Novel noise reduction method based on improved empirical wavelet transform and kurtosis for partial discharge signal of high-voltage cables

Abstract

Partial discharge (PD) detection is useful to the online monitoring of high-voltage cables, which are affected by periodic narrowband interference and random white noise. To suppress the influence of complex noise signals on the measurement of PD signals, a novel noise reduction method based on improved empirical wavelet transform (IEWT) and kurtosis for the PD signals of high-voltage cables is proposed. First, empirical wavelet function (EWF) signals arranged in order of frequency are obtained by decomposing the signal with IEWT. Then, the kurtosis criterion is introduced, and the reconstructed inherent modal function is adaptively screened. Finally, the improved threshold function is used in eliminating residual noise information in the reconstructed signal. Compared with the noise reduction methods based on EWT and EMD, the proposed noise reduction method can effectively suppress noise information in PD and has good practicability.

Keywords

• partial discharges
• white noise
• interference suppression
• wavelet transforms
• signal denoising
• reconstructed signal
• residual noise information
• improved threshold function
• reconstructed inherent modal function
• kurtosis criterion
• empirical wavelet function signals
• pd signals
• complex noise signals
• random white noise
• periodic narrowband interference
• partial discharge detection
• high-voltage cables
• partial discharge signal
• improved empirical wavelet
• novel noise reduction method