论文信息 - Development of a neural simulator for research reactor dynamics

Development of a neural simulator for research reactor dynamics

A research reactor simulator was designed and developed by neural networks model. This simulator can predict the reactor power and temperatures (fuel, clad and coolant) in normal and accident condition considering reactivity feedbacks. The main advantage of this method, as compared with custom calculational methods (simulation with PARET and RELAP) is real time simulation without the need for much skilled or experienced setting. The response of benchmark reactor core predicted by neural simulator was compared to that obtained from PARET code and close agreement was observed.

Hossein Khalafi | M. S. Terman

[1] I. J. Leontaritis,et al. Input-output parametric models for non-linear systems Part II: stochastic non-linear systems , 1985 .

[2] . M.S.Terman,et al. Analysis of Tehran Research Reactor Dynamics Behavior in Reactivity Insertion Accidents by Recurrent Neural Network , 2006 .

[3] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[4] W. L. Woodruff,et al. A Kinetics and Thermal-Hydraulics Capability for the Analysis of Research Reactors , 1984 .

[5] Tülay Adali,et al. Modeling nuclear reactor core dynamics with recurrent neural networks , 1997, Neurocomputing.

[6] W. L. Woodruff,et al. A comparison of the PARET/ANL and RELAP5/MOD3 codes for the analysis of IAEA benchmark transients , 1996 .

[7] Caro Lucas,et al. Identification of a nuclear reactor core (VVER) using recurrent neural networks , 2002 .

[8] H. Kazeminejad. Reactivity insertion limits in a typical pool-type research reactor cooled by natural circulation , 2006 .

[9] J. Duderstadt,et al. Nuclear reactor analysis , 1976 .