Regularization Methods for Inferential Sensing in Nuclear Power Plants

  • J. Wesley Hines
  • Andrei V. Gribok
  • Ibrahim Attieh
  • Robert E. Uhrig
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 38)


Inferential sensing is the use of information related to a plant parameter to infer its actual value. The most common method of inferential sensing uses a mathematical model to infer a parameter value from correlated sensor values. Collinearity in the predictor variables leads to an ill posed problem that causes inconsistent results when data based models such as linear regression and neural networks are used. This chapter presents several linear and non-linear inferential sensing methods including linear regression and neural networks. Both of these methods can be modified from their original form to solve ill posed problems and produce more consistent results.


Partial Little Square Nuclear Power Plant Singular Value Decomposition Hide Neuron Tikhonov Regularization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Basseville, M. (1988). “Detecting Changes in Signals and Systems–A Survey,” Automatica, 24, 309–326.MathSciNetCrossRefMATHGoogle Scholar
  2. Bishop, Christopher M. (1996), Neural Networks for Pattern Recognition,Oxford University Press.Google Scholar
  3. Black, C.L., R.E. Uhrig, and J.W. Hines, (1998), “System Modeling and Instrument Calibration Verification with a Non-linear State Estimation Technique,” published in the proceedings of the Maintenance and Reliability Conference (MARCON 98), Knoxville, TN, May 12–14.Google Scholar
  4. Cherkassky, V., and F. Muller (1998), Learning From Data,John Wiley & Sons.Google Scholar
  5. Desai, M., A. Ray (1981), “A Fault Detection and Isolation Methodology,” Proc. 20th Conf. on Decision and Control, 1363–1369.Google Scholar
  6. EPRI (1992), “Feedwater Flow Measurement in U.S. Nuclear Power Generation Stations,” TR-101388, Electric Power Research Institute.Google Scholar
  7. Efron, B. (1982), The Jacknife, The Bootstrap, and Other Resampling Plans. Philadelphia, Penn.: Society for Industrial and Applied Mathematics.Google Scholar
  8. Erriksson, J., Marten Gulliksson, Per Lindsrom and Per-Ake Wedin, “Regularization Tools for Training Large-Scale Neural Networks,” Technical report UMINF-96.05 Department of Computing Science, Umea University, Sweden.Google Scholar
  9. Gantmacher, F.R. (1959), Applications of the Theory of Matrices, Interscience Publishers, New York.MATHGoogle Scholar
  10. Geladi, P, and B.R. Kowalski (1986), “Partial Least-Squares Regression: A Tutorial,” Analyta Chimica, Acta, 185, pp 1–17.Google Scholar
  11. Gertler, J. (1988), “Survey of Model Based Failure Detection and Isolation in Complex Plants,” IEEE Control Systems Magazine, pp. 3–11.Google Scholar
  12. Glockler, O. (1991), “Fault Detection in Nuclear Power Plants Applying the Sequential Probability Ratio Test of Mar-Based Residual Time Series,” Proceedings of the AI 91 Frontiers in Innovative Computing for the Nuclear Industry, Jackson, Wyoming, 859–868.Google Scholar
  13. Golub, G. H., M.T. Heath, and G. Wahba (1979), Generalized cross-validation as a method for choosing a good ridge parameter, Technometrics, 21, pp. 215–223.Google Scholar
  14. Golub, G.H., and C.F. Van Loan (1996), Matrix Computations, Third Edition, the Johns Hopkins University Press, Baltimore, MD.Google Scholar
  15. Grini, R.E., O. Naess, O. Berg (1989), “Model-Based Fault Detection and Diagnosis in Process Plant Operation,” Proceedings of the Seventh Power Plant Dynamics, Control & Testing Symposium, Knoxville, Tennessee, 56.01–56.14.Google Scholar
  16. Gross, K.C., R.M. Singer, S.W. Wegerich, J.P. Herzog, R. Van Alstine, and F. K. Bockhorst (1997), “Application of a Model-based Fault Detection System to NuclearGoogle Scholar
