State Monitoring for Centrifugal Pump of PWR Based on HMM and SVM

Abstract:

The centrifugal pump of pressurized water reactor (PWR) in nuclear power plant is characterized by its complicated system, small accumulated data and fault samples. HMM has a strong ability to deal with time series modeling for dynamic process, while SVM has excellent generalization ability to solve the learning problems with small samples. This paper develops a state monitoring system based on the hybrid HMM/SVM model. The wavelet analysis techniques are used to extract features and the Hidden Markov Model (HMM) and Support Vector Machine (SVM) are used as the basic modeling and identification tools. The identification results of centrifugal pump show that the hybrid HMM/SVM system is effective and available for the state monitoring of the centrifugal pump of PWR in nuclear power plan.

• Periodical: Advanced Materials Research (Volumes 97-101)
• Pages: 3233-3238
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.97-101.3233
• Online since: March 2010
• Authors: Chun Liang Zhang, Sheng Li, Xia Yue
• Keywords: Centrifugal Pump, HMM, Pressurized Water Reactor, State Monitoring, Support Vector Machine (SVM)

References

[1] J. H. Xie, in: Hidden Markov Model (HMM) and its application in speech processing. Wuhan, Publishing House of Huazhong University of Science and Technology (1995).

[2] R. Hariharan, O. Viikki: An integrated study of speaker normalization and HMM adaptation for noise robust speaker-independent speech recognition. Speech Communication, Vol. 37 (3-4) (2002), pp.349-361.

DOI: 10.1016/s0167-6393(01)00039-5

[3] Vladimir N. Vapnik. Zhang Xue-gong (Translator), in: The nature of statistical learning theory. Tsinghua University Press(2006).

[4] Q. W. Wu: An Overview on the Identification, Prediction and Control Chatter (IPCC) During the Metal Machining Process. Optics and Precision Engineering, Vol. 3(1) (1995), pp.7-14.

[5] Vapnik V, in: The nature of statistics learning theory. New York: Springer-Verlag (1995), pp.40-50.

[6] Vapnik V, in: Statistical learning theory. NewYork: JohnWiley and Sons (1998), pp.102-110.

[7] X. M. Liu, J. Qiu, G. J. Liu: HMM-SVM Based Mixed Diagnostic Model and Its Application. Acta Aeronautica Et Astronautica Sinica, (1) (2006), pp.45-53.

[8] X. Wang, in: Measurement Intelligent Information Processing. Tsinghua University Press (2008).

[9] X. X. Ma, X. Y. Huang, Y. Chai: 2PTMC classification algorithm based on support vector machines and its application to fault diagnosis. Control and Decision, Vol. 18(3) (2003), pp.272-276.

[10] C. J. Feng: HMM Dynamical Pattern Recognition Theories, Methods and Applications in Faults Diagnosis of Rotating Machine [D, PhD thesis], Zhejiang University (2002), p.68.

[11] X. Y. Huang, B. Xiao, X. X. Ma, in: Theory and Application of modern intelligent algorithm. Science Press (2005).