Dynamic weighting ensembles for incremental learning and diagnosing new concept class faults in nuclear power systems

IEEE Transactions on Nuclear Science

Volumn 59, Issue 5 PART 3, 2012, Pages 2520-2530

  Razavi Far, Roozbeh ^a,b   Baraldi, Piero ^a   Zio, Enrico ^a,c  

^a POLITECNICO DI MILANO   (Italy)

^b UNIVERSITÉ LIBRE DE BRUXELLES   (Belgium)

^c EDF R AND D   (France)

Author keywords

Dynamic weighting ensembles; fault detection and classification; incremental learning; nuclear power systems

Indexed keywords

BASE CLASSIFIERS; CONCEPT CLASS; DIAGNOSTIC SYSTEMS; DYNAMIC APPLICATIONS; FAULT DETECTION AND CLASSIFICATION; FEEDWATER SYSTEMS; INCREMENTAL LEARNING; LEARN+; NOVEL CONCEPT; PRACTICAL IMPLEMENTATION; THRESHOLDING; UNKNOWN CLASS; WEIGHTED AVERAGES;

BOILING WATER REACTORS; FAULT DETECTION; NUCLEAR ENERGY;

ALGORITHMS;

EID: 84867668366     PISSN: 00189499     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNS.2012.2209125     Document Type: Article

References (48)

