基于PCA的主泵传感器状态监测模型

核电厂主泵的主、辅系统中布置了大量的传感器,随着主泵的运行,传感器会出现不同程度的老化或故障。为了改善现有核电厂传感器周期性测试和校准方案的不足,提高运行的安全性与经济性,采用主成分分析(PCA)技术对主泵的传感器进行状态监测。使用某核电厂主泵的运行数据建立PCA监测模型,并利用该模型对传感器的小漂移故障和共模故障进行识别,仿真结果表明该模型对主泵传感器具有很好的监测效果。

Condition Monitoring Model for Sensors of Reactor Coolant Pump Based on PCA

In order to meet the requirements of operation control and parameter monitoring, a large number of sensors are arranged in the main and auxiliary systems of the reactor coolant pump. As the reactor coolant pump operates, the sensors may age or malfunction. In order to improve the weakness of the periodic tests and calibration schemes of sensors in nuclear power plants, the principal component analysis (PCA) was utilized for the condition monitoring of the reactor coolant pump sensors. The PCA monitoring model was established based on the operating data of the reactor coolant pump of a nuclear power plant, and the small drift fault and common mode fault of the sensors were identified by the model. The simulation results show that the monitoring model has a good effect on the condition monitoring of the reactor coolant pump sensors.