A Framework for Monitoring and Fault Diagnosis in Nuclear Power Plants Based on Signed Directed Graph Methods

When nuclear power plants (NPPs) are in a state of failure, they may release radioactive material into the environment. The safety NPPs must thus be maintained at high standard. Online monitoring and fault detection diagnosis (FDD) important helping NPP operators understand system provide online guidance timely manner. Here, to mitigate shortcomings process NPPs, five-level threshold, qualitative trend analysis (QTA), signed directed graph (SDG) inference combined improve veracity sensitivity FDD. First, three-level threshold is used for ensure accuracy an alarm signal, candidate faults determined based on SDG backward from parameters. According faults, forward applied obtain Second, QTA determine parameters utilized Finally, real identified by basis To verify validity method, we have conducted simulation experiments, which comprise loss coolant accident, steam generator tube rupture, feed water, main line break, station black-out. This case study shows that proposed method superior conventional can diagnose more quickly accurately.