Multiscale Time-Frequency Sparse Transformer Based on Partly Interpretable Method for Bearing Fault Diagnosis
Shock and Vibration · 04.08.2023 · 2023 · 1-21
DOI: 10.1155/2023/1639287 ↗Kurz gefasst
Fachartikel in der Zeitschrift Shock and Vibration, erschienen am 04.08.2023. Verfasst von Shouquan Che und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Youth Program of the Education Foundation of Guizhou Province.
Abstract (Originalsprache)
Transformer model is being gradually studied and applied in bearing fault diagnosis tasks, which can overcome the feature extraction defects caused by long-term dependencies in convolution neural network (CNN) and recurrent neural network (RNN). To optimize the structure of existing transformer-like methods and improve the diagnostic accuracy, we proposed a novel method based on the multiscale time-frequency sparse transformer (MTFST) in this paper. First, a novel tokenizer based on shot-time Fourier transform (STFT) is designed, which processes the 1D format raw signals into 2D format discrete time-frequency sequences in the embedding space. Second, a sparse self-attention mechanism is designed to eliminate the feature mapping defect in naive self-attention mechanism. Then, the novel encoder-decoder structure is presented, the multiple encoders are employed to extract the hidden feature of different time-frequency sequences obtained by STFT with different window widths, and the decoder is used to remap the deep information and connect to the classifier for discriminating fault types. The proposed method is tested in the XJTU-SY bearing dataset and self-made experiment rig dataset, and the following work is conducted. The influences of hyperparameters on diagnosis accuracy and number of parameters are analysed in detail. The weights of the attention mechanism (AM) are visualized and analysed to study the interpretability, which explains the partly working pattern of the network. In the comparison test with other existing CNN, RNN, and transformer models, the diagnosis accuracy of different methods is statistically analysed, feature vectors are presented via the t-distributed stochastic neighbor embedding (t-SNE) method, and the proposed MTFST obtains the best accuracy and feature distribution form. The results demonstrate the effectiveness and superiority of the proposed method in bearing fault diagnosis.
Förderung
- Youth Program of the Education Foundation of Guizhou Province
Zitieren
APA
Che, S., Lu, J., Bao, C., Zhang, C., & Liu, Y. (2023). Multiscale Time-Frequency Sparse Transformer Based on Partly Interpretable Method for Bearing Fault Diagnosis. Shock and Vibration, 2023, 1-21. https://doi.org/10.1155/2023/1639287
Vancouver
Che S, Lu J, Bao C, Zhang C, Liu Y. Multiscale Time-Frequency Sparse Transformer Based on Partly Interpretable Method for Bearing Fault Diagnosis. Shock and Vibration. 2023;2023:1-21. doi:10.1155/2023/1639287
BibTeX
@article{Che2023,
author = {Che, Shouquan and Lu, Jianfeng and Bao, Congwang and Zhang, Caihong and Liu, Yongzhi},
title = {Multiscale Time-Frequency Sparse Transformer Based on Partly Interpretable Method for Bearing Fault Diagnosis},
journal = {Shock and Vibration},
year = {2023},
volume = {2023},
pages = {1--21},
doi = {10.1155/2023/1639287}
}
EUVIMED