Optimization of a dynamic uncertain causality graph for fault diagnosis in nuclear power plant
Tóm tắt
Fault diagnostics is important for safe operation of nuclear power plants (NPPs). In recent years, data-driven approaches have been proposed and implemented to tackle the problem, e.g., neural networks, fuzzy and neuro-fuzzy approaches, support vector machine, K-nearest neighbor classifiers and inference methodologies. Among these methods, dynamic uncertain causality graph (DUCG) has been proved effective in many practical cases. However, the causal graph construction behind the DUCG is complicate and, in many cases, results redundant on the symptoms needed to correctly classify the fault. In this paper, we propose a method to simplify causal graph construction in an automatic way. The method consists in transforming the expert knowledge-based DCUG into a fuzzy decision tree (FDT) by extracting from the DUCG a fuzzy rule base that resumes the used symptoms at the basis of the FDT. Genetic algorithm (GA) is, then, used for the optimization of the FDT, by performing a wrapper search around the FDT: the set of symptoms selected during the iterative search are taken as the best set of symptoms for the diagnosis of the faults that can occur in the system. The effectiveness of the approach is shown with respect to a DUCG model initially built to diagnose 23 faults originally using 262 symptoms of Unit-1 in the Ningde NPP of the China Guangdong Nuclear Power Corporation. The results show that the FDT, with GA-optimized symptoms and diagnosis strategy, can drive the construction of DUCG and lower the computational burden without loss of accuracy in diagnosis.
Tài liệu tham khảo
citation_journal_title=Neural Process. Lett.; citation_title=Least squares support vector machine classifiers; citation_author=JAK Suykens, J Vandewalle; citation_volume=9; citation_issue=3; citation_publication_date=1999; citation_pages=293-300; citation_doi=10.1023/A:1018628609742; citation_id=CR1
citation_title=Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence/Book and Disk; citation_publication_date=1992; citation_id=CR2; citation_author=B Kosko; citation_publisher=Prentice Hall
citation_journal_title=Automatica; citation_title=Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: a survey and some new results; citation_author=PM Frank; citation_volume=26; citation_issue=3; citation_publication_date=1990; citation_pages=459-474; citation_doi=10.1016/0005-1098(90)90018-D; citation_id=CR3
citation_journal_title=Int. J. Comput. Intell. Syst.; citation_title=From fuzzy clustering to a fuzzy rule-based fault classification model; citation_author=E Zio, P Baraldi, IC Popescu; citation_volume=1; citation_issue=1; citation_publication_date=2008; citation_pages=60-76; citation_id=CR4
citation_journal_title=Risk Anal.; citation_title=A fuzzy decision tree for fault classification; citation_author=E Zio, P Baraldi, IC Popescu; citation_volume=28; citation_issue=1; citation_publication_date=2008; citation_pages=49-67; citation_doi=10.1111/j.1539-6924.2008.01002.x; citation_id=CR5
citation_journal_title=Int. J. Comput. Intell. Syst.; citation_title=Unsupervised clustering for fault diagnosis in nuclear power plant components; citation_author=P Baraldi, F Maio, E Zio; citation_volume=6; citation_issue=4; citation_publication_date=2013; citation_pages=764-777; citation_doi=10.1080/18756891.2013.804145; citation_id=CR6
E. Zio, F. Di Maio, Fuzzy similarity-based method for failure detection and recovery time estimation. Int. J. Perform. Eng. 6(5), 407–424 (2010).
http://www.researchgate.net/publication/282063966_A_fuzzy_similarity-based_method_for_failure_detection_and_recovery_time_estimation
citation_journal_title=IEEE Trans. Reliab.; citation_title=Fuzzy C-means clustering of signal functional principal components for post-processing dynamic scenarios of a nuclear power plant digital instrumentation and control system; citation_author=F Di Maio, P Secchi, S Vantini, E Zio; citation_volume=60; citation_issue=2; citation_publication_date=2011; citation_pages=415-425; citation_doi=10.1109/TR.2011.2134230; citation_id=CR8
citation_journal_title=IEEE Trans. Inf. Theory; citation_title=Nearest neighbor pattern classification; citation_author=TM Cover, PE Hart; citation_volume=13; citation_issue=1; citation_publication_date=1967; citation_pages=21-27; citation_doi=10.1109/TIT.1967.1053964; citation_id=CR9
W.R. Nelson, REACTOR: An expert system for diagnosis and treatment of nuclear reactor accidents. AAAI 296–301 (1982).
