Development of partial discharge monitoring technique using a neural network in a gas insulated substation

A study was carried out to detect partial discharge signals generated in a gas insulated substation (GIS) subjected to an insulation spacer method (internal electrode method), and to determine whether or not partial discharges were generated and then locate them with a pattern recognition method using a neural network (NN). This paper describes the results, while also explaining the equivalence between simulation pulse injection and partial discharges as well as the determination using the NN mentioned above and then presenting applications using field data.