A complex classification approach of partial discharges from covered conductors in real environment

Partial discharges are known as indicators of degradation of insulation systems. In case of medium voltage overhead lines with covered conductors, the internal partial discharges indicate the degradation of insulation system, rupture or downfall of the line. The reliability and selectivity of methods to detect internal partial discharges in the covered conductors are mainly given by the level of background noise. The background noise distorts the pattern of partial discharges (PD-pattern) and decreases the capability of detection methods to recognize the features of PD-pattern corresponding to the degradation of an insulation system. This paper presents the results from the testing of a developed and optimized model for detection of covered conductor faults. The ability to identify covered conductor faults was verified in the real environment.