A NEURO-FUZZY CONTROLLER FOR AXIAL POWER DISTRIBUTION IN NUCLEAR-REACTORS

A neuro-fuzzy control algorithm is applied for the core power distribu tion in a pressurized water reactor. The inputs of the neural fuzzy sy stem are composed of data from each region of the reactor core. Rule o utputs consist of linear combinations of their inputs (first-order Sug eno-Takagi type), The consequent and antecedent parameters of the fuzz y rules are updated by the backpropagation method, The reactor model u sed for computer simulations is a two-point xenon oscillation model ba sed on the nonlinear xenon and iodine balance equations and the one-gr oup, one-dimensional neutron diffusion equation having nonlinear power reactivity feedback, The reactor core is axially divided into two reg ions, and each region has one input and one output and is coupled with the other region, The interaction between the regions of the reactor core is treated by a decoupling scheme, This proposed control method e xhibits very fast response to a step or a ramp change of target axial offset without any residual flux oscillations between the upper and lo wer halves of the reactor core.