  17. Plant Signals,“ Proc. 9th Intl. Conf. on IntelligentSystems Applications to Power Systems, Seoul, Korea.Google Scholar
  18. Gull, S.F. “Bayesian Inductive Inference and Maximum Entropy,” Maximum Entropy and Bayesian Methods in Science and Engineering,Vol.1, Erickson and Smith, eds., pp.53–74, Kluwer, Dordrecht.Google Scholar
  19. Hadamard, J. (1923), Lectures on Cauchy’s Problem in Linear Partial Differential Equations, Yale University Press, New Haven.Google Scholar
  20. Hansen, P.C. (1989), Regularization, GSVD and Truncated GSVD,BIT 29, pp. 491504.Google Scholar
  21. Hansen, P.C. (1990), The Discrete Picard Condition for Discrete Ill-Posed Problems, BIT 30, pp. 658–672.Google Scholar
  22. Hansen, P.C. (1994), Regularization Tools: A Matlab package for analysis and solution of discrete ill posed problems, Numer. Algorithms, vol. 6, pp. 1–35.Google Scholar
  23. Hansen, P.C. (1995), Test Matrices for Regularization Methods, SIAM J. SCI. Comput. vol. 16, No. 2, pp. 506–512.Google Scholar
  24. Hansen, P.C. (1997), Rank —Deficient and Discrete Ill-Posed Problems. Numerical Aspects of Linear Inversion, SIAM, Philadelphia.MATHGoogle Scholar
  25. Hansen, P.C. (1992), Analysis of Discrete Ill-Posed Problems by Means of the L-curve, SIAM Review vol. 34, No. 4, pp. 561–58.Google Scholar
  26. Hardy, C.R., D.W. Miller, B.K. Hajek (1992), “A Model-Based Approach to Malfunction Isolation in Interacting Systems,” Proceedings of the 8th Power Plant Control & Testing Symposium, Knoxville, Tennessee, 37.01–37.13.Google Scholar
  27. Hertz, J., A. Krogh, and R.G. Palmer (1991), Introduction to the Theory of Neural Computation,Addison-Wesley.Google Scholar
  28. Hines, J.W. and D.J. Wrest (1997a), “Signal Validation Using an Adaptive Neural Fuzzy Inference System,” Nuclear Technology, August, pp. 181–193.Google Scholar
  29. Hines, J.W. and R.E. Uhrig (1997b), “Use of Autoassociative Neural Networks for Signal Validation,” Journal of Intelligent and Robotic Systems, Kluwer Academic Press.Google Scholar
  30. Hines, J.W., R.E., Uhrig, C. Black and X. Xu (1997c), “An Evaluation of Instrument Calibration Monitoring Using Artificial Neural Networks,” published in the proceedings of the 1997 American Nuclear Society Winter Meeting, in Albuquerque, NM, November 16–20.Google Scholar
  31. Hoerl, A.E., and R.W. Kennard (1970), Ridge Regression: Biased Estimation for Nonorthogonal Problems, Technometrics, 12, pp. 55–67.CrossRefMATHGoogle Scholar
  32. Holbert, K.E. and B.R. Upadhyaya (1990), “An Integrated Signal Validation System For Nuclear Power Plants,” Nuclear Technology, Vol. 92, pp. 411–427.Google Scholar
  33. Holbert, K.E., Heger, S.A. and A.M. Ishaque, (1995) “Fuzzy Logic For Power Plant Signal Validation,” Proceedings of the 9th Power Plant Control & Testing Symposium, Knoxville, Tennessee, May 24–26, 20.01–20.15.Google Scholar
  34. Hornick, K., Stinchcombe, M., and H. White, 1989, Multilayer Feedforward Networks are Universal Approximators, Neural Networks, 2, pp 359–366.CrossRefGoogle Scholar
  35. Hoskuldsson, A., (1988), “PLS Regression Methods,” Journal of Chemometrics, Vol. 2, pp. 211–228.CrossRefGoogle Scholar
  36. Ikonomopoulos, A., R.E. Uhrig, L. H. Tsoukalas (1992), “A Methodology for Performing Virtual Measurements in a Nuclear Reactor System,” Transactions of the 1992 American Nuclear. Society International Conference on Fifty Years of Controlled Nuclear Chain Reaction: Past, Present, and Future, Chicago, Illinois, 106–107.Google Scholar
  37. Isermann, R. (1984), “Process Fault Detection Based on Modeling and Estimation Methods-A Survey,” Automatica, Vol. 20, No. 4, 381–404.CrossRefGoogle Scholar
  38. Jolliffe, I. (1986), Principal Components Analysis,, Springer-Verlag, New York.CrossRefGoogle Scholar
