Research on Fault Diagnosis of Metro Bearing Based on Wavelet Neural Network

Journal: Architecture Engineering and Science DOI: 10.32629/aes.v5i3.2557

Jinxuan Zhao

Beijing Jiaotong University, Beijing 100080, China

Abstract

Bearings are critical rotating components in subway vehicles, and their health directly affects the safety of train operation. Traditional bearing fault diagnosis heavily relies on simplistic signal processing techniques, which struggle to achieve high precision fault recognition. Therefore, this paper proposes a novel method for subway bearing fault diagnosis based on Wavelet Neural Networks (WNN). The paper analyzes the basic principles of wavelet transform and details the structural design of Wavelet Neural Networks. In the experimental section, vibration signals from subway bearings under different operating conditions are collected and analyzed using Wavelet Neural Networks to validate the effectiveness of the proposed method. Experimental results demonstrate that the fault diagnosis method based on Wavelet Neural Networks can accurately identify early bearing faults with higher precision compared to traditional methods.

Keywords

subway bearings; fault diagnosis; Wavelet Neural Network; vibration signals; intelligent diagnosis

References

[1] Wang, L., Xu, Y., Jie, T., et al. (2023). Fault diagnosis of subway traction motor bearings based on optimized CNN and information fusion. Mechanical and Electronics, 41(8), 39-44, 48.
[2] Li, X., Xing, Y., Yu, B. (2021). Analysis of relevant issues in the diagnosis of subway vehicle bogie bearing faults. Science and Technology Innovation, 2021(1), 167-168.
[3] Liu, M. (2020). Research on subway traction motor bearing fault diagnosis based on data and feature aggregation. Henan University of Science and Technology (Doctoral dissertation).
[4] Chen, G., Lu, X., He, L., et al. (2023). Fault diagnosis method for subway train rolling bearing based on SSA-VMD. Equipment Manufacturing Technology, 2023(7), 42-46.
[5] Ma, Y. (2020). Design and implementation of subway vehicle running gear bearing fault diagnosis system. Dalian University of Technology (Master's thesis).
[6] Rong, F., Jia, X., Yang, C. (2021). Fault diagnosis of subway axle box bearings based on CEEMD and fast spectral kurtosis map. Journal of Dalian Jiaotong University, 42(1), 48-51, 47.
[7] Hu, J. (2020). Research on diagnosis method of misalignment fault of rolling bearings in urban rail transit vehicles. Construction Engineering Technology and Design, 2020(8), 4939.

Copyright © 2024 Jinxuan Zhao

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License