Large-scale signal reconstruction for sensor monitoring and diagnostics in nuclear power plants

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Giulio Gola Davide Roverso Mario Hoffmann

Abstract

On-line sensor monitoring and diagnostics systems aim at detecting anomalies in sensors and reconstructing their correct signals during operation. Since 1994, research at the OECD Halden Reactor Project has focused on the problem of sensor monitoring and diagnostics, eventually leading to the development of the PEANO system for signal validation and reconstruction. PEANO combines empirical techniques like Fuzzy Clustering and Auto- Associative Neural Networks and has proved to be successful in a variety of practical applications. Nevertheless, using one single empirical model sets a limit to the number of signals that can be handled at a time. Recently, efforts have been made to extend the applicability of PEANO to the whole plant, which requires the validation and reconstruction of thousands of signals. This has entailed moving from a single-model to an ensemble-of-model approach which has involved the investigation of new issues. This paper presents the method hereby developed for on-line, large scale sensor monitoring and signal reconstruction and a practical application of the method to the reconstruction of signals measured at nuclear power plants.

How to Cite

Gola, G. ., Roverso, D. ., & Hoffmann, M. . (2010). Large-scale signal reconstruction for sensor monitoring and diagnostics in nuclear power plants. Annual Conference of the PHM Society, 2(2). https://doi.org/10.36001/phmconf.2010.v2i1.1915
Abstract 16 | PDF Downloads 14

##plugins.themes.bootstrap3.article.details##

Keywords

ensemble methods, applications: nuclear, sensor monitoring, signal validation, empirical models

References
(Baraldi et al., 2008a) P. Baraldi, E. Zio, G. Gola, D. Roverso, and M. Hoffmann, Genetic Algorithms for Signal Grouping in Sensor Validation: a Comparison of the Filter and Wrapper Approaches, Journal of Risk and Reliability, Proc. IMechE, vol. 222(Part O), pp. 189-206, 2008.

(Baraldi et al., 2008b) P. Baraldi, E. Zio, G. Gola, D. Roverso, and M. Hoffmann, Reconstruction of Faulty Signals by an Ensemble of Principal Component Analysis Models Optimized by a Multi- objective Genetic Algorithm, in Proceedings of the FLINS Conference, Madrid, Spain, 2008.

(Baraldi et al., 2009a) P. Baraldi, E. Zio, G. Gola, D. Roverso, and M. Hoffmann, A Procedure for the Reconstruction of Faulty Signals by means of an Ensemble of Regression Models based on Principal Components Analysis, in Proceedings of the ANS Topical Meeting - Nuclear Plant Instrumentation, Controls, and Human Machine Interface Technology, Knoxville, Tennessee, US, 2009.

(Baraldi et al., 2009b) P. Baraldi, E. Zio, G. Gola, D. Roverso, and M. Hoffmann, A Novel Ensemble Model Aggregation for Robust Signal Reconstruction in Nuclear Power Plants Monitoring, in Proceedings og 22nd International COMADEM Conference, San Sebastian, Spain, 2009.

(Baraldi et al., 2009c) P. Baraldi, E. Zio, G. Gola, D. Roverso, and M. Hoffmann, Aggregation of Randomized Model Ensemble Outcomes for Reconstructing Nuclear Signals from Faulty Sensors, in Proceedings of ESREL Conference, Prague, Czech Republic, vol 1, pp. 83-88, 2009.

(Baraldi et al., 2010) P. Baraldi, E. Zio, G. Gola, D. Roverso, and M. Hoffmann, Robust Nuclear Signal Reconstruction by a Novel Ensemble Model Aggregation Procedure, International Journal of Nuclear Knowledge Management, vol. 4(1), pp. 32- 41, 2010.

(Breiman, 1996) L. Breiman, Bagging Predictors, Machine Learning, vol. 24, pp. 123-140, 1996.

(Brown et al., 2005) G. Brown, J.L. Wyatt, and P. Tino, Managing Diversity in Regression Ensembles, Journal of Machine Learning Research, vol. 6, pp. 1621-1650, 2005.
Applications of PEANO for On-line Monitoring in Power Plants, Progress in nuclear energy, vol. 46, pp. 206-225, 2005.

(Fantoni and Mazzola, 1996) P.F. Fantoni and A. Mazzola, Multiple-Failure Signal Validation in Nuclear Power Plants using Artificial Neural Networks, Nuclear technology, vol. 113(3), pp. 368- 374, 1996.

(Fantoni et al., 2003) P.F. Fantoni, M. Hoffmann, R. Shankar, and E.L. Davis, On-line Monitoring of Instrument Channel Performance in Nuclear Power Plant using PEANO, Progress in Nuclear Energy, vol. 43(1-4), pp. 83-89, 2003.

