DOI QR코드

DOI QR Code

PREDICTION OF SEVERE ACCIDENT OCCURRENCE TIME USING SUPPORT VECTOR MACHINES

  • KIM, SEUNG GEUN (Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • NO, YOUNG GYU (Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • SEONG, POONG HYUN (Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology)
  • Received : 2014.08.18
  • Accepted : 2014.10.27
  • Published : 2015.02.25

Abstract

If a transient occurs in a nuclear power plant (NPP), operators will try to protect the NPP by estimating the kind of abnormality and mitigating it based on recommended procedures. Similarly, operators take actions based on severe accident management guidelines when there is the possibility of a severe accident occurrence in an NPP. In any such situation, information about the occurrence time of severe accident-related events can be very important to operators to set up severe accident management strategies. Therefore, support systems that can quickly provide this kind of information will be very useful when operators try to manage severe accidents. In this research, the occurrence times of several events that could happen during a severe accident were predicted using support vector machines with short time variations of plant status variables inputs. For the preliminary step, the break location and size of a loss of coolant accident (LOCA) were identified. Training and testing data sets were obtained using the MAAP5 code. The results show that the proposed algorithm can correctly classify the break location of the LOCA and can estimate the break size of the LOCA very accurately. In addition, the occurrence times of severe accident major events were predicted under various severe accident paths, with reasonable error. With these results, it is expected that it will be possible to apply the proposed algorithm to real NPPs because the algorithm uses only the early phase data after the reactor SCRAM, which can be obtained accurately for accident simulations.

Acknowledgement

Supported by : National Research Foundation (NRF)

References

  1. Z. Yangping, Z. Bingquan, W. Dongxin, Application of genetic algorithms to fault diagnosis in nuclear power plants, Reliab. Eng.Syst. Safe. 67 (2000) 153-160. https://doi.org/10.1016/S0951-8320(99)00061-7
  2. J.W. Hines, D.J. Wrest, R.E. Uhrig, Signal validation using an adaptive neural fuzzy inference system, Nucl. Technol. 199 (1997) 181-193.
  3. M.G. Na, A neuro-fuzzy inference system for sensor failure detection using wavelet denoising, PCA and SPRT, J. Korean Nucl. Soc. 33 (2001) 483-497.
  4. J. Garvey, D. Garvey, R. Seibert, J.W. Hines, Validation of online monitoring techniques to nuclear plant data, Nucl. Eng. Technol. 39 (2007) 149-158. https://doi.org/10.5516/NET.2007.39.2.149
  5. E.B. Bartlett, R.E. Uhrig, Nuclear power plant diagnostics using an artificial neural network, Nucl. Technol. 97 (1992) 272-281. https://doi.org/10.13182/NT92-A34635
  6. M. Marseguerra, E. Zio, Fault diagnosis via neural networks: the Boltzmann machine, Nucl. Sci. Eng. 117 (1994) 194e200. https://doi.org/10.13182/NSE94-A28534
  7. Y.G. No, J.H. Kim, M.G. Na, D.H. Lim, K.I. Ahn, Monitoring severe accidents using AI techniques, Nucl. Eng. Technol. 44 (2012) 393-404. https://doi.org/10.5516/NET.04.2012.512
  8. M.G. Na, W.S. Park, D.H. Lim, Detection and diagnostics of loss of coolant accident using support vector machines, IEEE Trans. Nucl. Sci. 55 (2008) 628-636. https://doi.org/10.1109/TNS.2007.911136
  9. M Claudia, S. Rocco, E. Zio, A support vector machine integrated system for the classification of operation anomalies in nuclear components and systems, Reliab. Eng. Sys. Safe. 92 (2007) 593-600. https://doi.org/10.1016/j.ress.2006.02.003
  10. I. Lindholm, E. Pekkarinen, H. Sjovall, Evaluation of reflooding effects on an overheated boiling water reactor core in a small steam-line break accident using MAAP, MELCOR, and SCDAP/RELAP5 computer codes, Nucl. Technol. 112 (1995) 42-57. https://doi.org/10.13182/NT95-A15850
  11. C. Allison, Comparison between MAAP, MELCOR, and SCDAP/RELAP5, Proceedings of the Workshop on Severe Accident Research in Japan (SARJ-97), JAERI (Japan atomic energy research institute), Yokohama, Japan, 1998 Oct 6e8, pp. 396-401.
  12. R. Gutierrez-Osuna, CSCE666: Pattern Analysis, Radial basis functions lecture notes [PowerPoint slides], Dept. of Computer Science & Engineering, Texas A&M University, Texas, U.S., 2011. Retrieved from http://research.cs.tamu.edu/prism/lectures/pr/pr_l19.pdf.
  13. N. Xin, X. Gu, H. Wu, Y. Hu, Z. Yang, Application of genetic algorithm-support vector regression (GA-SVR) for quantitative analysis of herbal medicines, J.Chemometr. 26 (2012) 353-360. https://doi.org/10.1002/cem.2435
  14. K. Chen, C. Wang, Support vector regression with genetic algorithms in forecasting tourism demand, Tourism Manage. 28 (2007) 215-226. https://doi.org/10.1016/j.tourman.2005.12.018