Statement Networks to Condition Monitoring of the Sealless Pump

Authors

  • Sebastian Rzydzik
  • Marcin Amarowicz
  • Krzysztof Psiuk
  • Tomasz Rogala

Abstract

This paper shows an application of multi-layer statement networks to condition monitoring of the sealless magnetic drive pump. In this case, statement networks are computed based on the use of Bayesian probabilities. Moreover, the tool called REx which allows implementing such networks is described. An example of created four-layer network as well as final results of the performed tests shows also.

References

E. Castillo, J. M. Gutiâerrez, A. S. Hadi, “Expert systems and probabilistic network models”, Monographs in Computer Science Series, Springer Verlag, Berlin 1997.

W. Cholewa, “Multimodal statements networks for diagnostic applications”, In: P. Sas, B. Bergen (Eds.) Proceedings of the International Conference on Noise and Virbation Engineering ISMA 2010, September 20-22, Katholique Universiteit Lueven, Lueven, Belgium, pp. 817–830, 2010.

W. Cholewa, T. Rogala, P. Chrzanowski, M. Amarowicz, “Statement Networks Development Environment REx”, In: P. Jędrzejowicz, N. T. Nguyen, K. Hoang, Computational Collective Intelligence. Technologies and Applications, Springer Verlag, Berlin, Germany, pp. 30-39, 2011.

F. Dawid, R. Cowell, S. Lauritzen, D. Spiegelhalter, “Probabilistic networks and expert systems”, Springer, New York, 2007.

J. C. Giarratano, G. D. Riley, Expert systems: principles and programming, TCT, 2005.

V. J. Jensen,” Bayesian networks and decision graphs”, Springer, New York, USA, 2002.

J. Korbicz, J. M. Kościelny, Z. Kowalczuk, W. Cholewa (Eds.), „Fault diagnosis. Models, artificial itelligence, applications”, Springer Verlag, Berlin Heidelberg, Germany, 2004.

H. G. Natke, Cz. Cempel, “Model-aided diagnosis of mechanical systems”, Springer Verlag, Germany, 1997.

Downloads

Published

2014-09-30

Issue

Section

Expert Systems, Technical Diagnostics