Abstract
In a nuclear power plant (NPP), periodic sensor calibrations are required to assure sensors are operating correctly. However, only a few faulty sensors are found to be calibrated. For the safe operation of an NPP and the reduction of unnecessary calibration, on-line calibration monitoring is needed. Most researches have been focused on improving only the accuracy of the system although sensitivity is another important performance index. This paper presents multi-response optimization for an on-line sensor drift monitoring system to detect drift and estimate sensor signal effectively. Accuracy and sensitivity of the principal component-based auto-associative support vector regression (PCSVR) were optimized at the same time by desirability function approach. Response surface methodology (RSM) is employed to efficiently determine the optimal values of SVR hyperparameters. The proposed optimization method was confirmed with actual plant data of Kori NPP Unit 3. The results show the trade-off between the accuracy and sensitivity of the model as we expected.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Upadhyaya, B.R., Eryurek, E.: Application of Neural Networks for Sensor Validation and Plant Monitoring. Nuclear Technology 97, 170–176 (1992)
Mott, Y., King, R.W.: Pattern Recognition Software for Plant Surveillance, U.S. DOE Report (1987)
Fantoni, P., Figedy, S., Racz, A.: A Neuro-Fuzzy Model Applied to Full Range Signal Validation of PWR Nuclear Power Plant Data. In: FLINS 1998, Antwerpen, Belgium (1998)
Cortes, C., Vapnik, V.: Support vector networks. Machine Learning 20, 273–297 (1995)
Zavaljevski, N., Gross, K.C.: Support Vector Machines for Nuclear Reactor State Estimation. In: ANS International Topical Meeting, Pittsburgh, USA, May 7-11 (2000)
Seo, I.-Y., Kim, S.J.: An On-line Monitoring Technique Using Support Vector Regression and Principal Component Analysis. In: CIMCA 2008, Vienna, Austria, December 10-12 (2008)
Seo, I.-Y., Ha, B.-N., Lee, S.-W., Shin, C.-H., Kim, S.-J.: Principal Components Based Support Vector Regression Model for On-line Instrument Calibration Monitoring in NPPs. Nucl. Eng. Tech. 42(2), 219–230 (2010)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)
Derringer, G., Suich, R.: Simultaneous optimization of several response variables. Journal of Quality Technology 12, 214–219 (1980)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Seo, IY., Ha, BN., Park, MH. (2011). Multi-response Variable Optimization in Sensor Drift Monitoring System Using Support Vector Regression. In: Nguyen, N.T., Kim, CG., Janiak, A. (eds) Intelligent Information and Database Systems. ACIIDS 2011. Lecture Notes in Computer Science(), vol 6592. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20042-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-20042-7_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20041-0
Online ISBN: 978-3-642-20042-7
eBook Packages: Computer ScienceComputer Science (R0)