Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

INTEGRATED DIAGNOSTIC TECHNIQUE FOR NUCLEAR POWER PLANTS

  • Gofuku, Akio (Graduate School of Natural Science and Technology, Okayama University)
  • Received : 2014.10.06
  • Published : 2014.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

It is very important to detect and identify small anomalies and component failures for the safe operation of complex and large-scale artifacts such as nuclear power plants. Each diagnostic technique has its own advantages and limitations. These facts inspire us not only to enhance the capability of diagnostic techniques but also to integrate the results of diagnostic subsystems in order to obtain more accurate diagnostic results. The article describes the outline of four diagnostic techniques developed for the condition monitoring of the fast breeder reactor "Monju". The techniques are (1) estimation technique of important state variables based on a physical model of the component, (2) a state identification technique by non-linear discrimination function applying SVM (Support Vector Machine), (3) a diagnostic technique applying WT (Wavelet Transformation) to detect changes in the characteristics of measurement signals, and (4) a state identification technique effectively using past cases. In addition, a hybrid diagnostic system in which a final diagnostic result is given by integrating the results from subsystems is introduced, where two sets of values called confidence values and trust values are used. A technique to determine the trust value is investigated under the condition that the confidence value is determined by each subsystem.

Keywords

References

  1. D. Ruan, P. F. Fanton, Power Plant Surveillance and Diagnostics: Applied Research with Artificial Intelligence, Springer, (2002).
  2. IAEA, Defence in Depth in Nuclear Safety, IN-SAG-10, (1996).
  3. G. Y. Heo, Condition Monitoring Using Empirical Models: Technical Review and Prospects for Nuclear Applications, Nuclear Engineering and Technology, 40 (1), 49-68 (2008). https://doi.org/10.5516/NET.2008.40.1.049
  4. M. Kitamura, T. Washio, K. Kotajima, K. Sugiyama, Small-sample modeling method for nonstationary reactor noise analysis, Annals of Nuclear Energy, 12 (8), 399-407 (1985). https://doi.org/10.1016/0306-4549(85)90019-2
  5. H. Furusawa, A. Gofuku, Diagnosis of Steam Generator by Estimating an Unobserved Important State Variable, Journal of Nuclear Science and Technology, 50 (9), 942-949 (2013). https://doi.org/10.1080/00223131.2013.816476
  6. Furusawa, H., Gofuku, A., Condition Monitoring of Steam Generator by Estimating the Overall Heat Transfer Coefficient, International Journal of Nuclear Safety and Simulation, 4 (1), 59-66 (2013).
  7. H. Minowa, Y. Furuta, Y. Munesawa, K. Suzuki, Process Data Selection Method to Diagnose Abnormal Situation of Plant Using Support Vector Machines, CD-ROM Proc. First International Symposium on Socially and Technically Symbiotic Systems, 03STSS2012-7.pdf, (2012).
  8. Nagamatsu, T., Gofuku, A.: Detection Method for Small Anomalies in Pumps Using Mother Wavelets Extracted from Real Vibration Signals, CD-ROM Proc. First International Symposium on Socially and Technically Symbiotic Systems, 01STSS2012-16.pdf, (2012).
  9. M. Takahashi, A. Gofuku, Case-based Reasoning Diagnostic Technique Based on Multi-attribute Similarity, USB Proc. ISOFIC/ISSNP2014 (International Symposium on Future I&C for Nuclear Power Plants/ International Symposium on Symbiotic Nuclear Power Systems), I&C81_Case-based reasoning diagnostic_Tohoku UNIV_TAKAHASHI.pdf, (2014).
  10. Gofuku A., Takahashi M., Nagamatsu T., Mochi-zuki H., Furusawa H., Minowa H., Hybrid Diagnostic Agent System for the Fast-Breeder Reactor "Monju", Int. J. Nuclear Safety and Simulation, 2013, 4 (2), 105-114.
  11. K. Takata, A. Gofuku, T. Sugihara, An Integration Technique of Diagnosis Results in Hybrid-type Diagnostic Systems, USB Proc. ISO-FIC/ISSNP2014 (International Symposium on Future I&C for Nuclear Power Plants/International Symposium on Symbiotic Nuclear Power Systems), I&C05_An Integration Technique of_Okayama UNIV_TAKATA.pdf, (2014).
  12. H. Mochizuki, Development of the plant dynamics analysis code NETFLOW++, Nuclear Engineering and Design, 240, 577-587 (2010). https://doi.org/10.1016/j.nucengdes.2009.10.019
  13. V. N. Vapnik, The Nature of Statistical Learning Theory, Springer Verlag, (1995).
  14. A. Widodo, B.-S. Yang, Support Vector Machine in Machine Condition Monitoring and Fault Di-agnosis, Mechanical Systems and Signal Pro-cessing, 21 (6), 2560-2574 (2007). https://doi.org/10.1016/j.ymssp.2006.12.007
  15. M. G. Na, H. Y. Yang, D. H. Lim, A Soft-sensing Model for Feedwater Flow Rate Using Fuzzy Support Vector Regression, Nuclear Engineering and Technology, 40 (1), 69-76 (2008). https://doi.org/10.5516/NET.2008.40.1.069
  16. S. Mallat, Wavelet Tour of Signal Processing, Academic Press, (1998).
  17. O. J. Kim, N. Z. Cho, C. J. Park, M. G. Park, Investigation of Reactor Condition Monitoring and Singularity Detection Via Wavelet Transfer and De-noising, Nuclear Engineering and Technology, 39 (3), 221-230 (2007). https://doi.org/10.5516/NET.2007.39.3.221
  18. Z. Zhang, H. Ikeuchi, T. Miyake, T. Imamura, Parasitic discrete wavelet transform and its application on abnormal detection, Proc. the Second International Conference on Innovative Computing, Information and Control (ICICIC '07), 125-128 (2007).
  19. Z. Zhang, H. Ikeuchi, N. Ssaiki, T. Imamura, H. Ishii, H. Toda, T. Miyake, Parasitic Discrete Wavelet Transform and Its Application on Abnormal Signal Detection, Transactions of the JSME (C), 75 (757), 163-170 (2009). (in Japanese)
  20. J. Kolodner, Case-Based Reasoning, Morgan Kaufmann, (1993).
  21. C. Diantoto, M. Takahashi, M. Kitamura, Symptom Database for Intelligent Detection and Characterization of Incipient Failures in Nuclear Power Plant, Proc. Maintenance and Reliability Conf. MARCON98, 1, 24.01-24.08 (1998).
  22. Y. Oomori, H. Ueno, Hybrid Troubleshooting Sys-tem Based on Object Model -Object Modelling and Model-Based Reasoning-, Journal of the Japanese Society for Artificial Intelligence, 5 (5), 604-616 (1990). (in Japanese)

Cited by

  1. A cascade intelligent fault diagnostic technique for nuclear power plants pp.1881-1248, 2018, https://doi.org/10.1080/00223131.2017.1394228
  2. Evaluation of Interface Defects in Inaccessible Reactor Shrink Fit Nozzle Welds Using Ultrasonic Waves vol.10, pp.5, 2017, https://doi.org/10.3390/en10050589