http://www.aaai.org/Papers/AAAI/1982/AAAI82-070.pdf
citation_journal_title=Ann. Nucl. Energy; citation_title=Fault diagnosis of Pakistan Research Reactor-2 with data-driven techniques; citation_author=F Jamil, M Abid, I Haq; citation_volume=90; citation_publication_date=2016; citation_pages=433-440; citation_doi=10.1016/j.anucene.2015.12.023; citation_id=CR11
B. Papin, G. Beltranda, Computerized monitoring systems: design requirements for a better impact on plant operation. Used Nucl. Power Plant Accid. Prev. Mitig. 169 (1989).
http://www.iaea.org/inis/collection/NCLCollectionStore/_Public/21/072/21072038.pdf#page=161
R. Bhatnagar, D.W. Miller, B.K. Hajek, et al., An integrated operator advisor system for plant monitoring, procedure management, and diagnosis. Nucl. Technol. 89(3), 281–317 (1990).
http://www.ans.org/pubs/journals/nt/a_34368
K. Haugset, N.T. Førdestrømmen, R.E. Grini, et al., Realisation of the integrated control room concept. ISACS (1991).
http://philpapers.org/rec/HAUROT-2
K. Follesø, N.T. Førdestrømmen, K. Haugset, et al., The integrated surveillance and control system ISACS: an advanced control room prototype, in International Conference on Design and Safety of Advanced Nuclear Power Plants (Tokyo, 1992).
http://www.ans.org/pubs/journals/nt/a_35000
T. Endestad, P. Meyer, GOMS Analysis as an Evaluation Tool in Process Control: An Evaluation of the ISACS-1 Prototype and the COPMA System (HWR-349) (1993).
http://www.researchgate.net/publication/239280321_Goms_analysis_as_an_evaluation_tool_in_process_control_an_evaluation_of_the_isacs-1_prototype_and_the_copma_system
citation_journal_title=Proc. Inst. Mech. Eng. O: J. Risk Reliab.; citation_title=Sensory information fusion-based fault diagnostics for complex electronic systems; citation_author=L Xu, J Xu; citation_volume=230; citation_issue=1; citation_publication_date=2016; citation_pages=109-119; citation_id=CR17
citation_journal_title=Reliab. Eng. Syst. Saf.; citation_title=An analytical model of electronic fault diagnosis on extension of the dependency theory; citation_author=Y Cui, J Shi, Z Wang; citation_volume=133; citation_publication_date=2015; citation_pages=192-202; citation_doi=10.1016/j.ress.2014.09.015; citation_id=CR18
D.T. Nguyen, Q.B. Duong, E. Zamai, et al., Fault diagnosis for the complex manufacturing system. Proc. Inst. Mech. Eng. O: J. Risk Reliab. 1748006X15623089 (2016). doi:
10.1177/1748006X15623089
citation_journal_title=Qual. Reliab. Eng. Int.; citation_title=Diagnosis modelling for dependability assessment of fault-tolerant systems based on stochastic activity networks; citation_author=S Maza; citation_volume=31; citation_issue=6; citation_publication_date=2015; citation_pages=963-976; citation_doi=10.1002/qre.1652; citation_id=CR20
citation_journal_title=Proc. Inst. Mech. Eng. O: J. Risk Reliab.; citation_title=Data mining-based intelligent fault diagnostics for integrated system health management to avionics; citation_author=J Xu, K Sun, L Xu; citation_volume=229; citation_issue=1; citation_publication_date=2015; citation_pages=3-15; citation_id=CR21
citation_journal_title=Comput. Ind. Eng.; citation_title=Optimizing kernel methods to reduce dimensionality in fault diagnosis of industrial systems; citation_author=JMB Lázaro, AP Moreno, OL Santiago; citation_volume=87; citation_publication_date=2015; citation_pages=140-149; citation_doi=10.1016/j.cie.2015.05.012; citation_id=CR22
citation_journal_title=Nucl. Eng. Technol.; citation_title=Semisupervised classification for fault diagnosis in nuclear power plants; citation_author=J Ma, J Jiang; citation_volume=47; citation_issue=2; citation_publication_date=2015; citation_pages=176-186; citation_doi=10.1016/j.net.2014.12.005; citation_id=CR23
citation_journal_title=Expert Syst. Appl.; citation_title=Vibrant fault diagnosis for hydroelectric generator units with a new combination of rough sets and support vector machine; citation_author=X Zhang, J Zhou, J Guo, Q Zou; citation_volume=39; citation_issue=3; citation_publication_date=2012; citation_pages=2621-2628; citation_doi=10.1016/j.eswa.2011.08.117; citation_id=CR24
citation_journal_title=Expert Syst. Appl.; citation_title=Rough set-based heuristic hybrid recognizer and its application in fault diagnosis; citation_author=Z Geng, Q Zhu; citation_volume=36; citation_issue=2; citation_publication_date=2009; citation_pages=2711-2718; citation_doi=10.1016/j.eswa.2008.01.020; citation_id=CR25
