Jorge Alfredo Ardila-Rey

TL;DR: In this paper, spectral power analyses of PD pulses and the spectral power ratios at different frequencies were calculated to classify PD sources and noise by means of a graphical representation in a plane, which is a flexible tool for noise identification and will be useful for pulse characterization.

TL;DR: In this paper, the authors reviewed recent progress made on ANN development for partial discharge (PD) pattern recognition by a literature survey and discussed several suggestions for improvement are proposed by the authors, such as determining the optimum weights in training the ANN, using PD data captured over long stressing period, recognizing different PD degradation levels, using the same resolution sizes of the PD patterns when training and testing the ANN with different PD dataset, understanding the characteristics of multiple concurrent PD faults and effectively recognizing them; and developing techniques in order to shorten the training time for the ANN as applied for PD recognition.

TL;DR: PD measurements with antennas and the effect of their EM propagation in power transformer tanks is an open research topic that is considered and can be found that mainly, the antenna frequency response, the frequency content distribution depending on the PD source and the enclosure resonances modes are the main factors to be considered in PD acquisitions with these sensors.

TL;DR: The experimental results demonstrate that this technique is highly effective in identifying PD for cases where several sources are active or when the noise level is high, and will help in the decision of decommissioning the asset with reduced costs and low impact to the grid reliability.

TL;DR: If several EM sources could be previously calibrated, it is possible to detect pulses corresponding to PD activity, and the calculation of the time length of the pulses is introduced to separate signals where the PR alone do not give a conclusive solution.