“…In recent years, the data-driven models based on artificial intelligence algorithms provide a new possibility to realize dielectric strength prediction, which is an alternative way except for the physical models and empirical formulas. Some artificial intelligence or machine learning algorithms, such as artificial neural networks (ANN) [17][18][19][20], support vector machine (SVM) [21][22][23][24][25], fuzzy logic [26,27], Gaussian process regression (GPR) [28], least squares regression (LSR) [29], and extremely randomized trees [30], etc., have been applied for breakdown voltage prediction of air gaps, transformer oils, and solid dielectrics like insulation paper and nanocomposites. These data-driven models mainly focus on the mathematical correlations between the dielectric strength and various influencing factors, and do not directly consider the discharge evolution process full of randomness and uncertainty, which is not restricted by the complex and unclear physical process.…”