FUNCTIONAL PRINCIPAL COMPONENT ANALYSIS FOR DYNAMIC FAULT SCENARIO CLASSIFICATION

This paper reports the results of a comparison of different approaches with respect to the classification of the numerous accidental scenarios generated in a dynamic safety analysis of a Nuclear Power Plant (NPP) with digital Instrumentation and Control (I&C). In particular, two algorithms are used for classification (Fuzzy C-Means clustering and kth nearest neighbor rule) with two sets of input variables (the values of the relevant process variable and the corresponding functional principal components)