Ship Generator Rotor Windings Short Circuit Fault Diagnosis Based On Wavelet And Neural Network

Vessel generator is the core component of the ship power system, related with the normal operation of the ship. Once it goes wrong, it must be made maintenance to return normal as soon as possible, or this may result in huge economic losses and endanger the lives of the staff in the ship. Therefore, the research of vessel generator fault diagnosis has great significance.The research of this paper is mainly vessel generator rotor winding inter turn short circuit, the main contents are included as follows:The paper analyzes the causes of generator rotor winding inter turn short circuit, and summarizes up the generator rotor winging inter turn short circuit in the diagnosis. The paper puts forward differential coin detection method to diagnose the generator rotor winding inter turn short circuit. Through analyzing the principle of generator,I set up the generator rotor winding inter turn short circuit fault diagnosis of analog signals and the signal is simulated.Because of the special advantages of wavelet analysis in signal processing, the paper puts forward the energy band wavelet analysis method to extract the eigenvalues of fault diagnosis. The number of short circuit turns is different, and various frequency bands through wavelet analysis of the energy values are different. Therefore, each band can be the energy eigenvalues as a diagnostic feature vector.Neural network can classify the different fault. After wavelet analysis extracts feature vectors, the paper constructs corresponding neural network for fault identification, and designs the combination of wavelet and neural network approach. Finally, the simulation concludes that the diagnosis using wavelet and neural network approach to generator rotor winding inter turn short circuit identification is feasible.