1. J. Reifman, "Survey of artificial intelligence methods for detection and identification of component faults in nuclear power plants," Nucl. Technol., vol. 119, pp. 76-97, 1997. (Pubitemid 127601958)
2. K. Kim and E. Bartlett, "Nuclear power plant fault diagnosis using neural networks with error estimation," IEEE Trans. Nucl. Sci., vol. 43, no. 4, pp. 2373-2388, Aug. 1996. (Pubitemid 126771619)
3. M. Embrechts and S. Benedek, "Hybrid identification of nuclear power plant transients with artificial neural networks," IEEE Trans. Ind. Electron., vol. 51, pp. 686-693, 2004.
4. E. Zio, "A study of the bootstrap method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes," IEEE Trans. Nucl. Sci., vol. 53, no. 3, pp. 1460-1478, Jun. 2006. (Pubitemid 44109454)
5. M. Marseguerra, E. Zio, and P. Baraldi, "A fuzzy modeling approach to the identification of transients in nuclear component," Ann. Nucl. Energy, vol. 31, no. 18, pp. 2093-2112, 2004.
6. E. Zio andP. Baraldi, "Identification of nuclear transients via optimized fuzzy clustering," Ann. Nucl. Energy, vol. 32, pp. 1068-1080, 2005. (Pubitemid 40574592)
7. M. Marseguerra, E. Zio, P. Baraldi, I. Popescu, and P. Ulmeanu, "A fuzzy logic-based model for the classification of faults in the pump seals of the primary heat transport system of a candu 6 reactor," Nucl. Sci. Eng., vol. 153, no. 2, pp. 157-171, 2006. (Pubitemid 43979452)
8. K. Zhao and B. Upadhyaya, "Adaptive fuzzy inference causal graph approach to fault detection and isolation of field devices in nuclear power plants," Progress Nucl. Energy, vol. 46, no. 3-4, pp. 226-240, 2005. (Pubitemid 41101266)
9. E. Zio, P. Baraldi, and I. Popescu, "A fuzzy decision tree for fault classification," Risk Anal., vol. 28, no. 1, pp. 49-67, 2008. (Pubitemid 351315502)
10. E. Zio, P. Baraldi, and I. Popescu, "From fuzzy clustering to a rulebased model for fault classification," Int. J. Comput. Intell. Syst., vol. 1, no. 1, pp. 60-76, 2008.
11. E. Zio, P. Baraldi, and I. Popescu, "A fuzzy decision tree method for fault classification in the steam generator of a pressurized water reactor," Ann. Nucl. Energy, vol. 36, no. 8, pp. 1159-1169, 2009.
12. C. D. Bocaniala and J. Sa da Costa, "Application of a novel fuzzy classifier to fault detection and isolation of the DAMADICS benchmark problem," Control Eng. Practice, vol. 14, no. 6, pp. 653-669, 2006.
13. A. Evsukoff and S. Gentil, "Recurrent neuro-fuzzy system for fault detection and isolation in nuclear reactors," Adv. Eng. Inform., vol. 19, no. 1, pp. 55-66, 2005. (Pubitemid 41000266)
14. E. Zio and G. Gola, "Neuro-fuzzy pattern classification for fault diagnosis," Ann. Nucl. Energy, vol. 33, pp. 415-426, 2006.
15. R. Razavi-Far, H. Davilu, V. Palade, and C. Lucas, "Model based fault detection and isolation of a steam generator using neuro-fuzzy networks," Neurocomput. J., vol. 72, pp. 2939-2951, 2009.
16. P. Baraldi, R. Razavi-Far, and E. Zio, "Bagged ensemble of FCMclassifier for nuclear transient identification," Ann. Nucl. Energy, vol. 38, no. 5, pp. 1161-1171, 2011.
17. F. Hamker, "Life-long learning cell structures-continuously learning without catastrophic interference," Neural Netw., vol. 14, no. 4-5, pp. 551-573, 2001. (Pubitemid 32475862)
18. E. M. Gold, "Language identification in the limit," Inf. Control, vol. 10, no. 5, pp. 447-474, 1967.
19. P. Baraldi, R. Razavi-Far, and E. Zio, "Classifier-ensemble incremental-learning procedure for nuclear transient identification at different operational conditions," Reliab. Eng. Syst. Safety, vol. 96, no. 4, pp. 480-488, 2010.
20. M. Muhlbaier, A. Topalis, and R. Polikar, "Learn NC: Combining ensemble of classifiers with dynamically weighted consult-and-vote for efficient incremental learning of new classes," IEEE Trans. Neural Netw., vol. 20, no. 1, pp. 152-168, Jan. 2009.
21. E. Puska and S. Norrman, "3-d core studies for hambo simulator," in Proc. Enlarged Halden Group Meeting, Storefjell, Norway, HPR-358, CD-ROM., Sep. 2002, vol. 2, pp. 8-13.
22. E. Zio, P. Baraldi, G. Gola, D. Roverso, and M. Hoffmann, "Diagnosing faults in nuclear components by an ensemble of feature-diverse fuzzy classifiers," Int. J. Nucl. Knowl. Manage., vol. 2, no. 3, pp. 224-238, 2007.
