Nuclear Engineering and Technology

  • 제37권2호
  • /
  • Pages.177-184
  • /
  • 2005
  • /
  • 1738-5733(pISSN)
  • /
  • 2234-358X(eISSN)
한국원자력학회 (Korean Nuclear Society)
권호 표지

MSET PERFORMANCE OPTIMIZATION THROUGH REGULARIZATION

  • HINES J. WESLEY (Nuclear Engineering Department The University of Tennessee Knoxville) ;
  • USYNIN ALEXANDER (Nuclear Engineering Department The University of Tennessee Knoxville)
  • 발행 : 2005.04.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The Multivariate State Estimation Technique (MSET) is being used in Nuclear Power Plants for sensor and equipment condition monitoring. This paper presents the use of regularization methods for optimizing MSET's predictive performance. The techniques are applied to a simulated data set and a data set obtained from a nuclear power plant currently implementing empirical, on-line, equipment condition monitoring techniques. The results show that regularization greatly enhances the predictive performance. Additionally, the selection of prototype vectors is investigated and a local modeling method is presented that can be applied when computational speed is desired.

키워드

참고문헌

  1. Hadamard, J., Lectures on Cauchy's Problem in Linear Partial Differential Equations, Yale University Press, New Haven, 1923
  2. Gribok, A.V., J.W. Hines, A. Urmanov, and R.E. Uhrig, 'Use of Kernel Based Techniques for Sensor Validation in Nuclear Power Plants', Statistical Data Mining and Knowledge Discovery, pp. 217-231, Chapman and Hall/CRC Press, 2004
  3. Hines, J.W., A.V. Gribok, I. Attieh, and R.E. Uhrig, 'Regularization Methods for Inferential Sensing in Nuclear Power Plants', Fuzzy Systems and Soft Computing in Nuclear Engineering, Ed. Da Ruan, Springer, 1999
  4. Gribok, A.V., J.W. Hines, A. Urmanov, and R.E. Uhrig, 'Regularization of Ill-Posed Surveillance and Diagnostic Measurements', Power Plant Surveillance and Diagnostics, Eds. Da Ruan and P. Fantoni, Springer, 2002
  5. Hoerl, A.E., and R.W. Kennard, 'Ridge regression: biased estimation for nonorthogonal problems', Technometrics, 12, pp.55-67, 1970 https://doi.org/10.2307/1267351
  6. Urmanov, A.M., A.V. Gribok, J.W. Hines, and R.E. Uhrig, 'Complexity-penalized model selection for feedwater inferential measurements in nuclear power plants', ANS International Topical Meeting on Nuclear Plant Instrumentation, Controls, and Human-Machine Interface Technologies (NPIC&HMIT 2000), Washington, DC, 2000
  7. Urmanov, A., A. Gribok, J.W. Hines, and Brandon Rasmussen, 'Application of Information Complexity in Principal Component Regression Modeling of the Venturi Meter Drift', published in the proceedings of the Maintenance and Reliability Conference (MARCON 2000), Knoxville, TN, May 6-9, 2001
  8. Hines, J.W., A. Gribok, A. Urmanov and M. Buckner, 'Selection of Multiple Regularization Parameters in Local Ridge Regression Using Evolutionary Algorithms and Prediction Risk Optimization', Inverse Problems in Engineering, Vol. 11, No. 3, pp. 215-227, 2003 https://doi.org/10.1080/1068276031000095822
  9. Buckner, M., 'Learning From Data with Localized Regression and Differential Evolution', Ph.D. Dissertation, The University of Tennessee, Nuclear Engineering Department, 2003
  10. Rasmussen, B., J.W. Hines, and R.E. Uhrig , 'Nonlinear Partial Least Squares Modeling for Instrument Surveillance and Calibration Verification', by published in the proceedings of the Maintenance and Reliability Conference (MARCON 2000), Knoxville, TN, May 7-10, 2000
  11. Hines, J.W., A.V. Gribok, I. Attieh, and R.E. Uhrig, 'Neural Network Regularization Techniques for a Sensor Validation System', American Nuclear Society Annual Meeting, San Diego, California, June 4-8, 2000
  12. Hines, J.W, A. Gribok, A. Urmanov and R.E. Uhrig, 'Heuristic, Systematic, and Informational Regularization for Process Monitoring', International Journal of Intelligent Systems on Intelligent Systems for Process Monitoring, Wiley Publishers, Vol. 17, No. 8, pp. 723-750, 2002 https://doi.org/10.1002/int.10047
  13. Singer, R.M., K.C. Gross, J.P. Herzog, R.W. King, and S.W. Wegerich, 'Model-Based Nuclear Power Plant Monitoring and Fault Detection: Theoretical Foundations,' Proc. 9th Intl. Conf. on Intelligent Systems Applications to Power Systems, Seoul, Korea, 1996
  14. Mott, J, Young, and R.W. King, 'Pattern Recognition Software for Plant Surveillance', US DOE Report, 1987
  15. Gross, K. C., R. M. Singer, S. W. Wegerich, J. P. Herzog, R. Van Alstine, and F. K. Bockhorst, 'Application of a Model-based Fault Detection System to Nuclear Plant Signals,' Proc. 9th Intl. Conf. on Intelligent Systems Applications to Power Systems, Seoul, Korea, 1997
  16. Aha, D.W., Editorial. Artificial Intelligence Review, 11(1-5), 1-6, Special Issue on Lazy Learning, 1997 https://doi.org/10.1016/S0954-1810(97)90003-0
  17. Atkeson, C.G., Moore, A.W., Schaal, S., 'Locally Weighted Learning', Artificial Intelligence Review, 11(1-5), 11-73, 1997 https://doi.org/10.1023/A:1006559212014
  18. Cherkassky, V., and F. Mulier, Learning From Data, John Wiley & Sons, 1998
  19. Wegerich, S, R. Singer, J. Herzog, and A. Wilks, 'Challenges Facing Equipment Condition Monitoring Systems', MARCON 2001, Gatlinburg TN, May 6-9, 2001
  20. Tibshirani, R., 'Regression shrinkage and selection via the lasso', Journal of the Royal Statistical Society B 58, 267-288, 1996
  21. Mallows, C.L., 'Some comments on CP', Technometrics, 15, No. 4, pp. 661-675, 1973 https://doi.org/10.2307/1267380
  22. Muller, Hans-Georg 'Nonparametric regression analysis of longitudinal data', Springer-Verlag, New York, p.94, 1988
  23. Hines, J.W., and A Usynin, 'Regularization Methods for MSET and other Kernel Techniques', Research Report for SmartSignal Inc., September 2003