Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

SEMISUPERVISED CLASSIFICATION FOR FAULT DIAGNOSIS IN NUCLEAR POWER PLANTS

  • MA, JIANPING (Department of Electrical and Computer Engineering, University of Western Ontario) ;
  • JIANG, JIN (Department of Electrical and Computer Engineering, University of Western Ontario)
  • Received : 2014.10.10
  • Accepted : 2014.12.22
  • Published : 2015.03.25
⟨ Previous Next ⟩

Abstract

Pattern classifications have become important tools for fault diagnosis in nuclear power plants (NPP). However, it is often difficult to obtain training data under fault conditions to train a supervised classification model. By contrast, normal plant operating data can be easily made available through increased deployment of supervisory, control, and data acquisition systems. Such data can also be used to train classification models to improve the performance of fault diagnosis scheme. In this paper, a fault diagnosis scheme based on semisupervised classification (SSC) scheme is developed. In this scheme, new measurements collected from the plant are integrated with data observed under fault conditions to train the SSC models. The trained models are subsequently applied to new measurements for fault diagnosis. In comparison with supervised classifiers, the proposed scheme requires significantly fewer data collected under fault conditions to train the classifier. The developed scheme has been validated using different fault scenarios on a desktop NPP simulator as well as on a physical NPP simulator using a graph-based SSC algorithm. All the considered faults have been successfully diagnosed. The results have demonstrated that SSC is a promising tool for fault diagnosis in NPPs.

