Data Driven Monitoring of Energy Systems: Gaussian Process Kernel Machine for Fault Identification with Application to Boiling Water Reactors

  • Miltiadis AlamaniotisEmail author
  • Stylianos Chatzidakis
  • Lefteri H. Tsoukalas
Part of the Studies in Computational Intelligence book series (SCI, volume 627)


Energy production units are large complex installations comprised of several smaller units, subsystems, and mechanical components, whose monitoring and control to secure safe operation are high demanding tasks. In particular, human operators are required to monitor a high volume of incoming data and must make critical decisions in very short time. Although they are explicitly trained in such situations, there are cases that may not be able to identify a gradually developing crucial faulty state. To that end, automated systems can be used for monitoring operational quantities and detecting potential faults in time. The field of machine learning offers a variety of tools that may be used as the ground for developing automated monitoring and control systems for energy systems. In the current chapter, we present an approach that adopts a single Gaussian process learning machine in monitoring high complex energy systems. The Gaussian process is a data-driven model assigned to monitor a set of operational parameters. The values of the operational parameters at a specific instance comprise the system’s operational vector at that time instance. The operational vector consists the input to the individual Gaussian process machine whose task is to classify the operation of the system either as normal (or steady state) or match it to a faulty state. The presented approach is benchmarked on a set of experimentally data taken from the Fix-II test facility that is a representation of a Boiling Water Reactor. Obtained results exhibit the potential of Gaussian processes in monitoring highly complex systems such as nuclear reactors, by identifying with high accuracy the faults in system operation.


