Neuro-fuzzy systems for fault detection and isolation in nuclear reactors

This work presents an application of recurrent neuro-fuzzy systems to fault detection and isolation in nuclear reactors. In the adopted framework, a fuzzification module is linked to an inference module, which is actually a neural network adapted to the recognition of the dynamic evolution of process variables. Two different approaches to the neural network inference module are tested over data simulated by a commissioned simulator for the detection and isolation of a number of security related faults in a nuclear reactor