Breakdown Voltage Prediction for Sphere and Semispheroid Geometries With Gaussian Process Regression-Based Model Under the Application of Lightning Impulses of Both Polarities

Abstract

The design of high-voltage (HV) systems is principally dependent on the discharge voltage of their insulation. Sphere geometry and semispheroid geometry are extremely important in HV systems, such as ground rods and gas-insulated substations (GISs). Hence, in this work, a machine learning algorithm is proposed to develop a model to predict the discharge characteristics of air for sphere and semispheroid geometries. Finite element method (FEM) simulations have been performed to extract different electric fields and energy features of air gaps in the range of 5-40 mm under lightning impulses of both polarities. While developing the model, these features along with gap lengths are considered. The features have been used for training a machine learning algorithm based on the Gaussian process regression (GPR) to develop the model. The outcomes received from the model are ratified with measured experimental data. A good comparison between the two establishes the fidelity of the novel model. The proposed methodology is also compared with the other state-of-the-art techniques and found good. Remarkable performance has been acquired for other gap geometries as well.