Gaussian processes Kernel learning machines Data-driven monitoring BWR 


  1. Agarwal, V., Lybeck, N.J., Pham, B.T., Rusaw, R., Bickford, R.: Online monitoring of plant assets in the nuclear industry. In: Annual Conference of the PHM Society, New Orleans, pp. 1–7, Oct 2013Google Scholar
  2. Alamaniotis, M., Agarwal, V.: Fuzzy integration of support vector regressor models for anticipatory control of complex energy systems. Int. J. Monit. Surveill. Technol. Res. 2(2), 26–40 (2014)CrossRefGoogle Scholar
  3. Alamaniotis, M., Ikonomopoulos, A., Tsoukalas, L.H.: Gaussian processes for failure prediction of slow degradation components in nuclear power plants. In: Proceedings of the European Safety and Reliability Conference 2010 (ESREL 2010), Rhodes, Greece, pp. 2096–2102, Sept 2010Google Scholar
  4. Alamaniotis, M., Ikonomopoulos, A., Tsoukalas, L.H.: Optimal Assembly of support vector regressors with application to system monitoring. Int. J. Artif. Intell. Tools 27(6), 1250034 (2012a)Google Scholar
  5. Alamaniotis, M., Ikonomopoulos, A., Tsoukalas, L.H.: Probabilistic kernel approach to online monitoring of nuclear power plants. Nucl. Technol. 177(1), 132–144 (2012)Google Scholar
  6. Alamaniotis, M., Agarwal, V., Jevremovic, T.: Anticipatory monitoring and control of complex energy systems using a fuzzy based fusion of support vector regressors. In: Proceedings of the 5th International Conference on Information, Intelligence, Systems and Applications, Chania, Greece, pp.1–5, July 2014Google Scholar
  7. Alamaniotis, M., Grelle, A., Tsoukalas, L.H.: Regression to fuzziness method for estimation of remaining useful life in power plant components. Mech. Syst. Signal Process. 48(1), 188–198 (2014)CrossRefGoogle Scholar
  8. Alamaniotis, M., Jin. X., Ray, A.: On-line condition monitoring of boiling water reactors using symbolic dynamic analysis. In: 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human Machine Interface Technologies (NPIC&HMIT 2015). American Nuclear Society, Charlotte, NC, USA (2015)Google Scholar
  9. Bishop, C.: Pattern Recognition and Machine Learning. Springer, New York (2006)zbMATHGoogle Scholar
  10. Chinnam, R.B., Baruah, P.: A neuro-fuzzy approach for estimating mean residual life in condition-based maintenance systems. Int. J. Mater. Prod. Technol. 20(1–3), 166–179 (2003)Google Scholar
  11. Choi, S.W., Lee, C., Lee, J.M., Park, J.H., Lee, I.B.: Fault detection and identification of nonlinear processes based on kernel PCA. Chemometr. Intell. Lab. Syst. 75(1), 55–67 (2005)CrossRefGoogle Scholar
  12. Gibbs, M.N.: Bayesian Gaussian processes for regression and classification. Ph.D. thesis, Department of Physics, University of Cambridge (1997)Google Scholar
  13. Gupta, S., Singh, D.S., Ray, A.: Statistical pattern analysis of ultrasonic signals for fatigue damage detection in mechanical structures. NDT and E Int. 41(7), 491–500 (2008)CrossRefGoogle Scholar
  14. Hines, J.W., Usinyn, A.: Current computational trends in equipment prognostics. Int. J. Comput. Intell. Syst. 1(1), 94–102 (2008)CrossRefGoogle Scholar
  15. Huang, R., Xi, L., Li, X., Liu, R., Qiu, H., Lee, J.: Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech. Syst. Signal Process. 21, 193–207 (2007)CrossRefGoogle Scholar
  16. Ikonomopoulos, A., Tsoukalas, L.H., Uhrig, R.E.: Integration of neural networks with fuzzy reasoning for measuring operational parameters in a nuclear reactor. Nucl. Technol. 104, 1–12 (1993)Google Scholar
  17. Ikonomopoulos, A., Alamaniotis, M., Chatzidakis, S., Tsoukalas, L.H.: Gaussian processes for state identification in pressurized water reactors. Nucl. Technol. 182(1), 1–12 (2013)Google Scholar
  18. Isermann, R.: Fault-diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance. Springer Science & Business Media, Berlin (2006)Google Scholar
  19. Jardine, A.K., Lin, D., Banjevic, D.: A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Signal process. 20(7), 1483–1510 (2006)Google Scholar
  20. Jarrell, D.B., Sisk, D.R., Bond, L.J.: Prognostics and condition-based maintenance: a new approach to precursive metrics. Nucl. Technol. 145, 275–286 (2004)Google Scholar
  21. Jin, X., Guo, Y., Sarkar, S., Ray, A., Edwards, R.M.: Anomaly detection in nuclear power plants via symbolic dynamic filtering. IEEE Trans. Nucl. Sci. 58(1), 277–288 (2011)CrossRefGoogle Scholar
  22. Nilsson, L.: FIX-II LOCA Blowdown and Pump Trip Heat Transfer Experiments, Experimental Results from Pump Trip Experiments of Test Groups Nos. 1, 2, 8 (STUDSVIK/NR-83/324) (1982)Google Scholar
  23. Orchard, M.E., Vachtsevanos, G.J.: A particle-filtering approach for on-line fault diagnosis and failure prognosis. Trans. Inst. Measur. Control 31(4), 221–246 (2009)CrossRefGoogle Scholar
  24. Papoulis, A., Pillai, S.U.: Probability, Random Variables, and Stochastic Processes. Mc-Graw Hill, New York (2002)Google Scholar
  25. Rajagopalan, V., Ray, A.: Symbolic time series analysis via wavelet-based partitioning. Sig. Process. 86(11), 3309–3320 (2006)CrossRefzbMATHGoogle Scholar
  26. Rasmussen, C.E., Williams, C.K.I.: Gaussian processes for machine learning. MIT Press, Boston (2006)Google Scholar
  27. Ray, A.: Symbolic dynamic analysis of complex systems for anomaly detection. Sig. Process. 84(7), 1115–1130 (2004)CrossRefzbMATHGoogle Scholar
  28. Tsoulfanidis, N.: The Nuclear Fuel Cycle. American Nuclear Sosiety, New York (2013)Google Scholar
  29. Uhrig, R.E., Tsoukalas, L.H.: Soft computing technologies in nuclear engineering applications. Prog. Nucl. Energy 34(1), 13–75 (1999)CrossRefGoogle Scholar
  30. Wang, P., Vachtsevanos, G.: Fault prognostics using dynamic wavelet neural networks. Artif. Intell. Eng. Des. Manuf. 15, 349–365 (2001)CrossRefzbMATHGoogle Scholar
  31. Wu, Z., Huang, N.E.: Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv. Adapt. Data Anal. 1(01), 1–41 (2009)CrossRefGoogle Scholar
  32. Xu, L., Chow, M.Y., Taylor, L.S.: Power distribution fault cause identification with imbalanced data using the data mining-based fuzzy classification e-algorithm. IEEE Trans. Power Syst. 22(1), 164–171 (2007)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • Miltiadis Alamaniotis
    • 1
    Email author
  • Stylianos Chatzidakis
    • 1
  • Lefteri H. Tsoukalas
    • 1
  1. 1.School of Nuclear EngineeringPurdue UniversityWest LafayetteUSA

Personalised recommendations