0
SPECIAL SECTION PAPERS

Intelligent Identification of Boiling Water Reactor State Utilizing Relevance Vector Regression Models

[+] Author and Article Information
Miltiadis Alamaniotis

Applied Intelligent Systems Laboratory,
School of Nuclear Engineering,
Purdue University,
400 Central Dr.,
West Lafayette, IN 47907
e-mail: malamani@ecn.purdue.edu

Mauro Cappelli

ENEA UTFISST-MEPING-Casaccia
Research Center,
Via Anguillarese,
Rome 301-00123, Italy
e-mail: mauro.cappelli@enea.it

Manuscript received October 3, 2016; final manuscript received June 26, 2017; published online March 5, 2018. Assoc. Editor: Leon Cizelj.

ASME J of Nuclear Rad Sci 4(2), 020904 (Mar 05, 2018) (9 pages) Paper No: NERS-16-1137; doi: 10.1115/1.4037203 History: Received October 03, 2016; Revised June 26, 2017

Modernization of reactor instrumentation and control systems is mainly characterized by the transition from analog to digital systems, expressed by replacement of hardware equipment with new software-driven devices. Digital systems may share intelligence capabilities where except for measuring and processing information may also make decisions. State identification systems are systems that process the measurements taken over operational variables and output the state of the reactor. This paper frames itself in the area of control systems applied to state identification of boiling water reactors (BWRs). It presents a methodology that utilizes machine learning tools, and more specifically, a set of relevance vector machines (RVMs) in order to process the incoming signals and identify the state of the BWR in real time. The proposed methodology is comprised of two stages: in the first stage, each RVM identifies the state of the BWR, while the second stage collects the RVM outputs and decides about the real state of the reactor adopting majority voting. The proposed methodology is tested on a set of real-world BWR data taken from the experimental FIX-II facility for recognizing various BWR loss-of-coolant accidents (LOCAs) as well as normal states. Results exhibit the efficiency of the methodology in correctly identifying the correct state of the BWR while promoting real time identification by providing fast responses. However, a strong dependence of identification performance on the form of kernel functions is also concluded.

FIGURES IN THIS ARTICLE
<>
Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.