citation_journal_title=Expert Syst. Appl.; citation_title=Diagnosis of hypoglycemic episodes using a neural network based rule discovery system; citation_author=KY Chan, SH Ling, TS Dillon, HT Nguyen; citation_volume=38; citation_issue=8; citation_publication_date=2011; citation_pages=9799-9808; citation_doi=10.1016/j.eswa.2011.02.020; citation_id=CR26
citation_journal_title=Expert Syst. Appl.; citation_title=Fault diagnosis for internal combustion engines using intake manifold pressure and artificial neural network; citation_author=J-D Wu, C-K Huang, Y-W Chang, Y-J Shiao; citation_volume=37; citation_issue=2; citation_publication_date=2010; citation_pages=949-958; citation_doi=10.1016/j.eswa.2009.05.082; citation_id=CR27
citation_journal_title=Artif. Intell. Med.; citation_title=Fuzzy theory approach for temporal model-based diagnosis: an application to medical domains; citation_author=J Palma, JM Juarez, M Campos, R Marin; citation_volume=38; citation_issue=2; citation_publication_date=2006; citation_pages=197-218; citation_doi=10.1016/j.artmed.2006.03.004; citation_id=CR28
citation_journal_title=Reliab. Eng. Syst. Saf.; citation_title=A neuro-fuzzy technique for fault diagnosis and its application to rotating machinery; citation_author=E Zio, G Gola; citation_volume=94; citation_issue=1; citation_publication_date=2009; citation_pages=78-88; citation_doi=10.1016/j.ress.2007.03.040; citation_id=CR29
citation_journal_title=Simul. Model. Pract. Theory; citation_title=Fault detection and diagnosis of an industrial steam turbine using a distributed configuration of adaptive neuro-fuzzy inference systems; citation_author=K Salahshoor, MS Khoshro, M Kordestani; citation_volume=19; citation_issue=5; citation_publication_date=2011; citation_pages=1280-1293; citation_doi=10.1016/j.simpat.2011.01.005; citation_id=CR30
citation_journal_title=Expert Syst. Appl.; citation_title=Practical expert diagnosis model based on the grey relational analysis technique; citation_author=Y-H Lin, P-C Lee, T-P Chang; citation_volume=36; citation_issue=2; citation_publication_date=2009; citation_pages=1523-1528; citation_doi=10.1016/j.eswa.2007.11.046; citation_id=CR31
citation_journal_title=Expert Syst. Appl.; citation_title=Grey clustering analysis for incipient fault diagnosis in oil-immersed transformers; citation_author=C-H Lin, C-H Wu, P-Z Huang; citation_volume=36; citation_issue=2; citation_publication_date=2009; citation_pages=1371-1379; citation_doi=10.1016/j.eswa.2007.11.019; citation_id=CR32
citation_journal_title=Automatica; citation_title=Fault detection for discrete event systems using Petri nets with unobservable transitions; citation_author=MP Cabasino, A Giua, C Seatzu; citation_volume=46; citation_issue=9; citation_publication_date=2010; citation_pages=1531-1539; citation_doi=10.1016/j.automatica.2010.06.013; citation_id=CR33
citation_journal_title=Control Eng. Pract.; citation_title=Discrete event diagnosis using labeled Petri nets An application to manufacturing systems; citation_author=MP Cabasino, A Giua, M Pocci, C Seatzu; citation_volume=19; citation_issue=9; citation_publication_date=2011; citation_pages=989-1001; citation_doi=10.1016/j.conengprac.2010.12.010; citation_id=CR34
citation_journal_title=Chem. Eng. Res. Des.; citation_title=A hybrid support vector machine and fuzzy reasoning based fault diagnosis and rescue system for stable glutamate fermentation; citation_author=J Ding, Y Cao, E Mpofu, Z Shi; citation_volume=90; citation_issue=9; citation_publication_date=2012; citation_pages=1197-1207; citation_doi=10.1016/j.cherd.2012.01.004; citation_id=CR35
citation_journal_title=Neural Comput. Appl.; citation_title=Support vector machine for fault diagnosis of the broken rotor bars of squirrel-cage induction motor; citation_author=J Kurek, S Osowski; citation_volume=19; citation_issue=4; citation_publication_date=2009; citation_pages=557-564; citation_doi=10.1007/s00521-009-0316-5; citation_id=CR36
J. Pearl, Causality: Models, Reasoning and Inference, 2nd edn (Cambridge University Press, Cambridge, 2009).
http://journals.cambridge.org/action/displayFulltext?type=1&fid=153246&jid=ECT&volumeId=19&issueId=04&aid=153245
F.V. Jensen, T.D. Nielsen, Bayesian Networks and Decision Graphs, 2nd edn (Springer, Berlin, 2007).
