基于PCA与SDG的反应堆一回路系统故障诊断方法研究

Research on Accident Diagnosis Method for Reactor Primary Circuit System Based on SDG and PCA

反应堆一回路系统复杂,运行参数耦合多变,安全问题突出。为了保障运行安全、快速定位故障源,提出基于主元分析(PCA)与符号有向图(SDG)的一回路系统故障诊断模型。以一回路系统为诊断研究对象建立PCA-SDG模型,通过PCA分析监测参数的残差,判断故障的发生;然后采用SDG模型进行反向推理,找到潜在故障类型。通过模拟机仿真试验验证,该方法能够有效诊断故障,并提供报警传递路径。该方法可用于运行人员辅助决策,对运行装置的状态监测、报警分析和故障诊断具有重要意义。

The reactor primary circuit system is complex,and the operation parameters are coupled and changeable,thus the safety problems are prominent.In order to ensure the operation safety and locate the fault source quickly after the accident,a fault diagnosis method of the primary system based on principle component analysis(PCA)and signed directed graph(SDG)model is proposed.Taking the reactor primary system as the research object,PCA-SDG model is established,and the residual analysis is conducted by PCA to detect the occurrence of fault;and then the reverse reasoning is carried out by using SDG model to find the possible fault types.Through the simulation test of the simulator,it is verified that the method can effectively diagnose the fault and provide the alarm transmission path.This method can be used to assist the decision making of the operator,which is of great significance to the status monitoring,alarm analysis and fault diagnosis of the operating device.