23. Y. Freund and R. Schapire, "A decision theoretic generalization of on-line learning and an application to boosting," Comput. Sys. Sci., vol. 57, no. 1, pp. 119-139, 1997. (Pubitemid 127433398)
24. L. Kuncheva, Combining Pattern Classifiers, Methods and Algorithms. Hoboken, NJ: Wiley, 2004.
25. L. Kuncheva, "A theoretical study on six classifier fusion strategies," IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 2, pp. 281-286, Feb. 2002. (Pubitemid 34198215)
26. M. Lewitt and R. Polikar, "An ensemble approach for data fusion with ," in Proc. 4th Int.WorkshopMultiple Classifier Syst. LNCS, Berlin, Germany, 2003, vol. 2709, pp. 176-186.
27. D. Parikh and R. Polikar, "An ensemble-based incremental learning approach to data fusion," IEEE Trans. Syst., Man, Cybern.-Part B: Cybern., vol. 37, no. 2, pp. 437-450, Apr. 2007. (Pubitemid 46523231)
28. R. Polikar, "Ensemble based systems in decision making," IEEE Circuits Syst. Mag., vol. 6, no. 3, pp. 21-45, Third Quarter, 2006.
29. R. Duin and D. Tax, "Classifier conditional posterior probabilities," in Lecture Notes in Computer Science, LNCS. Berlin, Germany: Springer, 1998, vol. 1451, pp. 611-619. (Pubitemid 128117163)
30. D. Wilson and T. Martinez, "Combining cross-validation and confidence to measure fitness," in IEEE Joint Conf. Neural Netw., 1999, vol. 2, pp. 1409-1414. (Pubitemid 30592992)
31. J. Byorick and R. Polikar, "Confidence estimation using the incremental learning algorithm, ," Springer-Verlag, LNCS, vol. 2714, pp. 181-188, 2003.
32. M. Muhlbaier, A. Topalis, and R. Polikar, Ensemble Confidence Estimates Posterior Probability, n.c. Berlin, Germany: Springer-Verlag , MCS, LNCS, 2005, vol. 3541, pp. 326-335.
33. P. Baraldi, R. Razavi-Far, and E. Zio, "A method for estimating the confidence in the identification of nuclear transients by a bagged ensemble of fcm classifiers," in Proc. NPIC&HMIT, Las Vegas, NV, Nov. 7-11, 2010, pp. 283-293.
34. R. Polikar, L. Udpa, S. Udpa, and V. Honavar, " : An incremental learning algorithm for supervised neural networks," IEEE Trans. Syst., Man, Cybern.-C: Applicat. Rev., vol. 31, no. 4, pp. 497-508, 2001. (Pubitemid 34191829)
35. M. Muhlbaier and R. Polikar, An Ensemble Approach for Incremental Learning in Nonstationary Environments. Berlin/Heidelberg, Germany: Springer-Verlag , MCS, LNCS, 2007, vol. 4472, pp. 490-500.
36. H. Drucker, C. Cortes, L. Jackel, Y. LeCun, and V. Vapnik, "Boosting and other ensemble methods," Neural Comput., vol. 6, no. 6, pp. 1289-1301, 1994.
37. L. Breiman, "Bagging predictors," Mach. Learn., vol. 24, no. 2, pp. 123-140, 1996. (Pubitemid 126724382)
38. E. Bauer and R. Kohavi, "An empirical comparison of voting classification algorithms: Bagging, boosting and variants," Mach. Learn., vol. 36, pp. 105-139, 1999.
39. L. I. Kuncheva, Classifier ensembles for changing environments. Book Series Lecture Notes in Computer Science. Berlin/Heidelberg, Germany: Springer, 2004, vol. 3077, pp. 1-15.
40. Y. Freund and R. Schapire, "Experiments with a new boosting algorithm," in Proc. Int. Conf. Mach. Learn., 1996.
41. R. Schapire, "The boosting approach to machine learning: An overview," Lecture Notes in Statistics, pp. 149-172, 2003.
42. C. Bishop, Neural Networks for Pattern Recognition. Oxford. Oxford, U.K.: Oxford Univ., 1995.
43. M. Markou and S. Singh, "Novelty detection: A review-part 1: Statistical approaches," Signal Process., vol. 83, no. 12, pp. 2481-2497, 2003.
44. M. Markou and S. Singh, "Novelty detection: A review-part 2: Neural network based approaches," Signal Process., vol. 83, no. 12, pp. 2499-2521, 2003.
45. B. Preshagen, Light Water Reactor Safety. Oxford, U.K.: Pergamon, 1989.
46. E. Zio, P. Baraldi, and N. Pedroni, "Selecting features for nuclear transients classification by means of genetic algorithms," IEEE Trans. Nucl. Sci., vol. 53, no. 3, pp. 1479-1493, Jun. 2006. (Pubitemid 44109455)
47. R. French, "Catastrophic forgetting in connectionist networks: causes, consequences and solutions," Trends in Cognitive Sci., vol. 3, no. 4, pp. 128-135, 1999. (Pubitemid 29155462)
48. M. Muhlbaier, A. Topalis, and R. Polikar, Learn++.MT: A New Approach to Incremental Learning. Berlin/Heidelberg, Germany: Springer-Verlag, MCS, LNCS 2004, vol. 3077, pp. 52-61.