References

Alamaniotis, M. , Ikonomopoulos, A. , and Tsoukalas, L. H. , 2011, “ On-line Surveillance of Nuclear Power Plant Peripheral Components Using Support Vector Regression,” International Symposium on Future Instrumentation and Control for Nuclear Power Plants, Cognitive Systems Engineering in Process Control, and International Symposium on Symbiotic Nuclear Power Systems (ICI), Daejeon, South Korea, Aug. 21–25, p. 1230. https://inis.iaea.org/search/search.aspx?orig_q=RN:44079341
Isermann, R. , 1984, “ Process Fault Detection Based on Modeling and Estimation Methods—A Survey,” Automatica, 20(4), pp. 387–404. [CrossRef]
Alamaniotis, M. , Ikonomopoulos, A. , and Tsoukalas, L. H. , 2012, “ Optimal Assembly of Support Vector Regressors With Application to System Monitoring,” Int. J. Artif. Intell. Tools, 21(06), p. 1250034. [CrossRef]
Nabeshima, K. , Suzudo, T. , Seker, S. , Ayaz, E. , Barutcu, B. , Türkcan, E. , Ohno, T. , and Kudo, K. , 2003, “ On-Line Neuro-Expert Monitoring System for Borssele Nuclear Power Plant,” Prog. Nucl. Energy, 43(1), pp. 397–404. [CrossRef]
Reifman, J. , 1997, “ Survey of Artificial Intelligence Methods for Detection and Identification of Component Faults in Nuclear Power Plants,” Nucl. Technol., 119(1), pp. 76–97. http://www.ans.org/pubs/journals/nt/a_35396
Ikonomopoulos, A. , Alamaniotis, M. , Chatzidakis, S. , and Tsoukalas, L. H. , 2013, “ Gaussian Processes for State Identification in Pressurized Water Reactors,” Nucl. Technol., 182(1), pp. 1–12. http://www.tandfonline.com/doi/abs/10.13182/NT13-A15821
Alamaniotis, M. , Chatzidakis, S. , and Tsoukalas, L. H. , 2015, “ Data Driven Monitoring of Complex Energy Systems: Gaussian Process Kernel Machines for Fault Identification With Application to Boiling Water Reactors,” Intelligent Computing Systems (Studies in Computational Intelligence), G. Tsihrintzis , and M. Virvou , eds., Vol. 627, Springer, Berlin, pp. 177–188.
Embrechts, M. J. , and Benedek, S. , 2004, “ Hybrid Identification of Nuclear Power Plant Transients With Artificial Neural Networks,” IEEE Trans. Ind. Electron., 51(3), pp. 686–693. [CrossRef]
Baptista Filho, B. D. , and Oliveira Barroso, A. C. D. , 2003, “ Identification of IRIS Reactor Transients With Self-Organized Maps,” Global 2003: Atoms for Prosperity: Updating Eisenhower's Global Vision for Nuclear Energy (GENES4/ANP), Kyoto, Japan, Sept. 15–19, Paper No. 1185. https://www.ipen.br/biblioteca/cd/genes4/2003/papers/1185-final.pdf
Varde, P. V. , Chowdhury, R. , Vinod, G. , Babar, A. K. , and Kushwaha, H. S. , 2002, “ Simulation of Pressurised Heavy Water Reactor Data Using Artificial Neural Network for Reactor Status/Transient Identification,” Barc Newsletter, International Conference on Quality, Reliability and Control, Oxford, UK, Mar. 21–22, pp. 57–63. http://www.barc.gov.in/publications/nl/2002/200210-08.pdf
Roverso, D. , 2002, “ Plant Diagnostics by Transient Classification: The Aladdin Approach,” Int. J. Intell. Syst., 17(8), pp. 767–790. [CrossRef]
Roverso, D. , 2000, “ Soft Computing Tools for Transient Classification,” Inf. Sci., 127(3), pp. 137–156. [CrossRef]
Akkurt, H. , and Çolak, Ü. , 2002, “ PWR System Simulation and Parameter Estimation With Neural Networks,” Ann. Nucl. Energy, 29(17), pp. 2087–2103. [CrossRef]
Antonio, C. D. , Martinez, A. S. , and Schirru, R. , 2003, “ A Neural Model for Transient Identification in Dynamic Processes With ‘Don't Know’ Response,” Ann. Nucl. Energy, 30(13), pp. 1365–1381. [CrossRef]
Gottlieb, C. , Arzhanov, V. , Gudowski, W. , and Garis, N. , 2006, “ Feasibility Study on Transient Identification in Nuclear Power Plants Using Support Vector Machines,” Nucl. Technol., 155(1), pp. 67–77. http://www.ans.org/pubs/journals/nt/a_3746
Jiang, B. T. , Hines, J. W. , and Zhao, F. Y. , 2016, “ Application of Fuzzy Weighted Support Vector Regression to Accidents Condition Monitoring of Nuclear Power Plant,” ASME Paper No. ICONE24-60983.
Medeiros, J. A. C. C. , and Schirru, R. , 2008, “ Identification of Nuclear Power Plant Transients Using the Particle Swarm Optimization Algorithm,” Ann. Nucl. Energy, 35(4), pp. 576–582. [CrossRef]
Dos Santos Nicolau, A. , and Schirru, R. , 2014, “ QDPSO and Minkowski Distance Applied to Transient Diagnosis System,” Sixth International Conference on Agents and Artificial Intelligence (ICAART), Angers, France, Mar. 6–8, pp. 611–616. https://www.researchgate.net/profile/Andressa_Nicolau/publication/292878434_QDPSO_and_minkowski_distance_applied_to_transient_diagnosis_system/links/58330edd08ae102f07366036/QDPSO-and-minkowski-distance-applied-to-transient-diagnosis-system.pdf
Prusty, M. R. , Chakraborty, J. , Seetha, H. , Jayanthi, T. , and Velusamy, K. , 2014, “ Fuzzy Logic Based Transient Identification System for Operator Guidance Using Prototype Fast Breeder Reactor Operator Training Simulator,” IEEE International Advance Computing Conference (IACC), Gurgaon, India, Feb. 21–22, pp. 1259–1264.
Guimarães, A. C. F. , and Lapa, C. M. F. , 2004, “ Nuclear Transient Phase Ranking Table Using Fuzzy Inference System,” Ann. Nucl. Energy, 31(15), pp. 1803–1812. [CrossRef]
Wang, X. , Tsoukalas, L. H. , Wei, T. Y. , and Reifman, J. , 2001, “ An Innovative Fuzzy-Logic-Based Methodology for Trend Identification,” Nucl. Technol., 135(1), pp. 67–84. http://www.tandfonline.com/doi/abs/10.13182/NT01-A3206
Da Costa, R. G. , de Abreu Mol, A. C. , de Carvalho, P. V. R. , and Lapa, C. M. F. , 2011, “ An Efficient Neuro-Fuzzy Approach to Nuclear Power Plant Transient Identification,” Ann. Nucl. Energy, 38(6), pp. 1418–1426. [CrossRef]
Ikonomopoulos, A. , Tsoukalas, L. H. , and Uhrig, R. E. , 1993, “ Integration of Neural Networks With Fuzzy Reasoning for Measuring Operational Parameters in a Nuclear Reactor,” Nucl. Technol., 104(1), pp. 1–12. http://www.tandfonline.com/doi/abs/10.13182/NT93-A34866
