Preliminary study on fault detection using artificial neural network for water-cooled reactors

J. A. Karim; T. Lanyau; M. Maskin; M. A. S. Anuar; A. Che Soh; R. Z. A. Rahman

doi:10.15282/jmes.14.4.2020.14.0588

Authors

J. A. Karim Reactor Technology Centre, Technical Support Division, Malaysian Nuclear Agency, 43000 Kajang, Selangor. Phone: +60389112000; Fax: +60389250755
T. Lanyau Reactor Technology Centre, Technical Support Division, Malaysian Nuclear Agency, 43000 Kajang, Selangor. Phone: +60389112000; Fax: +60389250755
M. Maskin Reactor Technology Centre, Technical Support Division, Malaysian Nuclear Agency, 43000 Kajang, Selangor. Phone: +60389112000; Fax: +60389250755
M. A. S. Anuar Control System and Signal Processing (CSSP) Research Centre, Department of Electrical and Electronic Engineering, Universiti Putra Malaysia, 43400 UPM, Serdang, Selangor
A. Che Soh Control System and Signal Processing (CSSP) Research Centre, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor
R. Z. A. Rahman Control System and Signal Processing (CSSP) Research Centre, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor

DOI:

https://doi.org/10.15282/jmes.14.4.2020.14.0588

Keywords:

Artificial neural network, cooling system, structures, systems and components, fault detection, residual

Abstract

In the PUSPATI TRIGA reactor (RTP), many variables and instruments need to be monitored to make sure it is functioning and running accordingly. The late detection of faults may result in accidents and affect workers’ safety and health. Therefore, an intelligent fault detection system is needed to detect faults in the process plant and alert for any safe point breach. This work was carried out to discover the use of an artificial neural network (ANN) to model and develop a fault detection programme in the RTP cooling system. Using actual data from the reactor to train the multilayer network model with backpropagation algorithm. Referring to the real data from the reactor, the simulation results demonstrate a good correlation between the proposed model using ANN and the real plants with a residual mean of below 1%. The preliminary results for fault detection show that ANN was able to predict the value of failure in residual factor by comparing the normal state and fault state of the plant. The proposed model using ANN method proofed that it could quickly diagnose the single fault and perform for any given failure. The research outcome could contribute to the improvement in frontier technologies and advanced manufacturing in Malaysia.

References

E. H. Riyadi, “A review for identification of initiating events in event tree development process on nuclear power plants,” AIP Conference Proceedings, vol. 1615, no. 1, pp. 152–155, 2014.

A. N. Allalou, M. Tadjine, and M. S. Boucherit, “Online monitoring and accident diagnosis aid system for the Nur nuclear research reactor,” Turkish Journal of Electrical Engineering & Computer Sciences, vol. 24, no. 3, pp. 1604–1614, 2016.

Tom, P.P, M. Maskin, A. H. S. Mohd Sarif, F. Mohamed, M. F. Zakaria, S. Ramli, M. P. Abu, “Development of System Model for Level 1 Probabilistic Safety Assessment of TRIGA PUSPATI Reactor”, R&D Seminar 2014: Research and Development Seminar 2014; Bangi (Malaysia); 14-16 Oct 2014

N. Ramli, M. Maskin, P. P. Tom, N. Husain, M. F. A. Farid, S. Ramli, A. S. Adnan, N. H. Z. Abidin, “Development of the ageing management database of PUSPATI TRIGA reactor”, Advancing Nuclear Science and Engineering for Sustainable Nuclear Energy Infrastructure, AIP Conference Proceedings 1704, pp. 020003-1–020003-6; 2016.

S. Heo and J. H. Lee, “Fault detection and classification using artificial neural network” IFAC, Elsevier, pp. 470–475, 2018.

S. Mandal, N. Sairam, S. Sridhar, P. Swaminathan,” Nuclear power plant sensor fault detection using singular value decomposition-based method”, Sadhana, Vol. 42, No. 9, , pp. 1473–1480,2017.

Liu Yong-kuo, Peng Min-jun, Xie Chun-li, Dong Ya-xin, “Research and design of distributed fault diagnosis system in nuclear power plant”, Progress in Nuclear Energy 68, pp. 97-110, 2013.

