Breakdown voltage modeling of Manila Paper in the presence of cavities under AC and DC conditions by Adaptive Fuzzy Logic Technique

Gaseous cavities within the insulating materials during manufacturing are potential sources of electrical trees which can lead to continuous degradation and breakdown of materials due to Partial Discharges (PD). To determine the suitability of use and to acquire the data for the dimensioning of electrical insulation systems breakdown voltage of insulators should be determined. In this paper, an Adaptive Sugeno Fuzzy Logic (ASFL) method is used to model breakdown voltages of solid insulating samples of Manila Paper due to PD based on experimental data generated in the laboratory. Two models are proposed with triangular shape of membership functions for the ASFL under both dc and ac voltage conditions. The cavities are created artificially with different dimensions. Low value of mean absolute errors of the estimated breakdown voltage of the test data shows the effectiveness of such models.