Classification of partial dischargesources ingas-insulated substations using novelpreprocessing strategies

Partial discharge activity in GIS can indicate impending breakdown. The activity is recorded as characteristic point on wave records which are classified into defect types by expert engineers. Classification assists with the assessment of the risk of catastrophic failure. An automatic technique has been developed aimed at replicating the strategy used by an expert during manual classification. Preprocessing techniques have been selected which implicitly incorporate the processes used by the expert rather than applying explicit rules. Information from the records pertinent to classification is extracted using mathematical morphology techniques allowing substantial compression of the data. An artificial neural network trained with such data has been shown to produce results indicating that classification matched that of the expert.