K. Hadad, M. Pourahmadi, H. Majidi-Maraghi, “ Fault diagnosis and classification based on wavelet transform and neural network”, Progress in Nuclear Energy 53, pp. 41-47, 2011.

T.V. Santhosh, M. Kumar, I. Thangamani, A. Srivastava, A. Dutta, V. Verma, D. Mukhopadhyay, S. Ganju, B. Chatterjee, V.V.S.S. Rao, H.G. Lele, A.K. Ghosh, “ A diagnostic system for identifying accident conditions in a nuclear reactor”, Nuclear Engineering and Design 241, pp. 177-184, 2011.

History, Development and Future of TRIGA Research Reactors, Technical Reports Series No. 482. International Atomic Energy Agency (IAEA), 2016.

Abu Bakar Ghazali, and Maslina Mohd Ibrahim, “Fault detection and analysis in Nuclear Research Facility using Artificial Intelligence Methods”, AIP Conference Proceedings 1704, 2016.

R. Tregoning, L. Abramason, and P. Scott, “Estimating Loss-of-Coolant Accident (LOCA) Frequencies Through the Elicitation Process,” 2008.

J. H. Park, Y. S. Cho, and J. H. Lee, “Effects of leak rate on LOCA probability of pipes in nuclear power plants,” in Proceedings of the International Congress (APCF/SIF-2014), 2014, pp. 203–207.

P. M. Frank, “Analytical and Qualitative Model-based Fault Diagnosis – A Survey and Some New Results,” European Journal of Control, vol. 2, no. 1, pp. 6–28, Jan. 1996.

M. jun Peng et al., “An intelligent hybrid methodology of on-line system-level fault diagnosis for nuclear power plant,” Nuclear Engineering and Technology, vol. 50, no. 3, pp. 396–410, 2018.

N. Khentout, H. Salhi, Giovanni Magrotti, and D. Merrouche, “Fault monitoring and accommodation of the heat exchanger parameters of Triga-Mark II nuclear research reactor using model-based analytical redundancy,” Progress in Nuclear Energy, vol. 109, no. November 2016, pp. 97–112, 2018.

O. Elnokity, I. I. Mahmoud, M. K. Refai, and H. M. Farahat, “ANN based sensor faults detection, isolation, and reading estimates - SFDIRE: Applied in a nuclear process,” Annals of Nuclear Energy, vol. 49, pp. 131–142, 2012.

Malaysian Nuclear Agency, “Safety Analysis Report for PUSPATI TRIGA Reactor 2017,” 2017.

T.Lanyau, N.S.Hamzah, A.M.Jalal Bayar, J.Abdul Karim, P.K.Phongsakorn, K.Mohammad Suhaimi, Z.Hashim, H.Md Razi, Z.M. Fazli, A.S.Ligam, M.K.A.Mustafa, M.Maskin, “Analysis of water volume changes and temperature measurement location effect to the accuracy of RTP power calibration”, IOP Conference Series: Materials Science and Engineering 298, pp 1-9,2018.

T. Lanyau, N. Hamzah and J. Abdul Karim, “Analysis of water volume changes and temperature measurement location effect to the accuracy of RTP power calibration,” IOP Conference Series: Materials Science and Engineering, vol. 298, no. 1, 2018.

D. Datta and C. Jang, “Failure probability assessment of a PWR primary system piping subcomponents under different loading conditions,” IAEA International Symposium on Nuclear Power Plant Life Management, Shanghai, China, pp. 1–14, 2007.

J. Gertler: Residual generation in model based fault diagnosis, Control-Theory and Advanced Technology, Vol. 9, pp. 259-285, March 1993.

A. D. Atkinson, R. R. Hill, J. J. Pignatiello, G. G. Vining, E. D. White, and E. Chicken, “Wavelet ANOVA approach to model validation,” Simulation Modelling Practice and Theory, vol. 78, pp. 18–27, Nov. 2017.

R.N. Bateson, Introduction to Control System Technology, Prentice Hall, 2002.