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.
Detection and Identification of Faults in NPP Instruments Using Kernel Principal Component Analysis
- Views Icon Views
- Share Icon Share
- Search Site
Ma, J., and Jiang, J. (December 29, 2011). "Detection and Identification of Faults in NPP Instruments Using Kernel Principal Component Analysis." ASME. J. Eng. Gas Turbines Power. March 2012; 134(3): 032901. https://doi.org/10.1115/1.4004596
Download citation file: