Fault Diagnosis of Power Electronic Circuit Based on Hybrid Intelligent Method

Abstract:

Because of the problems of fault diagnosis in the power electric circuit and the merit of FCM is efficient in clustering and the merit of hidden Markov model (HMM) that have the ability to deal with continuous dynamic signals and the merit of support vector machine (SVM) with perfect classifying ability, With the features extracted from the circuit, based on the trained FCM algorithm, HMM was used to calculate the matching degree among the unknown signal and the circuit’s states, which formed the features for SVM to diagnosis. Double-bridge 12-pulse rectifier is used as a example to verifiy the effectiveness of the method. The experimental results show that the proposed method has a good correct rate.

• Periodical: Applied Mechanics and Materials (Volumes 651-653)
• Pages: 1074-1077
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.651-653.1074
• Online since: September 2014
• Authors: Ren Wu Yan*, Jian Min Dai
• Keywords: Discrete Hidden Markov Model, Fault Diagnosis, Fuzzy C-Mean Clustering, Hybrid Method, Power Electronic Circuit, Support Vector Machine (SVM)

References

[1] H. Ma, and Y. S Lee, Fault diagnosis of power electroniccircuits based on neural network and waveform analysis", proceedings of IEEE PEDS, 99, 1999. pp.234-237.

[2] Szlosek. Marcin, Swiatek. Boguslaw, Hanzelka. Zbigniew, Application of neural networks to voltage fluctuations measurement — neural networks flickermete, Nonsinusoidal Currents and Compensation, 2008. ISNCC 2008 , p.1 –5, June (2008).

DOI: 10.1109/isncc.2008.4627515

[3] X.J. Zhang, J.B. Tan, and J.H. Han, A method of fault diagnosis based on BP neural network,. Systems engineering-theory & practice, 2002, vol. 34, no. 6, pp.61-66.

[4] Dunn and J.C., Some recent investigations of a new fuzzy partition algorithm and its application to pattern classification problems. J. Cybernetics, vol. 4, p.1–15, (1974).

DOI: 10.1080/01969727408546062

[5] Bezdek and J.C., Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum, New York, (1981).

[6] X. Wang, Y. Wang, and L. Wang, Improving Fuzzy c-Means Clustering based on Feature-Weight Learning. Pattern Recognition Letters, 25 (10), p.1123–1132, (2004).

DOI: 10.1016/j.patrec.2004.03.008

[7] Nefian. A. V, Hayes. M. H. III, An embedded HMM-based approach for face detection and recognition, "Acoustics, Speech, and Signal Processing, 1999. ICASSP , 99. Proceedings., 1999 IEEE, vol. 6, p.3553 – 3556, March (1999).

DOI: 10.1109/icassp.1999.757610

[8] Rabiner. L. R, A tutorial on hidden markov models and selected applications in speech recognition, , Proceedings of the IEEE, vol. 77, pp.257-286, Feb (1989).

DOI: 10.1109/5.18626

[9] Khanna. R, Huaping Liu, Control theoretic approach to intrusion detection using a distributed hidden Markov model, , Wireless Communications, IEEE, vol. 15, p.24 – 33, Aug. (2008).

DOI: 10.1109/mwc.2008.4599218

[10] Vladimir N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995, 187 pp.

[11] B. Scholkopf and A. J. Smola, Learning with Kernels. MIT Press, (2002).

[12] Xu Dehong, Cheng Zhaoji , Cui Xuejun, Fault diagnosis of power electronic circuits with discrete Fourier transform, Journal of Zhejiang University, vo1. 28, pp.666-673, (1994).