Alamaniotis, M. , Jin, X. , and Ray, A. , 2015, “ On-Line Condition Monitoring of Boiling Water Reactors Using Symbolic Dynamic Analysis,” Nineth International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human Machine Interface Technologies, Charlotte, NC, Feb. 22–26, pp. 722–732.
Jin, X. , Guo, Y. , Sarkar, S. , Ray, A. , and Edwards, R. M. , 2011, “ Anomaly Detection in Nuclear Power Plants Via Symbolic Dynamic Filtering,” IEEE Trans. Nucl. Sci., 58(1), pp. 277–288. [CrossRef]
Dos Santos Nicolau, A. , Schirru, R. , and de Moura Meneses, A. A. , 2011, “ Quantum Evolutionary Algorithm Applied to Transient Identification of a Nuclear Power Plant,” Prog. Nucl. Energy, 53(1), pp. 86–91. [CrossRef]
Sun, Y. , Ping, M. , and Li, F. , 2015, “ MSET-Based Abnormal Condition Monitoring Technology of Nuclear Power Plant,” Nineth International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human Machine Interface Technologies, Charlotte, NC, Feb. 22–26, pp. 18–23.
Ikonomopoulos, A. , and Endou, A. , 1998, “ Wavelet Decomposition and Radial Basis Function Networks for System Monitoring,” IEEE Trans. Nucl. Sci., 45(5), pp. 2293–2301. [CrossRef]
Antonopoulos-Domis, M. , and Tambouratzis, T. , 1998, “ System Identification During a Transient Via Wavelet Multiresolution Analysis Followed by Spectral Techniques,” Ann. Nucl. Energy, 25(7), pp. 465–480. [CrossRef]
Ciftcioglu, O. , and Turkcan, E. , 1996, “ Transient Detection by Wavelet Transform in Plant Monitoring,” Symposium on Nuclear Reactor Surveillance and Diagnostics (SMORN VII), Avignon, France, June 19–13, Vol. 1, pp. 185–193. https://inis.iaea.org/search/search.aspx?orig_q=RN:29017197
Shen, B. , Williams, J. G. , and Jouse, W. C. , 1994, “ Wavelet Transform of Reactor Power Transients,” IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Norfolk, VA, Oct. 30–Nov. 5, Vol. 3, pp. 1041–1043.
Chang, Y. , Huang, X. , Hao, Y. , and Li, C. W. , 2013, “ Linear Representation and Sparse Solution for Transient Identification in Nuclear Power Plants,” IEEE Trans. Nucl. Sci., 60(1), pp. 319–327. [CrossRef]
Mol, A. C. , Almeida, J. C. , Pereira, C. M. , Marins, E. R. , and Lapa, C. M. F. , 2006, “ Neural and Genetic-Based Approaches to Nuclear Transient Identification Including ‘Don't Know' Response,” Prog. Nucl. Energy, 48(3), pp. 268–282. [CrossRef]
Kwon, K. C. , and Kim, J. H. , 1999, “ Accident Identification in Nuclear Power Plants Using Hidden Markov Models,” Eng. Appl. Artif. Intell., 12(4), pp. 491–501. [CrossRef]
Ikonomopoulos, A. , Uhrig, R. E. , and Tsoukalas, L. H. , 1991, “ A Hybrid Neural Network-Fuzzy Logic Approach to Nuclear Power Plant Transient Identification,” International Conference on Frontiers in Innovative Computing for the Nuclear Industry (AI-91), Jackson, WY, Sept. 15–18, pp. 217–226. http://www.iaea.org/inis/collection/NCLCollectionStore/_Public/24/054/24054612.pdf
Cheon, S. W. , and Chang, S. H. , 1993, “ Application of Neural Networks to a Connectionist Expert System for Transient Identification in Nuclear Power Plants,” Nucl. Technol., 102(2), pp. 177–191. http://www.tandfonline.com/doi/abs/10.13182/NT93-A34815
Hsiao, T. Y. , Lin, C. , and Yuann, Y. R. , 2010, “ Identification of Initiating Events for Pressurized Water Reactor Accidents,” Ann. Nucl. Energy, 37(11), pp. 1502–1512. [CrossRef]
Lin, C. , and Chang, H. J. , 2011, “ Identification of Pressurized Water Reactor Transient Using Template Matching,” Ann. Nucl. Energy, 38(7), pp. 1662–1666. [CrossRef]
Galbally, J. , and Galbally, D. , 2015, “ A Pattern Recognition Approach Based on DTW for Automatic Transient Identification in Nuclear Power Plants,” Ann. Nucl. Energy, 81, pp. 287–300. [CrossRef]
Ikonomopoulos, A. , Varvayanni, M. , and Catsaros, N. , 2015, “ Instrumentation and Control Implementations in Research Reactors: A Review,” 24th International Conference Nuclear Energy for New Europe (NENE), Portorož, Slovenia, Sept. 14–17, p. 310. http://www.djs.si/proc/nene2015/pdf/NENE2015_310.pdf
Moshkbar-Bakhshayesh, K. , and Ghofrani, M. B. , 2013, “ Transient Identification in Nuclear Power Plants: A Review,” Prog. Nucl. Energy, 67, pp. 23–32. [CrossRef]
Bishop, C. M. , 2006, Pattern Recognition and Machine Learning, Springer, New York.
Yang, B. , Zhang, Z. , and Sun, Z. , 2007, “ Robust Relevance Vector Regression With Trimmed Likelihood Function,” IEEE Signal Process. Lett., 14(10), pp. 746–749. [CrossRef]
Tipping, M. E. , 2001, “ Sparse Bayesian Learning and the Relevance Vector Machine,” J. Mach. Learn. Res., 1, pp. 211–244. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.568.7983&rep=rep1&type=pdf
Alamaniotis, M. , and Cappelli, M. , 2016, “ Real-Time State Identification of Boiling Water Reactors Using Relevance Vector Machines,” ASME Paper No. ICONE24-60048.
Alamaniotis, M. , Bargiotas, D. , Bourbakis, N. , and Tsoukalas, L. H. , 2015, “ Genetic Optimal Regression of Relevance Vector Machines for Electricity Price Forecasting in Smart Grids,” IEEE Trans. Smart Grid, 6(6), pp. 2997–3005. [CrossRef]
Tsoukalas, L. H. , and Uhrig, R. E. , 1997, Fuzzy and Neural Approaches in Engineering, Wiley-Interscience, New York.
Nilsson, L. , and Gustafsson, P. A. , 1983, “ FIX-II: LOCA Blowdown and Pump Trip Heat Experiments,” Swedish Nuclear Power Plant Inspectorate, Stockholm, Sweden, Report No. STUDSVIK/E4-79-22.
Alamaniotis, M. , Ikonomopoulos, A. , and Tsoukalas, L. H. , 2012, “ Probabilistic Kernel Approach to Online Monitoring of Nuclear Power Plants,” Nucl. Technol., 177(1), pp. 132–144. http://www.tandfonline.com/doi/abs/10.13182/NT12-A13333
Alamaniotis, M. , Ikonomopoulos, A. , and Tsoukalas, L. H. , 2010, “ Gaussian Processes for Failure Prediction of Slow Degradation Components in Nuclear Power Plants,” European Safety and Reliability Conference, Prague, Czech Republic, Sept. 7–10, pp. 2096–2102.