Keywords

References

  1. C. Gottlieb, V. Arzhanov, W. Gudowski, N. Garis, Feasibility study on transient identification in nuclear power plants using support vector machines, Nucl. Technol. 155 (2006) 67-77. https://doi.org/10.13182/NT06-A3746
  2. E. Zio, G. Gola, Neuro-fuzzy pattern classification for fault diagnosis in nuclear components, Ann. Nucl. Energy 33 (2006) 415-426. https://doi.org/10.1016/j.anucene.2005.12.008
  3. R. Razavi-Far, H. Davilu, V. Palade, C. Lucas, Model-based fault detection and isolation of a steam generator using neuro-fuzzy networks, Neurocomputing 72 (2009) 2939-2951. https://doi.org/10.1016/j.neucom.2009.04.004
  4. J. Ma, J. Jiang, Applications of fault detection and diagnosis methods in nuclear power plants: a review, Prog. Nucl. Energy 53 (2011) 255-266. https://doi.org/10.1016/j.pnucene.2010.12.001
  5. J. Liu, R. Seraoui, V. Vitelli, E. Zio, Nuclear power plant components condition monitoring by probabilistic support vector machine, Ann. Nucl. Energy 56 (2011) 23-33.
  6. K. Moshkbar-Bakhshayesh, M.B. Ghofrani, Transient identification in nuclear power plants: a review, Prog. Nucl. Energy 67 (2013) 23-32. https://doi.org/10.1016/j.pnucene.2013.03.017
  7. L.H. Chiang, M.E. Kotanchek, A.K. Kordon, Fault diagnosis based on fisher discriminant analysis and support vector machines, Comput. Chem. Eng. 28 (2004) 1389-1401. https://doi.org/10.1016/j.compchemeng.2003.10.002
  8. A. Widodo, B.S. Yang, Support vector machine in machine condition monitoring and fault diagnosis, Mech. Syst. Signal Process. 21 (2007) 2560-2574. https://doi.org/10.1016/j.ymssp.2006.12.007
  9. S.K. Choi, J.Y. Park, I.B. Lee, Process monitoring using a gaussian mixture model via principal component analysis and discriminant analysis, Comput. Chem. Eng. (2004) 1377-1387.
  10. A. Widodo, B.S. Yang, Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors, Expert Syst. Appl. 33 (2007) 241-250. https://doi.org/10.1016/j.eswa.2006.04.020
  11. Z. Zhu, Z. Song, A novel fault diagnosis system using pattern classification on kernel fda subspace, Expert Syst. Appl. 38 (2011) 6895-6905. https://doi.org/10.1016/j.eswa.2010.12.034
  12. P. Baraldi, F. Di Maio, Unsupervised clustering for fault diagnosis in nuclear power plant components, Int. J. Comput. Intell. Syst. 6 (2013) 764-777. https://doi.org/10.1080/18756891.2013.804145
  13. J.H. Purba, A fuzzy-based reliability approach to evaluate basic events of fault tree analysis for nuclear power plant probabilistic safety assessment, Ann. Nucl. Energy 70 (2014) 21-29. https://doi.org/10.1016/j.anucene.2014.02.022
  14. O. Chapelle, B. Scholkopf, A. Zien (Eds.), Semi-supervised Learning, The MIT Press, Cambridge, MA, 2006.
  15. P. Niyogi, Manifold regularization and semi-supervised learning: some theoretical analyses, J. Mach. Learn. Res. 14 (2013) 1229-1250.
  16. R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, second ed., Wiley, 2000.
  17. E. Alpaydin, Introduction to Machine Learning, second ed., The MIT Press, Cambridge, MA, 2010.
  18. A.R. Webb, K.D. Copsey, Statistical Pattern Recognition, third ed., Wiley, 2011.
  19. X. Zhu, Semi-supervised Learning Literature Survey, Computer Sciences Technical Report 1530, University of Wisconsin, Madison, 2005.
  20. X. Zhu, A.B. Goldberg, Introduction to Semi-supervised Learning, Morgan and Claypool Publishers, San Rafael, 2009.
  21. M. Seeger, Learning with Labeled and Unlabeled Data, Technical Report No. EPFL-REPORT-161327, University of Edinburgh, Edinburgh, 2000.
  22. C.M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
  23. A. Singh, R.D. Nowak, X. Zhu, Unlabeled data: now it helps, now it doesn't, Adv. Neural Inf. Process. Syst. 21 (2008) 1513-1520.
  24. T. Lu, Fundamental Limitations of Semi-supervised Learning, Master Thesis, University of Waterloo, Ontario, 2009.
  25. D. Zhou, O. Bousquet, T.N. Lal, J. Weston, B. Scholkopf, Learning with local and global consistency, Adv. Neural Inf. Process. Syst. 16 (2003) 321-328.
  26. G. Camps-Valls, T.V. Marsheva, D. Zhou, Semi-supervised graph-based hyperspectral image classification, IEEE Trans. Geosci. Remote Sens. 45 (2007) 3044-3054. https://doi.org/10.1109/TGRS.2007.895416
  27. O. Chapelle, J. Weston, B. Scholkopf, Cluster kernels for semi-supervised learning, Adv. Neural Inf. Process. Syst. 15 (2002) 585-592.
  28. J. Shi, J. Malik, Normalized cuts and image segmentation, IEEE Trans. Pattern Anal. Mach. Intell. 22 (2002) 888-905.
  29. A.Y. Ng, M.I. Jordan, Y. Weiss, On spectral clustering: analysis and an algorithm, Adv. Neural Inf. Process. Syst. 14 (2001) 849-856.
  30. X. Zhu, Semi-supervised Learning with Graphs, Ph.D. Thesis, Carnegie Mellon University, Pittsburgh, PA, 2005.
  31. F. Li, Dynamic Modeling, Sensor Placement Design, and Fault Diagnosis of Nuclear Desalination Systems, Ph.D. Thesis, University of Tennessee, Knoxville, 2011.
  32. M. Bhushan, R. Rengaswamy, Comprehensive design of a sensor network for chemical plants based on various diagnosability and reliability criteria. 1. Framew. Ind. Eng. Chem. Res. 41 (2002) 1826-1839. https://doi.org/10.1021/ie0104363

Cited by

  1. A dynamic ordered concept lattice based algorithm for early diagnosis of NPP faults vol.92, pp.None, 2015, https://doi.org/10.1016/j.pnucene.2016.06.001
  2. Design and development of enhanced criticality alarm system for nuclear applications vol.50, pp.5, 2018, https://doi.org/10.1016/j.net.2018.01.022
  3. Unsupervised classification of NPPs transients based on online dynamic quantum clustering vol.134, pp.10, 2015, https://doi.org/10.1140/epjp/i2019-12915-4
  4. A Correlation-Based Feature Selection Algorithm for Operating Data of Nuclear Power Plants vol.2021, pp.None, 2015, https://doi.org/10.1155/2021/9994340
  5. A Framework for Monitoring and Fault Diagnosis in Nuclear Power Plants Based on Signed Directed Graph Methods vol.9, pp.None, 2015, https://doi.org/10.3389/fenrg.2021.641545
  6. Unsupervised machine learning techniques for fault detection and diagnosis in nuclear power plants vol.142, pp.None, 2015, https://doi.org/10.1016/j.pnucene.2021.103990