Abstract
This paper presents a wavelet analysis technique together with support vector machines (SVM) to discriminate partial discharges (PD) from external disturbances (electromagnetic noise) in a GIS PD measuring system based on magnetic antennas. The technique uses the Cross Wavelet Transform (XWT) to process the PD signals and the external disturbances coming from the magnetic antennas installed in the GIS compartments. The measurements were performed in a high voltage (HV) GIS containing a source of PD and common-mode external disturbances, where the external disturbances were created by an electric dipole radiator placed in the middle of the GIS. The PD were created by connecting a needle to the main conductor in one of the GIS compartments. The cross wavelet transform and its local relative phase were used for feature extraction from the PD and the external noise. The features extracted formed linearly separable clusters of PD and external disturbances. These clusters were automatically classified by a support vector machine (SVM) algorithm. The SVM presented an error rate of 0.33%, correctly classifying 99.66% of the signals. The technique is intended to reduce the PD false positive indications of the common-mode signals created by an electric dipole. The measuring system fundamentals, the XWT foundations, the features extraction, the data analysis, the classification algorithm, and the experimental results are presented.
Highlights
Nowadays, partial discharge (PD) measurements are essential for assessing the condition of high-voltage equipment because of its intrinsic ability to detect incipient defects in the insulation system
The PD measurement systems are based on electrical techniques, in which the PD are measured by electrical sensors such as coupling capacitors, ultra high frequency (UHF)
PD measurements are fundamental in the monitoring of high voltage (HV) GIS due to its high capabilities to detect in-service failures related to defects in the insulation system [1]
Summary
Partial discharge (PD) measurements are essential for assessing the condition of high-voltage equipment because of its intrinsic ability to detect incipient defects in the insulation system. The magnetic antennas are placed in the dielectric windows in such a way that a current signal, traveling inside the GIS in the TEM mode, causes a symmetric response in the two magnetic antenna loops This new measuring system is capable of estimating the PD apparent charge, and detecting PD pulses below 5 pC [9]. Because it is capable of transforming the signals in the time and frequency domain, helping in the analysis of aperiodic signals with irregular and transition features, such as the PD [17] These wavelet-based denoising techniques do not tackle the problem of pulse-type external interferences, which are the primary source of noise contamination for the magnetic antennas.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
