Application of Algorithm of Hidden Markov Model and High-Order Spectrum in Fault Diagnosis of Power Electronic Circuit

Abstract:

This paper presents a method of applying the discrete hidden markov model and high-order spectrum to fault diagnosis of power electronic circuit.With bispectrum analysis, an ARMA model parametric bispectrum estimation is presented for Fault feature extraction firstly,and then fault modes were trained and recognized by Discrete Hidden Markov Model. Finally, electric locomotive main converter of SS8 type is used as an example to illustrate the new approach of fault diagnosis. The experimental results show that the proposed method has a high correct rate.The correct rate of the proposed method is 100%in the case of no noise or 5% noise whicn is 16.11% and 23.79% higher respectively than that of DHMM and BP neural network methods. So the method has practical value.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 488-491
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.488
• Online since: February 2012
• Authors: Ren Wu Yan, Li Zhou, Zhan Ying Zhong
• Keywords: Discrete Hidden Markov Model, Fault Diagnosis, Higher-Order Spectrum, Power Electronic Circuit

References

[1] XU Dehong; CHENG Zhaoji; CUI Xuejun. Fault diagnosis of power electronic circuits with discrete fourier transform. Journal of Zhejiang University(Natural Science),1994,28(6) ): 666-673.

[2] SU Pengsheng,WANG Zhiqiang,JIANG Jianguo. Fault diagnosis of power electronic circuits using artificial neural networks.Journal of Tsinghua(Science and Technology),1999,39(3) :19-22.

[3] HU Qing; WANG Rongjie; ZHAN Yi-ju. Fault Diagnosis Technology Based on SVM in Power Electronics Circuit. Proceedings of the CSEE,2008,28(12) : 107- 111.

[4] CUI Jiang; WANG You-ren; LIU Quan. The Technique of Power Electronic Circuit Fault Diagnosis Based on Higher-order Spectrum Analysis and Support Vector Machines. Proceedings of the CSEE,2007,27(10) : 62-66.

[5] DOU Wei; LIU han-sheng; WANG Xiao-wei. Fault Diagnosis Approach Based on High-order Spectral and Principal Component Analysis. Fluid Machinery, 2007,35(2): 46-50.

[6] YANG Jiangtian, CHEN Jiaji, ZENG Ziping. Bispectral Analysis and Its Application in Machinery Diagnosis. CHINA MECHANICAL ENGINEERING, 2000, 11(4):424-426.

[7] J Dai. Hybrid approach to speech recognition using hidden Markov models and Markov chains. Vision,Image and Signal Processing, IEE Proceedings,1994,141(5): 273-279.

DOI: 10.1049/ip-vis:19941321

[8] El-Yacoubi A,Sabourin R,Gilloux M, Suen C Y.Improved model architecture and training phase in an off-line HMM-based word recognition system.Proc.Fourteenth International Conf.Pattern Recognition. Brisbane,Australia,1998.

DOI: 10.1109/icpr.1998.711997

[9] CHEN Tefang, ZHONG Yanke. Fault Diagnosis for Main Converter Based on Wavelet Analysis and SVM.Electric Drive for Locomotives, 2009,1(1): 57-59,73.