Power Peaking Factor Prediction using ANFIS Method
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Power peaking factors (PPF) is an important parameter for safe and efficient reactor operation. There areseveral methods to calculate the PPF at TRIGA research reactors such as MCNP and TRIGLAV codes. However, these methods are time-consuming and required high specifications of a computer system. Toovercome these limitations, artificial intelligence was introduced for parameter prediction. Previousstudies applied the neural network method to predict the PPF, but the publications using the ANFISmethod are not well developed yet. In this paper, the prediction of PPF using the ANFIS was conducted. Two input variables, control rod position, and neutron flux were collected while the PPF was calculatedusing TRIGLAV code as the data output. These input-output datasets were used for ANFIS model generation, training, and testing. In this study, four ANFIS model with two types of input space partitioningmethods shows good predictive performances with R2 values in the range of 96%e97%, reveals the strongrelationship between the predicted and actual PPF values. The RMSE calculated also near zero. From thisstatistical analysis, it is proven that the ANFIS could predict the PPF accurately and can be used as analternative method to develop a real-time monitoring system at TRIGA research reactors.
Abstract
Power peaking factors (PPF) is an important parameter for safe and efficient reactor operation. There areseveral methods to calculate the PPF at TRIGA research reactors such as MCNP and TRIGLAV codes. However, these methods are time-consuming and required high specifications of a computer system. Toovercome these limitations, artificial intelligence was introduced for parameter prediction. Previousstudies applied the neural network method to predict the PPF, but the publications using the ANFISmethod are not well developed yet. In this paper, the prediction of PPF using the ANFIS was conducted. Two input variables, control rod position, and neutron flux were collected while the PPF was calculatedusing TRIGLAV code as the data output. These input-output datasets were used for ANFIS model generation, training, and testing. In this study, four ANFIS model with two types of input space partitioningmethods shows good predictive performances with R2 values in the range of 96%e97%, reveals the strongrelationship between the predicted and actual PPF values. The RMSE calculated also near zero. From thisstatistical analysis, it is proven that the ANFIS could predict the PPF accurately and can be used as analternative method to develop a real-time monitoring system at TRIGA research reactors.
참고문헌 (26)
- A. M. Dias, "Determination of the power density distribution in a PWR reactor based on neutron flux measurements at fixed reactor incore detectors", Ann. Nucl. Energy, 90, pp.148~156 (2016)
- I. A. Alnour, "Determination of neutron flux parameters in PUSPATI TRIGA Mark II research reactor, Malaysia", J. Radioanal. Nucl. Chem, 296, pp.1231~1237 (2013)
- I. H. Bae, "Calculation of the power peaking factor in a nuclear reactor using support vector regression models", Ann. Nucl. Energy, 35, pp.2200~2205 (2008)
- L. Snoj, "TRIGLAV : a program package for TRIGA reactor calculations", Nucl. Eng. Des, 318, pp.24~34 (2017)
- Mohamad Hairie Rabir, "Neutron flux and power in RTP core-15", AIP Conf. Proc, 1704(1) (2016)
- Man Gyun Na, "Estimation of the power peaking factor in a nuclear reactor using fuzzy neural networks", J. Kor. Nucl. Soc, 36, pp.420~429 (2003)
- 배인호, "Estimation of the Power Peaking Factor in a Nuclear Reactor Using Support Vector Machines and Uncertainty Analysis", Nuclear Engineering and Technology, 41(9), pp.1181~1190 (2009), 한국원자력학회
- Antonio C.F., "Power peak factor estimation using adaptive neural fuzzy inference system", Adv. Comput. Sci. Eng, pp.1~22 (2008)
- S. M. Mirvakili, "Developing a computational tool for predicting physical parameters of a typical VVER-1000 core based on artificial neural network", Ann. Nucl. Energy, 50, pp.82~93 (2012)
- H. Mazrou, "Application of artificial neural network for safety core parameters prediction in LWRRS", Prog. Nucl. Energy, 44, pp.263~275 (2004)
- J. L. Montes, "Local power peaking factor estimation in nuclear fuel by artificial neural networks", Ann. Nucl. Energy, 36, pp.121~130 (2009)
- R. M. G. P. Souza, "Power peak factor for protection systems e experimental data for developing a correlation", Ann. Nucl. Energy, 33, pp.609~621 (2006)
- Saeid Niknafs, "Combined neural network for power peak factor estimation", Austr. J. Basic Appl. Sci, 4, pp.3404~3410 (2010)
- A. Pirouzmand, "Estimation of relative power distribution and power peaking factor in a VVER-1000 reactor core using artificial neural networks", Prog. Nucl. Energy, 85, pp.17~27 (2015)
- A. Saeed, "Development of core monitoring system for a nuclear power plant using artificial neural network technique", Ann. Nucl. Energy, 144, pp.107513~ (2020)
- M. K. Mayilvaganan, "ANN and fuzzy logic models for the prediction of groundwater level of a watershed", Int. J. Comput. Sci. Eng, 3, pp.2523~2530 (2011)
- M. M. Sherzoy, "Atterberg limits prediction comparing SVM with ANFIS model", J. Geosci. Eng. Environ. Technol, 2, pp.20~ (2017)
- Y. Gong, "A comparative study of artificial neural networks, support vector machines and adaptive neuro fuzzy inference system for forecasting groundwater levels near Lake Okeechobee, Florida", Water Resour. Manag, 30, pp.375~391 (2016)
- M. S. Zaghloul, "Comparison of adaptive neuro-fuzzy inference systems(ANFIS)and support vector regression(SVR)for data-driven modelling of aerobic granular sludge reactors", J. Environ. Chem. Eng, 8, pp.103742~ (2020)
- Jyh-Shing Roger Jang, "ANFIS : adaptive-network-based fuzzy inference system", IEEE Trans. Syst. Man Cybern, 23, pp.665~685 (1993)
- Y. Chan-Uk, "Performance comparison of ANFIS Models by input space partitioning methods", Symmetry, 10(700), pp.1~25 (2018)
- J. Y. Hoon, "Fuzzy system modelling : an introduction’", Encycl. Artif. Intell, 109, pp.734~743 (2009)
- Long Thanh Ngo, "A type-2 fuzzy subtractive clustering algorithm", Mech. Eng. Technol, 125, pp.395~402 (2012)
- Jun Ying Chen, "A weighted mean subtractive clustering algorithm", Inf. Technol. J, 7, pp.356~360 (2008)
- Mohamad Hairie Rabir, "Determination of New Core Configuration and Cycle Length Analysis for Triga Reactor", RnD Seminar (2018), Agensi Nuklear Malaysia
- Mohamad Hairie B. Rabir, "Neutronics calculation of RTP core’", AIP Conf. Proc, 1799, pp.020009~ (2017)