A Partial Discharge Acoustic Detection Method of the Switchgear Based on Wavelet Denoising

Abstract

Abstract To ensure the safe operation of the power grid and accurately identify the acoustic signal of the partial discharge of the switchgear, a partial discharge acoustic detection method for switchgear based on wavelet denoising is proposed in this paper. First, the Gaussian mixture algorithm model is used to denoise the discharge acoustic signal; then, the feature extraction and training of the acoustic signal samples are carried out; finally, a classifier is used to complete the discharge state recognition. The experimental results show that the detection accuracy of the proposed detection algorithm can reach more than 90%, and the robustness is good in different noise environments.