Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

VALIDATION OF ON-LINE MONITORING TECHNIQUES TO NUCLEAR PLANT DATA

  • Garvey, Jamie (Nuclear Engineering Department, The University of Tennessee) ;
  • Garvey, Dustin (Nuclear Engineering Department, The University of Tennessee) ;
  • Seibert, Rebecca (Nuclear Engineering Department, The University of Tennessee) ;
  • Hines, J. Wesley (Nuclear Engineering Department, The University of Tennessee)
  • Published : 2007.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The Electric Power Research Institute (EPRI) demonstrated a method for monitoring the performance of instrument channels in Topical Report (TR) 104965, 'On-Line Monitoring of Instrument Channel Performance.' This paper presents the results of several models originally developed by EPRI to monitor three nuclear plant sensor sets: Pressurizer Level, Reactor Protection System (RPS) Loop A, and Reactor Coolant System (RCS) Loop A Steam Generator (SG) Level. The sensor sets investigated include one redundant sensor model and two non-redundant sensor models. Each model employs an Auto-Associative Kernel Regression (AAKR) model architecture to predict correct sensor behavior. Performance of each of the developed models is evaluated using four metrics: accuracy, auto-sensitivity, cross-sensitivity, and newly developed Error Uncertainty Limit Monitoring (EULM) detectability. The uncertainty estimate for each model is also calculated through two methods: analytic formulas and Monte Carlo estimation. The uncertainty estimates are verified by calculating confidence interval coverages to assure that 95% of the measured data fall within the confidence intervals. The model performance evaluation identified the Pressurizer Level model as acceptable for on-line monitoring (OLM) implementation. The other two models, RPS Loop A and RCS Loop A SG Level, highlight two common problems that occur in model development and evaluation, namely faulty data and poor signal selection

Keywords

References

  1. J.W. HINES and D.R. GARVEY, 'Development and Application of Fault Detectability Performance Metrics for Instrument Calibration Verification and Anomaly Detection', Journal of Pattern Recognition Research, 1: (2006)
  2. J.W. HINES, D.R. GARVEY, R.M. SEIBERT, and S.A. ARNDT, 'On-Line Sensor Calibration Monitoring Challenges and Effective Monte Carlo Based Uncertainty Estimation', IAEA Technical Meeting on On-Line Monitoring, Knoxville, TN: June 27-30, (2005)
  3. D.R. GARVEY and J.W. HINES, 'An Adaptive Distance Measure for Use with Nonparametric Models', 5th International Topical Meeting on Nuclear Plant Instrumentation, Controland Human-Machine Interface Technologies, Albuquerque, NM: November 12-14, (2006)
  4. J.W. HINES and D.R. GARVEY, 'Traditional and Robust Vector Selection Methods for Use with Similarity Based Models', 5th International Topical Meeting on Nuclear PlantInstrumentation, Control and Human-Machine Interface Technologies, Albuquerque, NM: November 12-14, (2006)
  5. J.W. HINES and A. USYNIN, 'On-Line Monitoring Robustness Measures and Comparisons', International Atomic Energy Agency Technical Meeting on 'Increasing instrument calibration interval through on-line calibration technology', OECD Halden Reactor Project, Halden, Norway: September 27-29, (2004)
  6. D.R. GARVEY and J.W. HINES, 'Development and Application of Fault Detectability Performance Metrics for Instrument Calibration Verification and Anomaly Detection', Journal of Pattern Recognition Research, 1, pp.2-15, (2006) https://doi.org/10.13176/11.5
  7. J.W. HINES and A. USYNIN, 'MSET Performance Optimization Through Regularization', Nuclear Engineering and Technology, Vol. 37, No. 2, pp 177-184, (2005)
  8. On-Line Monitoring of Instrument Channel Performance Volume 2: Model Examples, Algorithm Descriptions, and Additional Results, EPRI, Palo Alto, CA: 2004. 1003579
  9. J.W. HINES and E. DAVIS, 'Lessons Learned From the U.S. Nuclear Power Plant On-Line Monitoring Programs', Progress in Nuclear Energy, 46(3-4), pp. 176-189, (2005) https://doi.org/10.1016/j.pnucene.2005.03.003
  10. J.W. HINES and D.R. GARVEY, 'The Development of a Process and Equipment Monitoring (PEM) Toolbox and Its Application to Sensor Calibration Monitoring', Proceedings of The 4th International Conference on Quality and Reliability (ICQR2005), Beijing, China, August 9-11, (2005)
  11. I. DIAZ, A.B. DIEZ, and A.A. CUADRUDO VEGA, 'Complex Process Visualization Through Continuous Feature Maps Using Radial Basis Functions', Proceedings of the International Conference on Artificial Neural Networks, Vienna, Austria: August 21-25, (2001)
  12. S. WEGERICH, 'Similarity Based Modeling of Time Synchronous Average Vibration Signals for Machinery Health Monitoring', Proceedings of the IEEE Aerospace Conference, 6, March 6-13, (2004) https://doi.org/10.1109/AERO.2004.1368182
  13. W.P. WAND and M.C. JONES, Kernel Smoothing, London: Chapman & Hall, (1995)
  14. D.R. GARVEY and J.W. HINES, 'Robust Distance Measures for On-Line Monitoring: Why Use Euclidean?', 7th International Fuzzy Logic and Intelligent technologies in Nuclear Science (FLINS) Conference on Applied Artificial Intelligence, Genova, Italy, August 29-31, (2006)
  15. E.A. NADARYA, 'On Estimating Regression', Theory of Probability and Its Applications, 10, pp.186-190: (1964) https://doi.org/10.1137/1110024
  16. G.S. WATSON, 'Smooth Regression Analysis', The Indian Journal of Statistics, Series A, 26, pp.359-372: (1964)
  17. B. RASMUSSEN, 'Prediction Interval Estimation Techniques for Empirical Modeling Strategies and their Applications to Signal Validation Tasks,' Ph.D. dissertation, NuclearEngineering Department, The University of Tennessee, Knoxville, TN: (2003)

