Predicting the severity of nuclear power plant transients by using genetic and nearest neighbor algorithms

Nuclear power plant status is monitored by a human operator. To enhance the operator`s capability to diagnose the nuclear power plant status in case of a transient, several systems were developed to identify the type of the transient. Few of them addressed the further question: how severe is the transient? In this paper, we explore the possibility of predicting the severity of a transient using genetic algorithms and nearest neighbor algorithms after its type has been identified.