Prediction of Switching Impulse Breakdown Voltage of the Air Gap Between Tubular Buses in Substation

Obtaining the breakdown voltage of the air gap by the artificial intelligence algorithm is helpful to reduce the workload of the test. In this paper, the support vector machine (SVM) is used to predict the positive 50% switching impulse breakdown voltage (U
50%+
) between tubular buses in 220kV substations. The features reflecting the electric field distribution are extracted from the shortest discharge path of the air gap, and the breakdown voltage prediction models are established. The predicted results indicate that the range of U
50%+
of the tubular bus gap in the 220kV substations with a gap distance of 3.325 meters is 1540kV-1589kV. The predicted value is within the range of breakdown voltage recommended in the IEC standard. This method may provide a reference for air gap insulation prediction engineering applications.