Machine-Learning Methods in Prognosis of Ageing Phenomena in Nuclear Power Plant Components


  • Miki Sirola
  • John Einar Hulsund



data analysis, machine learning, nuclear power plant, component ageing, prognosis


In the Long-Term Degradation Management (LTDM) project we approach component ageing problems with data-analysis methods. It includes literature review about related work. We have used several data sources: water chemistry data from the Halden reactor, simulator data from the HAMBO simulator, and data from a local coffee machine instrumented with sensors. K-means clustering is used in cluster analysis of nuclear power plant data. A method for detecting trends in selected clusters is developed. Prognosis models are developed and tested. In our analysis ARIMA models and gamma processes are used. Such tasks as classification and time-series prediction are focused on. Methodologies are tested in experiments. The realization of practical applications is made with the Jupyter Notebook programming tool and Python 3 programming language. Failure rates and drifts from normal operating states can be the first symptoms of an approaching fault. The problem is to find data sources with enough transients and events to create prognostic models. Prognosis models for predicting possible developing ageing features in nuclear power plant data utilizing machine learning methods or closely related methods are demonstrated.


J. Lienig, H. Bruemmer, Fundamentals of Electronic Systems Design, Springer International Publishing, p. 54, 2017. ISBN 978-3-319-55839-4.

P. Athanasios, S. Pillai, Probability, Random Variables, and Stochastic Processes (4th ed.). Boston: McGraw-Hill, 2002. ISBN 0-07-366011-6.

R. Jiang, D.N.P. Murthy, “A study of Weibull shape parameter: Properties and significance,” Reliability Engineering & System Safety, vol. 96, issue 12, pp. 1619–26, 2011.

T. Allenius, Ageing Classification for Electrical Components, University of Applied Sciences (Vaasa). Bachelor’s thesis, 2013, 58 p. (In Finnish).

M. Sirola, J.E. Hulsund, “Data-analysis methods in detecting, visualizing and predicting nuclear power plant component ageing phenomena,” Proceedings of the IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS’2019), Metz, France, 18-21 September; 2019, pp. 624-627.

Z. Welz, J. Coble, B. Upadhyaya and W. Hines, “Maintenance-based prognostics of nuclear power plant equipment for long-term operation,” Nuclear Engineering and Technology, vol. 49, issue 5, pp. 914-919, 2017.

H. Abe and T. Inagaki, “New maintenance strategy and effective ageing management in TEPCO,” E-Journal of Advanced Maintenance (EJAM), vol. 1, no. 2, pp. 1-17, 2014.

M. Boo, J. Lee and J. Park, “Long term asset management strategy for refurbishment and replacement of nuclear power plants in Korea,” Proceedings of the 3th International Conference on Nuclear Plant Life Management (PLIM) for Long Term Operation (LTO), pp. 1-8, 2012.

L. Ulanova et al., “Efficient long-term degradation profiling in time series for complex physical systems,” Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD2015), Sydney, Australia, 2015, pp. 1-10.

J.E. Hulsund, O. Saarela, Lifetime estimation models of air filters for nuclear power plants. HWR-1116, OECD Halden Reactor Project, 2014.

J.E. Hulsund et al., Predictive analysis and visualization of condenser fouling using big data and machine learning. HWR-1221, OECD Halden Reactor Project, 2015.

B.H. Nystad et al., “Technical condition assessment and remaining useful life estimation of choke valves subject to erosion,” Proceedings of the Annual Conference of the Prognostics and Management Society, 2010, pp. 1-9.

A. Jardine, D. Lin, D. Banjevic, “A review on machine diagnostics and prognostics implementing condition-based maintenance,” Mechanical Systems and Signal Processing, vol. 20, issue 7, pp. 1483-1510, 2006.

J. Lee, “Machine performance monitoring and proactive maintenance in computer-integrated manufacturing: review and perspective,” International Journal of Computer Integrated manufacturing, vol. 8, issue 5, pp. 370-380, 1995.

Y. Peng, M. Dong, M. Zuo, “Current status of machine prognostics in condition-based maintenance: a review,” The International Journal of Advanced Manufacturing Technology, vol. 50, issue 1-4, pp. 297-313, 2010.

G. Park, C. Lee, J. Kim, J. Ryu, H. Jung, Identification of nuclear components degradation by time-frequency ridge pattern, United States: N. p., Web, 2006.

M. Na et al., Prediction of major transient scenarios for severe accidents in nuclear power plants, IEEE Transactions on Nuclear Science, vol. 51, no. 2, pp. 313-321, 2004.

C. Rocco, E. Zio, “A support vector machine integrated system for the classification of operation anomalies in nuclear components and systems,” Reliability Engineering & System Safety, vol. 92, issue 5, pp. 593-600, 2007.