(Gola et al., 2007) G. Gola, E. Zio, P. Baraldi, D. Roverso, and M. Hoffmann, Signal Grouping for Sensor Validation: a Multi-Objective Genetic Algorithm Approach, HWR-852, OECD Halden Reactor Project, 2007.

(Gola et al., 2008) G. Gola, E. Zio, P. Baraldi, D. Roverso, and M. Hoffmann, Reconstructing Signals for Sensor Validation by a GA-optimized Ensemble of PCA Models, HWR-894, OECD Halden Reactor Project, 2008.

(Heger et al., 1996) A.S. Heger, K.E. Holbert, and A.M. Ishaque, Fuzzy Associative Memories for Instrument Fault Detection, Annals of Nuclear Energy, vol. 23(9), pp. 739-756, 1996.

(Hoffmann et al., 2001) M. Hoffmann, P.F. Fantoni, and M. Sepielli. PEANO Advancements in 1999- 2000. HWR-641, OECD Halden Reactor Project, 2001.

(Hoffmann, 2005) M. Hoffmann, On-line Monitoring for Calibration Reduction, HWR-784, OECD Halden Reactor Project, 2005.

(Hoffmann, 2006) M. Hoffmann, Signal Grouping Algorithm for an Improved On-line Calibration Monitoring System, in Proceedings of FLINS Conference, Genova, Italy, 2006.

(Hoffmann and Kirschner, 2004) M. Hoffmann and A. Kirschner, PEANO - Findings from using the NNPLS Algorithm and HAMMLAB Applications, HWR-690, OECD Halden Reactor Project, 2004.

(Holbert, 1992) K.E. Holbert, Neural Networks for Signal Validation in Nuclear Power Plants, in Proceedings of the Second Annual Industrial
Partnership Program Conference, 1992.

(Holbert and Upadhyaya, 1990) K.E. Holbert and B.R. Upadhyaya, An Integrated Signal Validation for Nuclear Power Plants, Nuclear Technology, vol.
92(3), pp. 411-427, 1990.

(Holbert et al., 1995) K.E. Holbert,, A.S. Heger, and
A.M. Ishaque, Fuzzy Logic for Power Plant Signal Validation, in Proceedings of the Ninth Power Plant Dynamics, Control & Testing Symposium, Knoxville, US, 1995.

(Kirschner and Hoffmann, 2004) A. Kirschner and M. Hoffmann, PEANO NNPLS: Advancements in 2002-03, HWR-741, OECD Halden Reactor Project, 2004.

(Polikar, 2006) R. Polikar, Ensemble based Systems in Decision Making, IEEE Circuits and Systems Magazine, vol. 6(3), pp. 21-45, 2006.

(Roverso et al., 2007) D. Roverso, M. Hoffmann, E. Zio, P. Baraldi, and G. Gola, Solutions for Plant- wide On-line Calibration Monitoring, in Proceedings of the ESREL Conference, vol. 1, pp. 827-832, Stavanger, Norway, 2007.

(Song and Kabasov, 2001) Q. Song and N. Kasabov, ECM - A Novel On-line, Evolving Clustering Method and its Applications, in Proceedings of the Fifth Biannual Conference on Artificial Neural Networks and Expert Systems, Dunedin, New Zealand, pp. 87-92, 2001.

(Tsymbal et al., 2001) A. Tsymbal, S. Puuronen, and I. Skrypnyk I.: Ensemble Feature Selection with Dynamic Integration of Classifiers, in Proceedings of the Int. ICSC Congress on Computational Intelligence Methods and Applications, Bangor, Wales, UK, pp. 558-564, 2001.

(Tsymbal et al., 2005) A. Tsymbal, M. Pechenizkiy, and P. Cunningham, Diversity in Search Strategy for Ensemble Feature Selection, Information Fusion, vol. 6, pp. 83-98, 2005.

(Wang and Holbert, 1995) X. Wang and K.E. Holbert, A Neural Network Realization of Linear Least- Square Estimate for Sensor Validation, in Proceedings of the Ninth Power Plant Dynamics, Control & Testing Symposium, Knoxville, US, 1995.

(Yu et al., 2007) Y. Yu, Z.-H. Zhou, and K. Ming Ting, Cocktail Ensemble for Regression, in Proceedings of the 7th IEEE International Conference on Data Mining, Omaha, Nebraska, US pp.721-726,. 2007.

(Zio et al., 2007) E. Zio, P. Baraldi, G. Gola, D. Roverso, and M. Hoffmann, Genetic Algorithms for Grouping of Signals for System Monitoring and Diagnostics, in Proceedings of the ESREL Conference, vol. 1, pp. 833-840, Stavanger, Norway, 2007.
Section
Poster Presentations