http://books.google.com/books?hl=zh-CN&lr=&id=37CAgCykQaAC&oi=fnd&pg=PR5&dq=Bayesian+Networks+and+Decision+Graphs.&ots=fl0sioBPp_&sig=i5Kve24fzOg1bnEX0TEZ1ZQ0gjA#v=onepage&q=Bayesian%20Networks%20and%20Decision%20Graphs.&f=false
citation_journal_title=Mach. Learn.; citation_title=Factorial hidden Markov models; citation_author=Z Ghahramani, MI Jordan; citation_volume=29; citation_issue=2–3; citation_publication_date=1997; citation_pages=245-273; citation_doi=10.1023/A:1007425814087; citation_id=CR39
citation_journal_title=J. Vib. Acoust.; citation_title=HMM-based fault detection and diagnosis scheme for rolling element bearings; citation_author=H Ocak, KA Loparo; citation_volume=127; citation_issue=4; citation_publication_date=2005; citation_pages=299-306; citation_doi=10.1115/1.1924636; citation_id=CR40
citation_journal_title=Reliab. Eng. Syst. Saf.; citation_title=A fault diagnosis system for interdependent critical infrastructures based on HMMs; citation_author=S Ntalampiras, Y Soupionis, G Giannopoulos; citation_volume=138; citation_publication_date=2015; citation_pages=73-81; citation_doi=10.1016/j.ress.2015.01.024; citation_id=CR41
N.L. Zhang, Hierarchical latent class models for cluster analysis. J. Mach. Learn. Res. 5, 697–723 (2004).
http://www.jmlr.org/papers/volume5/zhang04a/zhang04a.pdf
citation_journal_title=Comput. Math Appl.; citation_title=Uncertainty reasoning based on cloud models in controllers; citation_author=D Li, D Cheung, X Shi; citation_volume=35; citation_issue=3; citation_publication_date=1998; citation_pages=99-123; citation_doi=10.1016/S0898-1221(97)00282-4; citation_id=CR43
citation_journal_title=J. Comput. Sci. Technol.; citation_title=Dynamic uncertain causality graph for knowledge representation and reasoning: discrete DAG cases; citation_author=Q Zhang; citation_volume=27; citation_issue=1; citation_publication_date=2012; citation_pages=1-23; citation_doi=10.1007/s11390-012-1202-7; citation_id=CR44
citation_journal_title=IEEE Trans. Neural Netw. Learn. Syst.; citation_title=Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: directed cyclic graph and joint probability distribution; citation_author=Q Zhang; citation_publication_date=2015; citation_id=CR45
citation_journal_title=IEEE Trans. Neural Netw. Learn. Syst.; citation_title=Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: statistics base, matrix, and application; citation_author=Q Zhang, C Dong, Y Cui; citation_volume=25; citation_issue=4; citation_publication_date=2014; citation_pages=645-663; citation_doi=10.1109/TNNLS.2013.2279320; citation_id=CR46
citation_journal_title=IEEE Trans. Syst. Man Cybern: Syst.; citation_title=Dynamic uncertain causality graph for knowledge representation and reasoning: continuous variable, uncertain evidence, and failure forecast; citation_author=Q Zhang; citation_publication_date=2015; citation_id=CR47
citation_journal_title=IEEE Trans. Reliab; citation_title=Dynamic uncertain causality graph applied to dynamic fault diagnoses of large and complex systems; citation_author=Q Zhang, S Geng; citation_publication_date=2015; citation_id=CR48
citation_journal_title=Comput. Methods Programs Biomed.; citation_title=The methodology of dynamic uncertain causality graph for intelligent diagnosis of vertigo; citation_author=C Dong, Y Wang, Q Zhang; citation_volume=113; citation_issue=1; citation_publication_date=2014; citation_pages=162-174; citation_doi=10.1016/j.cmpb.2013.10.002; citation_id=CR49
citation_journal_title=Atomic Energy Sci. Technol.; citation_title=Application of DUCG in fault diagnosis of nuclear power plant secondary loop; citation_author=Y Zhao, Q Zhang, HC Deng; citation_volume=48; citation_issue=1; citation_publication_date=2014; citation_pages=496-501; citation_id=CR50
citation_journal_title=Technol.; citation_title=Fault diagnostics using DUCG incomplex systems. J. Tsinghua Univers. (Sci; citation_author=Y Zhao, CL Dong, Q Zhang; citation_volume=56; citation_publication_date=2016; citation_pages=530-537; citation_id=CR51