Classification of Nuclear Reactor Severe Accidents using Probabilistic Neural Network based on Particle Swarm Optimization
DOI:
https://doi.org/10.17146/tdm.2021.23.3.6247Keywords:
Probabilistic Neural Network, Particle Swarm Optimization, Severe accident, Nuclear reactorAbstract
Due to its exposure to hazard and complexity, the identification and prediction of severe accident scenarios against an initiating event of a nuclear power plant remain a challenging task. This paper aims to classify severe accidents at the Advanced Power Reactor 1400MWe (APR1400), which include the loss of coolant accident (LOCA), total loss of feedwater (TLOFW), steam generator tube rupture (SGTR), and station blackout (SBO) using a standard Probabilistic Neural Network (PNN) and Particle Swarm Optimization-based Probabilistic Neural Network (PSO PNN). The algorithm has been implemented in MATLAB. The experiment results showed that supervised PNN PSO could classify severe accident of nuclear power plant by 19.4-point percent better than the standard PNN.
References
Santoso S., Himawan R., Situmorang J., Suryono T.J., Edison E. Reactor Operational Experience Review and Analysis Based on Un-intended Reactor Trip Data. J. Teknol. Reakt. Nukl. TRI DASA MEGA. 2019. 21(2):71-78.
https://doi.org/10.17146/tdm.2019.21.2.5300
No Y.-G., Kim J.-H., Na M.-G., Lim D.-H., Ahn K.-I. Monitoring Severe Accidents Using AI Techniques. Nucl. Eng. Technol. 2012. 44(4):393-404.
https://doi.org/10.5516/NET.04.2012.512
Kim S.H., Shin S.G., Han S., Kim M.H., Pyeon C.H. Feasibility Study on Application of an Artificial Neural Network for Automatic Design of a Reactor Core at the Kyoto University Critical Assembly. Prog. Nucl. Energy. 2020. 119:103183.
https://doi.org/10.1016/j.pnucene.2019.103183
Zhao Y., Li T., Zhang X., Zhang C. Artificial Intelligence-based Fault Detection and Diagnosis Methods for Building Energy Systems: Advantages, Challenges and the Future. Renew. Sustain. Energy Rev. 2019. 109:85-101.
https://doi.org/10.1016/j.rser.2019.04.021
Tian D., Deng J., Vinod G., Santhosh T. V, Tawfik H. A Constraint-based Genetic Algorithm for Optimizing Neural Network Architectures for Detection of Loss of Coolant Accidents of Nuclear Power Plants. Neurocomputing. 2018. 322:102-109.
https://doi.org/10.1016/j.neucom.2018.09.014
Lee D., Seong P.H., Kim J. Autonomous Operation Algorithm for Safety Systems of Nuclear Power Plants by Using Long-short Term Memory and Function-based Hierarchical Framework. Ann. Nucl. Energy. 2018. 119:287-299.
https://doi.org/10.1016/j.anucene.2018.05.020
Shi J., Deng Y., Wang Z. Analog Circuit Fault Diagnosis Based on Density Peaks Clustering and Dynamic Weight Probabilistic Neural Network. Neurocomputing. 2020. 407:354-365.
https://doi.org/10.1016/j.neucom.2020.04.113
Santhosh T. V, Gopika V., Ghosh A.K., Fernandes B.G. An Approach for Reliability Prediction of Instrumentation & Control Cables by Artificial Neural Networks and Weibull Theory for Probabilistic Safety Assessment of NPPs. Reliab. Eng. Syst. Saf. 2018. 170:31- 44.
https://doi.org/10.1016/j.ress.2017.10.010
Zhu H., Lu L., Yao J., Dai S., Hu Y. Fault Diagnosis Approach for Photovoltaic Arrays Based on Unsupervised Sample Clustering and Probabilistic Neural Network Model. Sol. Energy. 2018. 176:395 -405.
https://doi.org/10.1016/j.solener.2018.10.054
Gao W., Zhao Y., Smidts C. Component Detection in Piping and Instrumentation Diagrams of Nuclear Power Plants Based on Neural Networks. Prog. Nucl. Energy. 2020. 128:103491.
https://doi.org/10.1016/j.pnucene.2020.103491
Liu J., Seraoui R., Vitelli V., Zio E. Nuclear Power Plant Components Condition Monitoring by Probabilistic Support Vector Machine. Ann. Nucl. Energy. 2013. 56:23-33.
https://doi.org/10.1016/j.anucene.2013.01.005
Dos Santos M.C., Pinheiro V.H.C., Do Desterro F.S.M., De Avellar R.K., Schirru R., Dos Santos Nicolau A., et al. Deep Rectifier Neural Network Applied to the Accident Identification Problem in a PWR Nuclear Power Plant. Ann. Nucl. Energy. 2019. 133:400-408.
https://doi.org/10.1016/j.anucene.2019.05.039
Zhao Y., Tong J., Zhang L. Rapid Source Term Prediction in Nuclear Power Plant Accidents Based on Dynamic Bayesian Networks and Probabilistic Risk Assessment. Ann. Nucl. Energy. 2021. 158:108217.
https://doi.org/10.1016/j.anucene.2021.108217
Norouzi N., Sadegh-Amalnick M., Alinaghiyan M. Evaluating of the Particle Swarm Optimization in a Periodic Vehicle Routing Problem. Measurement. 2015. 62:162-169.
https://doi.org/10.1016/j.measurement.2014.10.024
Augusto J.P. da S.C., Dos Santos Nicolau A., Schirru R. PSO with Dynamic Topology and Random Keys Method Applied to Nuclear Reactor Reload. Prog. Nucl. Energy. 2015. 83:191-196.
https://doi.org/10.1016/j.pnucene.2015.03.009
Jamalipour M., Gharib M., Sayareh R., Khoshahval F. PWR Power Distribution Flattening Using Quantum Particle Swarm Intelligence. Ann. Nucl. Energy. 2013. 56:143-150.
https://doi.org/10.1016/j.anucene.2013.01.026
Pambudi Y.D.S., Wahab W., Kusumoputro B. Particle Swarm Optimization-Based Direct Inverse Control for Controlling the Power Level of the Indonesian Multipurpose Reactor. Sci. Technol. Nucl. Install. 2016. 2016:1- 9.
https://doi.org/10.1155/2016/1065790
Coban R. Power Level Control of the TRIGA Mark-II Research Reactor Using the Multifeedback Layer Neural Network and the Particle Swarm Optimization. Ann. Nucl. Energy. 2014. 69:260-266.
https://doi.org/10.1016/j.anucene.2014.02.019
Jiang Y., Li X., Huang C., Wu X. Application of Particle Swarm Optimization Based on CHKS Smoothing Function for Solving Nonlinear Bilevel Programming Problem. Appl. Math. Comput. 2013. 219(9):4332 - 4339.