Figures

Grahic Jump Location
Fig. 1

Block diagram of the proposed BWR state identification methodology

Grahic Jump Location
Fig. 2

RVR training process for state identification

Grahic Jump Location
Fig. 3

RVR “potentially identified” state process

Grahic Jump Location
Fig. 4

Differential pressure between the lower plenum at outlet level and the bottom of lower plenum in FIX-II facility for (a) LOCA 3025, (b) LOCA 3061, and (c) LOCA 5052

Grahic Jump Location
Fig. 5

Differential pressure between lower plenum at bundle inlet level and bundle bottom in FIX-II facility for (a) LOCA 3025, (b) LOCA 3061, and (c) LOCA 5052

Grahic Jump Location
Fig. 6

Differential pressure between bundle level 5 and bundle level 6 in FIX-II facility for (i) LOCA 3025, (ii) LOCA 3061, and (iii) LOCA 5052

Grahic Jump Location
Fig. 7

Identification results for cases 1–5 (combinations 1–5 from Table 4)

Grahic Jump Location
Fig. 8

Identification results for cases 6–10 (combinations 6–10 from Table 4)

Grahic Jump Location
Fig. 9

Identification results for cases 11–15 (combinations 11–15 from Table 4)

Grahic Jump Location
Fig. 10

Identification results for cases 16–21 (combinations 16–21 from Table 4)

Grahic Jump Location
Fig. 11

Average correct identification rate for each (combinations 1–21 from Table 4)

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In