基于PCA的核电站传感器状态监测方法研究

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

针对目前核电站中以物理冗余为主的传感器状态监测方法所存在的不足之处,提出了基于主元分析(PCA)的传感器状态监测方法,这种基于解析冗余的方法是对物理冗余方法的验证,解决了物理冗余方法不能实现传感器小漂移的监测,改善了冗余传感器组中多数传感器出现共模故障时,物理冗余监测方法可能给出错误融合结果的问题。使用核电站的真实传感器数据建立PCA监测模型,人为引入故障到测试数据中进行分析,仿真结果验证了文中提出的传感器状态监测模型的有效性。

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.