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

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