Cited by

  1. Detection and Diagnostics of Loss of Coolant Accidents Using Support Vector Machines vol.55, pp.1, 2008, https://doi.org/10.1109/TNS.2007.911136
  2. Monitoring Minimum DNBR Using a Support Vector Regression Model vol.56, pp.1, 2009, https://doi.org/10.1109/TNS.2008.2009216
  3. Monitoring and Uncertainty Analysis of Feedwater Flow Rate Using Data-Based Modeling Methods vol.56, pp.4, 2009, https://doi.org/10.1109/TNS.2009.2022366
  4. Smart Soft-Sensing for the Feedwater Flowrate at PWRs Using a GMDH Algorithm vol.57, pp.1, 2010, https://doi.org/10.1109/TNS.2009.2035121
  5. Prediction of DNBR Using Fuzzy Support Vector Regression and Uncertainty Analysis vol.57, pp.3, 2010, https://doi.org/10.1109/TNS.2010.2047265
  6. 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
  7. Smart Sensing of the RPV Water Level in NPP Severe Accidents Using a GMDH Algorithm vol.61, pp.2, 2014, https://doi.org/10.1109/TNS.2014.2305444
  8. Prediction of Leak Flow Rate Using Fuzzy Neural Networks in Severe Post-LOCA Circumstances vol.61, pp.6, 2014, https://doi.org/10.1109/TNS.2014.2357583
  9. Calorimetric Analysis to Infer Primary Circuit Flow in Integral and Pool-Type Reactors vol.64, pp.2, 2017, https://doi.org/10.1109/TNS.2017.2650963
  10. Selection of optimal denoising-based regularization hyper-parameters for performance improvement in a sensor validation model pp.1573-7462, 2017, https://doi.org/10.1007/s10462-017-9546-6
  11. Predicting Diametral Creep of the Pressure Tubes in CANDU Reactors Using Fuzzy Neural Networks vol.48, pp.1, 2011, https://doi.org/10.1080/18811248.2011.9711681
  12. Optimal Fault Classification Using Fisher Discriminant Analysis in the Parity Space for Applications to NPPs vol.65, pp.3, 2018, https://doi.org/10.1109/TNS.2018.2803658