The fuzzy logic and neural network are combined in this paper, and the distinct differences and connections between the fuzzy logic and neural network are compared. Furthermore, the algorithm and structure of the fuzzy neural network are introduced. This theory is applied to the nuclear power plant, and the fault diagnostic system of the nuclear power plant based on fuzzy neural network is built. In order to test the validity of the system, the inverted U-tubes break accident of steam generator is used as an example and many experiments are done. The test result showed that the fuzzy neural network could identify the fault.