It is true that a fault diagnosis method based on BP neural network is proposed, the structure and parameters of the network are determined, and the network is trained. The simulation results show that the neural network has good fault identification ability, and the fault diagnosis system of three-phase inverter based on BP neural network is feasible.
Power electronics technology is widely used in national defense, military and industrial production. Once the power electronic equipment fails, it may damage the equipment or system and even threaten personal safety. Therefore, it is very meaningful to detect and diagnose the faults of power electronic equipment. Because of the small overload capacity and fast damage speed of power electronic devices, fault information only exists in tens of milliseconds from fault to power failure, so dynamic monitoring and online diagnosis are needed. At present, people can only diagnose whether it has a fault and what kind of fault it is from the output waveform, but there are many fault diagnosis methods for power electronic circuits. BP network is used to diagnose the open circuit fault of inverter main circuit components in reactive power generator. The fault diagnosis of the main circuit of three-phase converter is realized by Fourier analysis method. Wavelet analysis and neural network are proposed to diagnose power electronic equipment.
Equipment fault diagnosis method. Taking the three-phase bridge inverter circuit as an example, this paper studies the method of fault diagnosis using BP neural network.