Acoustic Emission Diagnosis of Rolling Bearing Faults based on Optimized VMD-Transformer

Hao Chen; Yang Yu

doi:10.54097/3xpe9h24

Authors

Hao Chen
Yang Yu

DOI:

https://doi.org/10.54097/3xpe9h24

Keywords:

Acoustic Emission Signa, Rolling Bearing, Sea-horse Optimizer, Transformer, Variational Module Architecture

Abstract

The acoustic emission signal of rolling bearing fault has poor feature data extraction effect, resulting in low fault diagnosis accuracy. This paper proposes a rolling bearing fault diagnosis method based on optimized variational mode decomposition (VMD) denoising and feature enhancement, and using the Transformer model for diagnosis. The Seahorse Optimizer (SHO) algorithm is used to optimize the VMD parameters [K, α]. The optimized VMD is used to decompose the acoustic emission signal of the bearing to obtain several intrinsic mode components (IMFs). The intrinsic mode components containing more fault information are selected according to the envelope entropy and kurtosis, and the signal is reconstructed; the reconstructed signal is input into the Transformer model to complete the diagnosis. The experimental results show that the accuracy of the optimized VMD-Transformer fault diagnosis model reaches 98.1%, which is significantly improved compared with other fault diagnosis models.

Downloads

Download data is not yet available.

References

[1] Smith, W. A., & Randall, R. B. (2015). Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mechanical Systems and Signal Processing, 64, 100-131.

[2] Jin Rongshun, Shen Gongtian, Wang Qiang, et al. Fault diagnosis of rolling bearing acoustic emission signals of large cable car based on EMD and approximate entropy [J]. Journal of China University of Metrology, 2018, 29 (04): 417-423.

[3] Xu Zhonglin, Li Guolu, Dong Tianshun, et al. Research progress in acoustic emission signal analysis and processing methods [J]. Materials Review, 2014, 28 (09): 56-60+73.

[4] K. Dragomiretskiy and D. Zosso, "Variational Mode Decomposition," in IEEE Transactions on Signal Processing, vol. 62, no. 3, pp. 531-544, Feb.1, 2014.

[5] Xu Ke, Chen Zonghai, Zhang Chenbin, et al. Rolling bearing fault diagnosis based on empirical mode decomposition and support vector machine [J]. Control Theory and Applications, 2019, 36 (06): 915-922.

[6] Zhang Yu, Chen Jun, Wang Xiaofeng, et al. Application of random forest in rolling bearing fault diagnosis [J]. Computer Engineering and Applications, 2018, 54 (06): 100-104+114.

[7] Chen Renxiang, Huang Xin, Yang Lixia, et al. Rolling bearing fault diagnosis based on convolutional neural network and discrete wavelet transform [J]. Journal of Vibration Engineering, 2018, 31 (05): 883-891.

[8] Chen Baojia, Chen Xueli, Shen Baoming, et al. Application of CNN-LSTM deep neural network in rolling bearing fault diagnosis [J]. Journal of Xi'an Jiaotong University, 2021, 55 (06): 28-36.

[9] Qiu Dawei, Liu Zichen, Zhou Yiqing, et al. Rolling bearing fault type identification based on Transformer neural network [J]. High Technology Letters, 2021, 31 (01): 1-11.

[10] Zhao, S., Zhang, T., Ma, S. et al. Sea-horse optimizer: a novel nature-inspired meta-heuristic for global optimization problems. Appl Intell 53, 11833–11860 (2023).