Detection and Identification of Faults in NPP Instruments Using Kernel Principal Component Analysis

Abstract

In this paper, kernel principal component analysis (KPCA) is studied for fault detection and identification of the instruments in nuclear power plants. A KPCA model for fault isolation and identification is proposed by using the average sensor reconstruction errors. Based on this model, faults in multiple sensors can be isolated and identified simultaneously. Performance of the KPCA-based method is demonstrated with real NPP measurements.