Optimizing the fuel management in a VVER-1000 reactor using an artificial neural network

The present work investigates an appropriate way to solve the problem of optimizing fuel management in a VVER/1000 reactor. To automate this procedure, a computer program has been developed. This program suggests an optimal core configuration which is determined according to established safety constraints. The suggested solution is based on the use of coupled programs, one of which is the nuclear code, for making a database and modeling the core, and another one is the Hopfield neural network. An objective function is developed based on the following two basic parameters:(1) Power Peaking Factor (PPF) and (2) evaluation of the effective multiplication factor (keff).The procedure uses the optimized parameters in order to find configurations in which keff is maximized. The penalty function is applied to limit the value of local PPF in the neighborhood fuel assemblies. Therefore, in this paper we proposed a new approach for the use of Hopfield neural network to guide the heuristic search, and for evaluating the obtained results pertaining to the first core. The results show that applying the Hopfield Neural Network Artificial (HNNA) led us to the appropriate PPF and keff. Therefore, we achieved to a set of two basic parameters PPF and keff as effective factors on satisfying the safety constraints of VVER/1000 reactor core. These calculations have been performed for hot full power (without xenon and equilibrium xenon) conditions.

► The analysis technique was developed to find the optimum core configuration.
► Using Hopfield neural network to optimize fuel management in VVER/1000 reactor.
► Coupling the nuclear code and Hopfield neural network to find the optimum core.