Data-Driven Dynamics Learning on Time Simulation of SF6 HVDC-GIS Conical Solid Insulators

An HVDC-GIL system with a conical spacer in a radioactive environment is studied in this work using simulated data on COMSOL® Multiphysics. Electromagnetic simulations on a 2D model were performed with varying ion-pair generation rates and potential applied to the system. This article explores machine learning methods to derive time to steady state, dark current, gas conductivity, and surface charge density expressions. The focus was on constructing symbolic representations, which could be interpretable and less prone to overfitting, using the symbolic regression (SR) and sparse identification of nonlinear dynamics (SINDy) algorithms. The study successfully derived the intended expressions, demonstrating the power of symbolic regression. Predictions of dark currents in the gas–ground electrode interface reported an absolute error and mean absolute percentage error (MAPE) of 1.04 × (Formula presented.) pA and 0.01%, respectively. The solid–ground electrode interface reported an error of 8.99 × (Formula presented.) pA and MAPE of 0.04%, showing strong agreement with simulation data. Expressions for time to steady state had a test error of approximately 110 h with MAPE of around 3%. Steady-state gas conductivity expression achieved an absolute error of 0.55 log(S/m) and MAPE of 1%. An interpretable equation was created with SINDy to model the time evolution of surface charge density, achieving a root mean squared error of 1.12 nC/m2/s across time-series data. These results demonstrate the capability of SR and SINDy to provide interpretable and computationally efficient alternatives to time-consuming numerical simulations of HVDC systems under radiation conditions. While the model provides useful insights, performance and practical applications of the expressions can improve with more diverse datasets, which might include experimental data in the future.