis of agricultural machinery components is critical. Therefore, this paper proposes a new method based on SVD-EDS-GST and ResNet-Vision Transformer (ResViT) for the fault diagnosis of rolling bearings in agricultural machines. Firstly, an experimental platform for rolling bearing failure in agricultural machinery is built, and one-dimensional vibration signals are obtained using acceleration sensors. Next, the signal is preprocessed for noise reduction using singular value decomposition (SVD) combined with the energy difference spectrum (EDS) to solve for the interference of complex noise and redundant components in the vibration signal. Secondly, generalized S-transform (GST) is used to process vibration signals into images. Then, the ResViT model is proposed, where the ResNet34 network is used to replace the image chunking mechanism in the original Vision Transformer model for feature extraction. Finally, an improved Vision Transformer (ViT) is utilized to synthesize global and local information for fault classification. The experimental results show that the proposed method’s average accuracy in rolling bearing fault classification for agricultural machinery reaches 99.08%. In addition, compared with SVD-EDS-GST-CNN, SVD-EDS-GST-LSTM, STFT-ViT, GST-ViT, and SVD-EDS-GST-ViT, the accuracy rate was improved by 3.5%, 3.84%, 4.8%, 8.02%, and 0.56%, and the standard deviation was also minimized.

Keywords: agricultural machinery rolling bearing; fault diagnosis; SVD-EDS; GST; ResViT (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2077-0472/14/8/1286/pdf (application/pdf)
https://www.mdpi.com/2077-0472/14/8/1286/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:14:y:2024:i:8:p:1286-:d:1449806

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().