A new fast method for supplying measures to avoid the high voltage mode of electromagnetic voltage transformer

A new fast method for supplying preventive measures to avoid the failure of electromagnetic voltage transformers (EMVT) due to sustained overvoltage on switch-off is proposed. This method makes full use of the characteristics of artificial neural networks and utilizes the Kohonen network model to design a classifier which can fast supply a satisfactory solution to prevent EMVT damage due to a sustained overvoltage on switch-off. Tests on a 110 kV EMVT show that the fast method has improved protection performance.<
>