Operator support architecture for monitoring abnormal symptoms of nuclear power plant based on knowledge engineering

An architecture to support nuclear power plant operators for monitoring abnormal symptoms has been proposed based on the techniques of knowledge engineering, and the feasibility of a plant monitoring support system was investigated. The purpose of the support system is to present the operators with useful information so that they can make correct judgment at an early and subtle stage of abnormal plant conditions. In the architecture proposed, abductive reasoning is performed to search for causal events and deductive one to predict consequential events using the knowledge representing plant components as frames and those representing causal relations as production rules. A method to deal with uncertainties in each types of reasoning has been adopted, and it is used to rank several hypotheses of causal events and to assess the importance of plant parameters for monitoring. A prototype system was developed, and its usefulness was tested using a case of failure in a recirculation pump of a BWR plant. (author)