Pattern recognition application for surveillance of abnormal conditions in a nuclear reactor

Abstract The system to monitor abnormal conditions in a nuclear reactor, based on the noise analysis of the reactor basic parameters such as power, temperature and coolant flow rate has been developed. The pattern recognition techniques such as clustering, cluster analysis, feature selection and cluster visualization methods form the basis of the software system. Apart from non-hierarchical clustering procedures applied earlier, the hierarchical one is recommended. The system application for IBR-2 Dubna reactor diagnostics is shown.