Research on Condition Monitoring Technique of Sensors in NPPs Based on PCA

To solve the shortcomings of physical redundancy methods, Principal Component Analysis（PCA） is adopted. Firstly, PCA can be used to verify the monitoring results of physical redundancy method. Secondly, PCA method can detect the small drift of sensors which physical redundancy method can hardly deal with. Finally, PCA method can detect the common mode faults in the redundant sensors. At the end of this paper, sensor measurements from a real NPP are used to train the PCA model. Artificial failures are imposed to the original measurements. Simulation results show that the PCA method has good effects on the issues that have been raised above.