Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

PRINCIPAL COMPONENTS BASED SUPPORT VECTOR REGRESSION MODEL FOR ON-LINE INSTRUMENT CALIBRATION MONITORING IN NPPS

  • Seo, In-Yong (Transmission and Distribution Laboratory, KEPCO Research Institute) ;
  • Ha, Bok-Nam (Transmission and Distribution Laboratory, KEPCO Research Institute) ;
  • Lee, Sung-Woo (Transmission and Distribution Laboratory, KEPCO Research Institute) ;
  • Shin, Chang-Hoon (Transmission and Distribution Laboratory, KEPCO Research Institute) ;
  • Kim, Seong-Jun (Department of Industrial Engineering, Kangnung National University)
  • Received : 2009.09.21
  • Accepted : 2010.03.02
  • Published : 2010.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In nuclear power plants (NPPs), periodic sensor calibrations are required to assure that sensors are operating correctly. By checking the sensor's operating status at every fuel outage, faulty sensors may remain undetected for periods of up to 24 months. Moreover, typically, only a few faulty sensors are found to be calibrated. For the safe operation of NPP and the reduction of unnecessary calibration, on-line instrument calibration monitoring is needed. In this study, principal component-based auto-associative support vector regression (PCSVR) using response surface methodology (RSM) is proposed for the sensor signal validation of NPPs. This paper describes the design of a PCSVR-based sensor validation system for a power generation system. RSM is employed to determine the optimal values of SVR hyperparameters and is compared to the genetic algorithm (GA). The proposed PCSVR model is confirmed with the actual plant data of Kori Nuclear Power Plant Unit 3 and is compared with the Auto-Associative support vector regression (AASVR) and the auto-associative neural network (AANN) model. The auto-sensitivity of AASVR is improved by around six times by using a PCA, resulting in good detection of sensor drift. Compared to AANN, accuracy and cross-sensitivity are better while the auto-sensitivity is almost the same. Meanwhile, the proposed RSM for the optimization of the PCSVR algorithm performs even better in terms of accuracy, auto-sensitivity, and averaged maximum error, except in averaged RMS error, and this method is much more time efficient compared to the conventional GA method.

Keywords

References

  1. Upadhyaya, B. R., and E. Eryurek (1992), "Application of Neural Networks for Sensor Validation and Plant Monitoring", Nuclear Technology, 97, 170-176 (February 1992).
  2. Mott, Y., and R. W. King (1987), Pattern Recognition Software for Plant Surveillance, U.S. DOE Report.
  3. Wegerich, S. (2002), "Performance Comparison of Variable Selection and Grouping Algorithms", Technical Report, SmartSignal Corp.
  4. Fantoni, P., S. Figedy, and A. Racz (1998), "A Neuro- Fuzzy Model Applied to Full Range Signal Validation of PWR Nuclear Power Plant Data", FLINS-98, Antwerpen, Belgium.
  5. C. Cortes and V. Vapnik. Support vector networks, Machine Learning 20: 273-297, 1995.
  6. V. Vapnik. The Nature of Statistical Learning Theory, Springer Verlag, 1995.
  7. N. Zavaljevski and K. C. Gross. "Support Vector Machines for Nuclear Reactor State Estimation", ANS International Topical Meeting May 7-11, 2000, Pittsburgh, USA
  8. A. V. Gribok, J. W. Hines, R. E. Uhrig. "Use of Kernel Based Techniques For Sensor Validation In Nuclear Power Plants", NPIC&HMIT 2000, Washington, DC, November, 2000.
  9. Liu X, Chen HC, Liu TA, Li YL, Lu ZR, Lu WC. "Application of PCA-SVR to NIR prediction model for tobacco chemical composition", 2007 Dec; 27 (12):2460-3
  10. Xuexiang Jin, Yi Zhang, and Danya Yao. "Simultaneously Prediction of Network Traffic Flow Based on PCA-SVR", LNCS 4492, pp. 1022-1031, 2007
  11. X. G. Hua, Y. Q. Ni, J. M. Ko, F. ASCE and K. Y. Wong. "Modeling of Temperature-Frequency Correlation Using Combined Principal Component Analysis and Support Vector Regression Technique", journal of computing in civil engineering march/April 2007, 122-135
  12. V. N. Vapnik, The Nature of Statistical Learning Theory, New York: Springer, 1995.
  13. EPRI, "On-Line Monitoring of Instrument Channel Performance Volume 3: Applications to Nuclear Power Plant Technical Specification Instrumentation," Final Report # 1007930, EPRI, Palo Alto, CA. 2004
  14. Rencher, A. C. Methods of multivariate analysis, 2nd Ed., Wiley, New York (2002).
  15. M. G . Na, "A Neuro-Fuzzy Inference System for Sensor Failure Detection Using Wavelet Denosing, PCA and SPRT," J. Korean Nucl. Soc., vol 33, no. 5, pp483-497, Oct. 2001.
  16. M. G. Na, H. Y. Yang, D. H. Lim, "A Soft-sensing Model for Feedwater Flow Rate Using Fuzzy Support Vector Regression," Nucl. Eng. Tech., vol 40, no. 1, pp69-76, Feb. 2008. https://doi.org/10.5516/NET.2008.40.1.069
  17. M. G. Na, I. J. Hwang, and Y. J. Lee, "Inferential Sensing and Monitoring for Feedwater Flowrate in Pressurized Water Reactors," IEEE Trans. Nucl. Sci., vol.53, no. 4, pp.2335-2342, 2006. https://doi.org/10.1109/TNS.2006.878159
  18. I. Y. Seo, and S. J. Kim, "An On-line Monitoring Technique Using Support Vector Regression and Principal Component Analysis" CIMCA 2008, Vienna, Austria, pp. 663-669. 2008.
  19. O. Omitaomu, M. K. Jeong, A. Badiru, and J. W. Hines, "On-Line Support Vector Regression Approach for the Monitoring of Motor Shaft Misalignment and Feedwater Flow Rate," IEEE Transactions on Systems, Man, Cybernetics, Part C, 37(5), 962-970. 2007. https://doi.org/10.1109/TSMCC.2007.900648

Cited by

  1. Prediction of Axial DNBR Distribution in a Hot Fuel Rod Using Support Vector Regression Models vol.58, pp.4, 2011, https://doi.org/10.1109/TNS.2011.2159738
  2. Empirical Modeling of Cryogenic System for Hybrid SFCL Using Support Vector Regression vol.26, pp.4, 2013, https://doi.org/10.1007/s10948-012-1965-7