Diagnosis of Turbine Valves in the Kori Nuclear Power Plant Using Fuzzy Logic and Neural Networks

This manuscript introduces a fault diagnosis system for a turbine-governor system that is an important control system in a nuclear power plant. Because the turbine governor system is operated by high oil pressure, it is very difficult to maintain the operating condition properly. The turbine valves in the turbine governor system supply an oil pressure for operation. Using the pressure change data of the turbine valves, the condition of the turbine governor control system is evaluated. This study uses fuzzy logic and neural networks to evaluate the performance of the turbine governor. The pressure data of the turbine governor and stop valves is used in the turbine governor diagnosis algorithms. The features of the pressure signals are defined to be applied in the fuzzy diagnosis system. And Fourier transformed signals of the pressure signals are used in the neural network models for diagnosis. The diagnosis results both by fuzzy logic and neural networks are compared to evaluated the performance of the designed system.