Fault diagnosis of turbine unit equipment based on data fusion and RBF neural network

The monitoring of turbine in operation condition and fault diagnosis system in power plant is the key to guarantee the units long-term security and economic operation. The turbine faults were determined by a variety of factors, which brought many difficulties to the fault diagnosis. In general condition, using the RBF neural network can make the turbine fault diagnosis right. However, in some time, as the judging value of the method for multiple fault types were close, it was difficult to determine the fault type accurately. A fault diagnosis method for turbine based on data fusion and RBF neural network was proposed in the paper. Combined with the advantages of data fusion, the method can be used to avoid the situations when the fault types were unable to be determined. The algorithm has been demonstrated by the experimental results. Therefore, the application of fault diagnosis, using the method proposed in the paper can determine the fault type accurately, which played an important role in detecting and eliminating faults in time.