Diagnosing Intermittent Faults to Restrain BIT False Alarm Based on EMD-MSVM

Abstract:

Intermittent fault is an important factor causing built-in test(BIT) false alarm. Diagnosing intermittent fault is an important approach to restrain BIT false alarms. This paper proposes a intermittent faults diagnostic methods based on empirical mode decomposition (EMD) and multiple support vector machine (MSVM). Firstly, the EMD method is used to decompose the original signal into a number of intrinsic mode function (IMF), the auto-regressive (AR) model of each IMF component is established. The AR model parameters and the variance of remnant are regarded as the feature vectors, are input to MSVM classifier, so the working conditions and faults are classified. The experimental results show that the BIT false alarm caused by intermittent fault can be effectively reduced by this proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 105-107)
• Pages: 729-732
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.105-107.729
• Online since: September 2011
• Authors: Ming Wei Guo, Shi Hong Ni, Jia Hai Zhu
• Keywords: Auto Regression (AR) Model, Built-In Test (BIT), Empirical Mode Decomposition (EMD), False Alarm, Intermittent Fault, Multiple Support Vector Machine (MSVM)

References

[1] Z. Tian, J.Y. Shi: Design analysis and validation of system testability. Beijing University of Aeronautics and Astronautics Press, (2003).

[2] R. Drew, N. Young: Role of BIT in support system maintenance and availability. IEEE AES Magazine, vol. 19(2004), p.3.

[3] X.S. Wen, Y.C. Xu and X.S. Yi: Theory and application of intelligent Built-in Test, National defence Industry Press, (2002).

[4] J. Zbytniewski, K. Anderson: Smart BIT-2: adding intelligence to built in test. Proceedings of the IEEE National Aerospace and Electronics Conference, vol. 4(1989), p. (2035).

DOI: 10.1109/naecon.1989.40500

[5] F. Aylstock, L. Elerin, J. HintzandC. Learoyd, Neural network false alarm filter. NTIS No: AD2A293114/5/HDM, (1994).

[6] X.M. Liu, Q. Jing and G.J. Liu: Analysis of the 3-state Markov model in BIT. Journal of National University of Defense Technology, Vo. l26(2004) No. 1, p.84, (In Chinese).

[7] N.E. Huang, Z. Shen and S.R. Long: The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London, Series A (1998), p.903.

DOI: 10.1098/rspa.1998.0193

[8] William W.S. Wei. Time Series Analysis, Univariate and Multivariate Methods, (2005).

[9] Vapnik V N. The Nature of Statistical Learning Theory. New York Spring Verag, (1995).

[10] S. Singh, A. Kodali and K. Pattipati, in: A Factorial Hidden Markov Model (FHMM)-based Reasoner for Diagnosing Multiple Intermittent Faults. 5th Annual IEEE Conference on Automation Science and Engineering Bangalore (India, August 22-25, 2009) p.146.

DOI: 10.1109/coase.2009.5234134