Fault prediction method and system for voltage transformer CVT

The invention discloses a fault prediction method and system for a voltage transformer CVT, and belongs to the field of voltage transformer CVT fault detection, and the method comprises the steps: collecting a voltage effective value and a voltage phase value during the operation of the voltage transformer CVT, carrying out the deletion processing of an abnormal value, and carrying out the filling of null value data, and obtaining CVT voltage data; and constructing an LSTM-Informer model consisting of an encoding processing module, a multi-scale fusion module, an encoder, a decoder and a rolling period data capture prediction module, training through the CVT voltage data, and constructing a fault prediction model for performing fault prediction on the voltage transformer CVT. According to the invention, fault prediction can be carried out on the voltage transformer CVT in a period of time in the future, and a key direction is indicated for subsequent fault monitoring of workers, so that the workers can make a