Partial discharge pattern recognition of power transformer with neural network applications

Power transformers play a crucial role in operation of transmission and distribution systems. A dielectric failure in a power transformer could result in unplanned outages of power systems, which affect a large number of customers. In this paper, the application of two different networks to recognize patterns of partial discharge (PD) of power transformer models is studied. Eleven well-designed discharge models are presented as well. According to results of PD measurements and neural network (NN) training and testing, two different NN paradigms can recognize different PD sources for those data at the same voltage level. NN might misclassify those PD patterns or sources with data of different voltage level