Study for optimization of fuel recharge pattern for a PWR reactor using neural networks multilayer Feedforward

Fuel recharge management in a power reactor is primarily focused on the core recharge pattern to achieve better cycle performance by observing all safety parameters adopted. The possibility of fuel distribution, considering an equilibrium core, with 1/3 recharge of this and N fuel elements, reaches N^N combinations. In this paper we present the strategy of an algorithm based on artificial neural networks to optimize fuel recharge in the core of a nuclear reactor. The idea is to develop a methodology capable of choosing the best combinations that satisfy the radial power peak factor and maximize the effective multiplication factor at the beginning of the cycle, and also satisfy the minimum critical power ratio and maximum heat generation rate in the end of cycle. In this study we present the development of the neural network multilayered feedforward based on multivalued neurons that will be used for the development of the methodology