Fault Diagnosis of Rolling Bearings in Agricultural Machines Using SVD-EDS-GST and ResViT
Open Access
- 4 August 2024
- journal article
- research article
- Published by MDPI AG in Agriculture
- Vol. 14 (8) , 1286
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
Funding Information
- National Natural Science Foundation of China (52265068, 20224BAB204050, KLCEZ2022-02, GJJ2200627)
- Natural Science Foundation of Jiangxi Province (52265068, 20224BAB204050, KLCEZ2022-02, GJJ2200627)
- Equipment Key Laboratory Project of the Ministry of Education (52265068, 20224BAB204050, KLCEZ2022-02, GJJ2200627)
- Project of Jiangxi Provincial Department of Education (52265068, 20224BAB204050, KLCEZ2022-02, GJJ2200627)
This publication has 31 references indexed in Scilit:
- Measurement and diagnostic system for detecting and classifying faults in the rotary hay tedder using multilayer perceptron neural networksEngineering Applications of Artificial Intelligence, 2024
- Fault transfer diagnosis of rolling bearings across multiple working conditions via subdomain adaptation and improved vision transformer networkAdvanced Engineering Informatics, 2023
- Diagnosisformer: An efficient rolling bearing fault diagnosis method based on improved TransformerEngineering Applications of Artificial Intelligence, 2023
- Lesion-aware visual transformer network for Paddy diseases detection in precision agricultureEuropean Journal of Agronomy, 2023
- An efficient and robust Phonocardiography (PCG)-based Valvular Heart Diseases (VHD) detection framework using Vision Transformer (ViT)Computers in Biology and Medicine, 2023
- Fault Diagnosis of Rolling Bearing Under Variable Working Conditions Based on CWT and T-ResNetJournal of Vibration Engineering & Technologies, 2022
- Local lowest-rank dynamic mode decomposition for transient feature extraction of rolling bearingsISA Transactions, 2022
- Unsupervised domain-share CNN for machine fault transfer diagnosis from steady speeds to time-varying speedsJournal of Manufacturing Systems, 2022
- Transformer models for text-based emotion detection: a review of BERT-based approachesArtificial Intelligence Review, 2021
- A transfer convolutional neural network for fault diagnosis based on ResNet-50Neural Computing and Applications, 2019