A Real Time Expert System for Decision Support in Nuclear Power Plants

Authors: Andressa dos Santos Nicolau, João P. da S.C Algusto, Claudio Márcio do N. A. Pereira, Roberto Schirru

Abstract:

In case of abnormal situations, the nuclear power plant (NPP) operators must follow written procedures to check the condition of the plant and to classify the type of emergency. In this paper, we proposed a Real Time Expert System in order to improve operator’s performance in case of transient or accident with reactor shutdown. The expert system’s knowledge is based on the sequence of events (SoE) of known accident and two emergency procedures of the Brazilian Pressurized Water Reactor (PWR) NPP and uses two kinds of knowledge representation: rule and logic trees. The results show that the system was able to classify the response of the automatic protection systems, as well as to evaluate the conditions of the plant, diagnosing the type of occurrence, recovery procedure to be followed, indicating the shutdown root cause, and classifying the emergency level.

Keywords: Emergence procedure, expert system, operator support, PWR nuclear power plant.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1131982

References:

[1] Y. Bartal, J. Lin, R. E. Uhrig, “Nuclear Power Plant Transient Diagnosis Using Artificial Neural Network that Allow Don't Know Classifications,” Nuclear Technology, pp. 272-281, 1992.
[2] E. B., Bartlett, R. E. Uhrig, “Nuclear Power Plant Status Diagnostics Using an Artificial Neural Network”, Nuclear Technology, vol. 97, pp. 272-281, 1992.
[3] A .C.A. Mol., “A Neural model for transient identification in dynamic processes with ‘don’t know’ response”, Pergamon, vol. 30, pp. 1365-1381, 2002.
[4] C. M. N. A. Pereira, R. Schirru, A. S. Martinez, “Learning an Optimized Classification System From a Data Base of time Series Patterns Using Genetic Algorithm,” Data Mining, Computation Mechanics Publications WIT Press, 1998.
[5] J. A. C. C. Medeiros, R. Schirru, “Identification of a nuclear power plant transients using the Particle Swarm Optimization Algorithm,” Annals of Nuclear Energy, pp. 576-582, 2008.
[6] A. S. Nicolau, and R. Schirru, “A new methodology for diagnosis system with ‘Don’t Know response for Nuclear Power Plant,” Annals of Nuclear Energy, vol. 100, pp. 91-97, 2017.
[7] Y. J. on, “A Diagnostic Expert System for the Nuclear Power Plant Based on the Hybrid Knowledge Approach,” IEEE Transactions on Nuclear Science, vol.36, n.6, December 1989.
[8] K. S. Kang, S. W. Cheon, and S. H. Chang, “Development of an expert system for performance evaluation and diagnosis in nuclear power plants,” IEEE fifth Conference on Human Factors and Power Plants, Seou, pp. 308-313, 1992.
[9] H. B. Pnttgen and J. F. Jansen, “An Expert System for the design of a power plant electrical auxiliary system,” IEE Transactions on Power Systems, vol. 3, pp. 254-261, 1988.
[10] R. S. Zhongyn, W. Virgilio, A. Centeno, “Power System Islanding Detection & Identification using Topology Approach and Decision Tree,” IEEE, pp. 1-6, 2011.
[11] N. Mayadevi, S. S. Vinodchandra, S. Ushakumari, “A Review on Expert System Applications in Power Plants,” International Journal of Electrical and Computer Engineering, vol.4, n.1, pp.116-126, February 2014.
[12] F. Hayes-Roth, D. A. Waterman, D.B. Lenat. Building Expert Systems. (Book style), 1983.
[13] PYTHON, About Python. https://www.python.org/about/.