Abstract
I n order to diagnose the PWM rectifier’s fault switch tube efficiently and accurately. The output voltage of the main circuit is analyzed by three-layer wavelet decomposition. When all the wavelet coefficients are obtained, the band’s wavelet energy spectrum is calculated. Then, the energy spectrum as a set of input variables is input into the improved BP neural network after normalization. The simulation results show that the method is accurate, efficient, and the learning convergence speed is better than the traditional wavelet analysis or neural network diagnosis method. The diagnosed accuracy rate is 86.7 %.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu Z, Ye B, Liang H (2004) Power electronics. Beijingjiaotong University Press, Beijing (in Chinese)
Luo H, Wang Y et al (2010) Multi-source feature level fusion fault diagnosis method of power electronic circuits. Electric Mach Control 14(4):92–95 (in Chinese)
Xu X, Fu X (2011) Analog circuit fault diagnosis research based on wavelet decomposition and the BP neural network. Mod Electron Technol 34(19):171–175 (in Chinese)
Wang Y, Meng Q et al (2009) Fault diagnosis of power electronic devices based on wavelet energy method and neural network. Intell Control Technol 31(2):25–27
Meng L, Wang L et al (2012) Traction converter fault diagnosis based on improved BP neural network. Electron Design Eng 20(6):61–63 (in Chinese)
Yi W (2005) Fault diagnosis of locomotive traction converters based on data mining. Southwest Jiaotong University, Chengdu, 4.10 (in Chinese)
Ming T, Yao X (2010) The centrifugal pump’s fault diagnosis method based on wavelet—principal component analysis. J Wuhan Univ Technol 12 (in Chinese)
Li B, Zhang P (2008) Feature extraction and selection for diagnosis gear using wavelet entropy and mutual information (in Chinese)
Dong Z, Jin X, Yang Y (2009) Fault diagnose for temperature, flow rate and pressure sensors in VAV systems using wavelet neural network. Appl Energy 2009(86):1624–1631
Acknowledgments
The work was supported by high-speed railway traction power system safety prediction and control (U1134204); supported by “the Fundamental Research Funds for the Central Universities” (2013YJS083). We appreciate the anonymous reviewers for their comments and suggestions here.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Meng, L., Fu, Y., Liu, Z., Jia, L., Wang, L. (2014). Fault Diagnosis of PWM Rectifier Based on Wavelet Neural Network. In: Jia, L., Liu, Z., Qin, Y., Zhao, M., Diao, L. (eds) Proceedings of the 2013 International Conference on Electrical and Information Technologies for Rail Transportation (EITRT2013)-Volume I. Lecture Notes in Electrical Engineering, vol 287. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-53778-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-53778-3_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-53777-6
Online ISBN: 978-3-642-53778-3
eBook Packages: EngineeringEngineering (R0)