Partial discharge (PD) signal classification analysis on cross-linked polyethylene (XLPE) cables is complex, requiring a comprehensive understanding of the characteristics of PD patterns. In the realm of high-voltage electrical insulation, PD pattern characteristics, such as PD charge and inception voltage, are essential as assessment criteria in diagnostics systems using PD classifiers. This paper provides a review of various PD patterns and classifiers used by previous researchers, specifically for XLPE cables. In addition, the differences of the research on various sensor development based on PD detection in the past 27 years are also discussed. The repeatability, recognition accuracy, recognition speed, and effect of feature sizes on each PD classification method are reviewed and explained. The review indicates that the pattern recognition for PD signal using artificial neural network (ANN) exhibits better performance in terms of accuracy and repeatability than the other methods, and the reduction of feature size does not affect the accuracy of ANN.INDEX TERMS Partial discharge (PD), cross-linked polyethylene (XLPE) cable, solid insulator, pattern recognition, feature extraction, artificial neural network (ANN)
<span>This paper presents, wavelet based de-noising technique for on-site partial discharge (PD) measurement signal. The signal is measured from medium voltage power cable at 11 kV distribution substation. The best mother wavelet, decomposition level and the type of threshold for the de-noising technique are selected based on the signal to noise ratio (SNR) aggregation. The SNR aggregation is determined based on the minimum, maximum, mean and standard deviation parameters. The same standard de-noising procedure is applied for two different PD signals and the selection parameters are done based on the accuracy of de-noising analysis. The analysis is performed in MATLAB software environment and Daubechies 2 (db2) is found as the best mother wavelet at tenth decomposition levels with soft threshold type. This study is specifically performed to develop the de-noising procedure for on-site PD measurement. Overall results indicate that the right selection of the de-noising procedure will help to improve the PD signal detection from on–site measurement.</span>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.