Hybrid prediction of the power frequency breakdown voltage of short air gaps based on orthogonal design and support vector machine

This paper attempts to establish the grey correlation between the breakdown voltage of air gap and its energy storage status before discharge inception. A new method is presented for the breakdown voltage prediction of short air gaps. This method is based on an orthogonal design array and support vector machine (SVM). A hybrid model is established to predict the power frequency breakdown voltage of three typical air gaps including sphere-sphere, rod-plane, and rod-rod gaps. The input data are fifty parameters extracted from the static electric field distribution of the air gap, and the output of the model is whether the gap will breakdown under a given voltage. This model is trained by 9 samples selected by L9(33) orthogonal array and applied to predict the breakdown voltage of 90 test samples. With effective feature dimension reduction and parameter optimization of the SVM model, the predicted results coincide well with the experimental data, and the mean absolute percentage error (MAPE) is only 3.9%. The SVM model is also applied to predict the breakdown voltage of some atypical short air gaps including sphere-plane gaps, rod-sphere gaps, sphere-sphere gaps with different diameters, and rod-plane-sphere gaps. The MAPEs are respectively 4.3, 3.2, 4.2, and 6.4%, which verifies the validity and generalization performance of the proposed method. This model provides a new way to gain the critical breakdown voltage of air gaps, and therefore contributes to reducing the required test work.