D. Roverso, “Multivariate temporal classification by windowed wavelet decomposition and recurrent neural networks,” International Topical Meeting on Nuclear Plant Instrumentation, Controls, and Human-Machine Interface Technologies (NPIC&HMIT 2000), pp. 1-8, Washinton, USA, 2000.

D. Gibbons, G. Wukelic, J. Leighton, M. Doyle, Application of Landsat thematic mapper data for coastal thermal plume analysis at Diablo Canyon, United States: N. p., Web, 1989.

K-Y. Chen, L-S. Chen, M-C. Chen, C-L. Lee, “Using SVM method for equipment fault detection in a thermal power plant,” Computers and Industry, vol. 62, issue 1, pp. 42-50, 2011.

P. Ramuhalli, Nondestructive examination (NDE) detection and characterization of degradation precursors, Technical progress report for FY 2012. Pacific Northwest national laboratory, 2012.

J.Z. Sikorska, M. Hodkiewicz, L. Ma, “Prognostic modelling options for remaining useful life estimation by industry,” Mechanical Systems and Signal Processing, vol. 25, issue 5, pp. 1803-1836, 2011.

J.M. van Noortwijk, “A survey of the application of gamma process in maintenance,” Reliability Engineering and System Safety, vol. 94, issue 1, pp. 2-21, 2009.

W. Wu, J. Hu, J, Zhang, “Prognostics of machine health condition using an improved ARIMA-based prediction method,” Proceedings of the IEEE Conference on Industrial Electronics and Applications, Harbin, China, 2007, pp. 1062-1067.

N. Gebraeel, M. Lawley, R. Liu, V. Parmeshwaran, “Residual life predictions from vibration-based degradation signals: a neural network approach,” IEEE Transactions on Industrial Electronics, vol. 51, no. 3, pp. 694–700, 2004.

R. Huang et al., “Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods,” Mechanical Systems and Signal Processing, vol. 21, issue 1, pp. 193-207, 2007.

E.D. Eason, R. Pathania, “Disposition curves for irradiation-assisted stress corrosion cracking of authentic stainless steel in light water reactor environments,” ASME 2015 Pressure Vessel & Piping Conference (PVP2015), 2015, Paper No: PVP2015-45323, V06AT06A075, pp. 1-10.

R. Havel, Safe Long-term Operation of Nuclear Power Plants, IAEA Safety Report Series, no. 57, 2008.

T. Hastie, R. Tibshirani, J, Friedman, The Elements of Statistical Learning – Data Mining, Inference and Prediction, Springer, 2008.

K. Sultan, H. Ali, Z. Zhang, “Big data perspective and challenges in next generation networks,” Future Internet (MDPI), pp. 1-20, 2018.

J.A. Hartigan, M.A. Wong, “Algorithm AS 136: A K-Means Clustering Algorithm,” Journal of the Royal Statistical Society, Series C (Applied Statistics), vol. 28, issue 1, pp. 100–108, 1979.

ARIMA Model – Complete Guide to Time Series Forecasting in Python, Machine Learning Plus. [Online]. Available at:

J. Brownlee, “How to create an ARIMA model for time series forecasting in Python,” Machine Learning Mastery, Web publication, 2017.

J. van Noortwijk, M. Pandey, “A stochastic deterioration process for time-dependent reliability analysis,” Proceeding of IFIP WG 7.5 Working Conference on Reliability and Optimization of Structural Systems, Banff, Canada, 2003, pp. 259-265.

D. Asteriou, S.G. Hall, “ARIMA models and the Box–Jenkins methodology,” Applied Econometrics (Second ed.), Palgrave MacMillan, 2011, pp. 265–286. ISBN 978-0-230-27182-1.

D. Applebaum, Lévy Processes and Stochastic Calculus, CUP, 2004. ISBN 0-521-83263-2. [Online]. Available at:

R.M. Dudley, Real Analysis and Probability, Wadsworth and Brooks/Cole, 1989.

L. Breiman, “Random Forests,” Machine Learning, vol. 45, issue 1, pp. 5–32, 2001.

T. Kohonen, Self-Organization and Associative Memory, Springer, Berlin, 1984.

F.M. Awan, Y. Saleem, R. Minerva, N. Crespi, “A comparative analysis of machine/deep learning models for parking space availability prediction,” Sensors, vol. 10, issue 1, 322, 2020.

K. Wojcik, M. Piekarczyk, “Machine learning methodology in a system applying the adaptive strategy for teaching human motions,” Sensors, vol. 20, issue 1, 314, 2020.




How to Cite

Sirola, M., & Hulsund, J. E. (2021). Machine-Learning Methods in Prognosis of Ageing Phenomena in Nuclear Power Plant Components. International Journal of Computing, 20(1), 11-21.