Modeling of Breakdown voltage of Solid Insulating Materials Using Soft Computing Techniques

Abstract

The voids or cavities within the solid insulating material during manufacturing are potential sources of electrical trees which can lead to continuous degradation and breakdown of insulating material due to Partial Discharge (PD). To determine the suitability of use and acquire the data for the dimensioning of electrical insulation systems breakdown voltage of insulator should be determined. A major field of Artificial Neural Networks (ANN) and Least Square Support Vector Machine (LS-SVM) application is function estimation due to its useful features, they are, non-linearity and adaptively. In this project, the breakdown voltage due to PD in cavities for five insulating materials under AC conditions has been predicted as a function of different input parameters, such as, the insulating sample thickness ‘t,’ the thickness of the void ‘t1’ diameter of the void ‘d’ and relative permittivity of materials by using two different models. The requisite training data are obtained from experimental studies performed on a Cylinder-Plane Electrode system. Different dimensioned voids are artificially created.. On completion of training, it is found that the ANN and LS-SVM models are capable of predicting the breakdown voltage Vb = f (t, t1, d, ) very efficiently and with a small value of Mean Absolute Error. The system has been predicted using MATLAB.