Prediction of DC Corona Onset Voltage for Rod-Plane Air Gaps by a Support Vector Machine

Thispaperproposesanewmethodtopredictthecoronaonsetvoltageforarodplaneairgap,basedonthesupportvectormachine(SVM).BecausetheSVMisnotlimitedbythesize,dimensionandnonlinearityofthesamples,thismethodcanrealizeaccuratepredictionwithfewtrainingdata.Onlyelectricfieldfeaturesarechosenastheinput;nogeometricparameterisincluded.Therefore,theexperimentdataofonekindofelectrodecanbeusedtopredictthecoronaonsetvoltagesofotherelectrodeswithdifferentsizes.Withtheexperimentaldataobtainedbyozonedetectiontechnology,andexperimentaldataprovidedbythereference,theefficiencyoftheproposedmethodisvalidated.Accuratepredictedresultswithanaveragerelativelessthan3%areobtainedwithonly6experimentaldata.