Gas Insulated Switchgear Partial Discharge Type Identification Based on Frequency Division Features and Improved Long Short-Term Memory Neural Networks

Abstract

In order to ensure the safe and stable operation of gas insulated switchgear (GIS), a new method for identifying the type of partial discharge in GIS is proposed. First, the GIS partial discharge experimental platform produced four partial discharge signals. Second, the energy moments are calculated at each frequency to produce the frequency division features after the four partial discharge signals have been decomposed using variational modal decomposition (VMD). Finally, the type of GIS partial discharge is determined using the LSTM model enhanced by the quantum cuckoo search (QCS) algorithm. The experimental results show that the proposed method can successfully identify four types of partial discharge in GIS with an accuracy of 99%.