Ferromagnetic Resonance Fault Identification of 10kV Electromagnetic Voltage Transformer

With the increasing development of power grids, the problem of ferroresonance in neutral-point non-grounded power distribution systems is becoming more and more serious. Due to the close similarities in characteristics between single-phase grounding fault overvoltage and ferroresonance overvoltage, in order to correctly diagnose the type of overvoltage, firstly, the simulation model was built by PSCAD to obtain the simulation waveform of different faults. Then, the resonance overvoltage fault feature extraction method based on VMD was constructed by MATLAB. Finally, by comparing the influence of the number of input layer nodes and the number of hidden layer neurons on the BP neural network, the BP neural network was optimized by MATLAB to achieve the identification of ferroresonance and normal working, grounding fault states, and provide a reliable judgment standard for the action of protection devices.