An overview of application of artificial neural network to partial discharge pattern classification

This paper presents an overview of an artificial neural network(ANN) based partial discharge (PD) distribution pattern recognition problem to power system application. After referring briefly to the developments of ANN technique-based PD measurements, the paper outlines how the introduction of new emerging technology has resulted in the design of a number of PD diagnostic systems for practical application in test laboratories and on site. The structure of a PD data base and selection of learning of PD data pattern, extraction of relevant characteristic feature or information for PD recognition are discussed. Some practical problems encountered in the neuro-fuzzy techniques based real time PD recognition are also addressed.