Distributed Fault Diagnosis Framework for Nuclear Power Plants

Fault diagnosis can quickly and accurately diagnose the cause of the fault. Based on the characteristics of nuclear power plant (NPP), this paper proposed the distributed fault diagnosis methods. BP neural network and decision tree reasoning combined methods for fault diagnosis are studied in this paper. Firstly, fault diagnosis is carried out by BP neural network and decision tree reasoning, and then the global fusion diagnosis is carried out by information fusion. Secondly, the key technologies of BP neural network and decision tree sample construction are studied. Finally, simulation results show that the developed distributed fault diagnosis system has high reliability and expected diagnostic ability, which can realize the rapid and accurate diagnosis. The distributed fault diagnosis system for NPPs also lays a foundation for future research.