On-line Detection And Fault Diagnosis System Of Transformer Based On Electric Characteristics

As a key equipment,the state of Power Transformer have a direct effect on the safe operation of power grids.For this reason,major research effort has focused on detecting failures of their insulating systems prior to unexpected machine outage,coming up with several industrial methods for the on-line and off-line monitoring of power transformers to make up for differential protection deficiencies.In this paper the on-line analysis of leakage flux will be presented as an alternative and efficient procedure for assessing machine integrity and detecting the presence of insulating failures during earliest stages.And a novel integrated morphology-wavelet filter is used for suppressing field noise,which is effective in suppressing fielding noise and applicable in PD detection.Finally, using ID3 method to make decision tree to form part of the fault diagnosis rules for the operation maintenance staff with intellectual support.