Partial discharge type identification method based on synchrosqueezing wavelet transform

Abstract

The invention provides a partial discharge type identification method based on synchrosqueezing wavelet transform, and aims to provide an identification method for the partial discharge signal of a transformer to realize the identification of the partial discharge signal of the transformer. The method comprises first, decomposing the typical partial discharge signal of the transformer by using thesynchrosqueezing wavelet transform; then, using a multi-scale permutation entropy as a feature quantity of the discharge type identification by using the energy and complexity difference of the partial discharge signal at different decomposition scales; and finally, identifying a discharge type by using a support vector machine classifier based on the extracted feature quantity. The method can achieve average partial discharge signal identification accuracy higher than 90%, and is obviously superior to other commonly used transformer partial discharge identification methods.

Description

technical field [0001] The invention relates to a partial discharge type identification method based on synchronous squeeze wavelet transform and the field of power system signal processing. Background technique [0002] The power transformer is one of the most critical equipment in the power system, and its safety performance affects the safe and effective operation of the power grid. Partial Discharge (PD) is the main cause of insulation damage to large high-voltage equipment such as power transformers, and different types of partial discharge have different degrees of insulation damage, and their formation mechanisms are also different. Therefore, quickly and accurately identifying different transformer partial discharge types not only provides a solid and powerful basis for subsequent fault location identification, but also has important guiding significance for maintaining the stable and effective operation of the power system. [0003] At present, the methods for dete...

AI Technical Summary

Problems solved by technology

However, since the wavelet transform only further decomposes the low frequency part, the frequency resolution of the high frequency part is poor

After the PD signal is decomposed by wavelet transform, there are interlaced frequency bands in the amplitude-frequency response curve, and there are often serious spectrum aliasing and energy leakage between the sub-bands. Therefore, the multi-scale feature parameters extracted from the sub-bands decomposed by wavelet transform often cannot accurately describe the PD signal. Time-frequency information is not conducive to subsequent classification and identification

Images