Electrostatic Field Feature Selection Technique for Breakdown Voltage Prediction of Sphere Gaps Using Support Vector Regression
Zhibin Qiu, Louxing Zhang, Yan Liu, Jianben Liu, Huasheng Hou, Xiongjian Zhu
Abstract
This article proposes a methodology for air gap breakdown voltage (BV) prediction based on support vector regression (SVR), taking various features extracted from the electrostatic field calculation results as input variables. The genetic algorithm (GA) is applied for feature selection to improve the performance of the SVR model. A case study on sphere gap BV prediction is reported to demonstrate the validity of the proposed technique. This study provides a reference for dielectric strength prediction by artificial intelligence algorithms, thus to guide the optimal design of air insulation structures.
Topics & Concepts
Support vector machineFeature selectionComputer scienceSelection (genetic algorithm)Field (mathematics)Artificial intelligenceVoltageAir gap (plumbing)Regression analysisGenetic algorithmRegressionMachine learningMathematicsPhysicsMaterials scienceStatisticsComposite materialQuantum mechanicsPure mathematicsHigh voltage insulation and dielectric phenomenaAerosol Filtration and Electrostatic PrecipitationPower Transformer Diagnostics and Insulation