  39. Kavaklioglu, K., and Belle R. Upadhyaya (1994), “Monitoring Feedwater Flow Rate and Component Thermal Performance of Pressurized Water Reactors By Means of Artificial Neural Networks,” Nuclear Technology Vol. 107.Google Scholar
  40. Kittamura, M. (1980), “Detection of Sensor Failures in Nuclear Plants Using Analytical Redundancy,” Transactions of the American Nuclear Society, 34, 581–583.Google Scholar
  41. Kramer, R. (1998), Chemometric Techniques for Quantitative Analysis,Marcel-Dekker.Google Scholar
  42. MacKay, David J.C. (1992), “Bayesian Interpolation,” Neural Computation, Vol. 4, No. 3, pp. 415–447.CrossRefGoogle Scholar
  43. MacKay, David J.C. (1992), “A Practical Bayesian Framework for Backpropagation Networks,” Neural Computation, Vol. 4 No. 3, pp. 448–472CrossRefGoogle Scholar
  44. MacKay, David J.C. (1995), “Bayesian Methods for Neural Networks:Theory and Applications,” Course notes for neural network summer school. University of Cambridge programme for industry.Google Scholar
  45. Morozov, V.A. (1984), Methods for Solving Incorrectly Posed Problems, Springer-Verlag, New York.CrossRefGoogle Scholar
  46. Nuclear News, “Flow Rate Mismeasurement Causes Unneeded Derating,” Nucl. News, 36, 2, 39, Feb., 1993.Google Scholar
  47. Patton, R.J., J. Chen (1991), “A Review of Parity Space Approaches to Fault Diagnosis,” IFAC/IMACS Safeprocess Conference, Baden-Baden, Germany, 239–255.Google Scholar
  48. Qin, S.J., and T.J. McAvoy (1992), “Nonlinear PLS Modeling Using Neural Networks,” Computers chem. Engng., Vol. 16, No. 4, pp. 379–391.CrossRefGoogle Scholar
  49. Qualls, A.L., R.E. Uhrig, and B.R. Upadhyaya (1988), “Development of an Expert System for Signal Validation,” Topical Report prepared for the U.S. Department of Energy, by The University of Tennessee, Knoxville, DOE/NE/37959–17.Google Scholar
  50. Singer, R.M., K. C. Gross, J.P. Herzog, R. W. King, and S. W. Wegerich (1997), “Model-Based Nuclear Power Plant Monitoring and Fault Detection: Theoretical Foundations,” Proc. 9th Intl. Conf. on Intelligent Systems Applications to Power Systems, Seoul, Korea.Google Scholar
  51. Tikhonov, A.N. (1963), Solution of incorrectly formulated problems and the regularization method, Doklady Akad. Nauk USSR 151 (1963), pp. 501–504.Google Scholar
  52. Tsoukalas, L.H. (1992), “Expert Systems for Power Plant Applications: An Overview,” Proceedings of the 8th Power Plant Control & Testing Symposium, Knoxville, Tennessee, May 27–29, pp47. 01–47. 10.Google Scholar
  53. Uhrig, R.E. (1993), “Artificial Neural Networks and Potential Applications to Nuclear Power Plants,” Proceedings of the Conference on Structural Mechanics in Reactor Technology, Knostanz, Germany.Google Scholar
  54. Uhrig, R.E., J.W. Hines, and W.R. Nelson (1998), “Integration of Artificial Intelligence Systems into a Monitoring and Diagnostic System for Nuclear Power Plants,” presented at the Special Meeting on Instrumentation and Control of the Halden Research Center, Lillihammer, Norway, March 28–21.Google Scholar
  55. Upadhyaya, B.R., E. Eryurek (1992), “Application of Neural Networks for Sensor Validation and Plant Monitoring,” Nuclear Technology, Vol. 97, 170–176.Google Scholar
  56. Willsky, A.S. (1976), “A Survey of Design Methods for Failure Detection in Dynamic Systems,” Automatica, Vol. 12, 601–611.MathSciNetCrossRefMATHGoogle Scholar
  57. Flow Rate Mismeasurement Causes Unneeded Derating,“ Nucl. News,36, 2, 39, Feb., 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • J. Wesley Hines
    • 1
  • Andrei V. Gribok
    • 1
  • Ibrahim Attieh
    • 1
  • Robert E. Uhrig
    • 1
  1. 1.Nuclear Engineering DepartmentThe University of Tennessee KnoxvilleTennesseeUSA

Personalised recommendations