Title :
Quality criteria of partial discharge patterns
Author_Institution :
Thomastr. 8, Hambrucken, Germany
Abstract :
Partial Discharge (PD) Measurement is one of the most powerful diagnostic methods for design and improvement of electrical hv equipment. The main aspect is the interpretation of the phase resolved PD patterns. A database of 4.000 pd patterns of on-site measurements has now been used for basic investigations with neural networks. In a first step 500 of them have been preselected and classified by a human expert. These files have been classified into 44 classes. Due to the recognition results of the neural network quality criteria have been considered
Keywords :
neural nets; partial discharge measurement; pattern classification; HV electrical equipment; insulation diagnosis; neural network; on-site measurement; pattern classification; pattern recognition; phase resolved partial discharge pattern; quality criteria; Acoustic measurements; Humans; Neural networks; Neurons; Partial discharge measurement; Partial discharges; Pulse measurements; Shape; Testing; Voltage;
Conference_Titel :
Electrical Insulation and Dielectric Phenomena, 1998. Annual Report. Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-5035-9
DOI :
10.1109/CEIDP.1998.732925
