Perpustakaan Digital ITB

Transformer have an insulation system to keep it performance during operation. The ageing of the oil-impregnated cellulose insulation and the associated loss of mechanical strength is one of the important factors that limit the life expectancy of a transformer. To determine the condition of oil-impregnated cellulose insulation, Degree of Polymerization (DP) parameter is used. The conventional method to measure the value of DP interfere the transformer operation. Fuzzy Inference System (FIS) and Adaptive Neuro-Fuzzy Inference System (ANFIS) has been developed to predict the DP value by the dielectric characteristic and dissolved gas parameters (Acidity, Interfacial Tension, CO, CO2, Breakdown Voltage and Water). ANFIS has an advantage to combine the concept of FIS and Artificial Neural Network (ANN) for improving the performance. Estimation result has observed and evaluated so that FIS and ANFIS is suitable to estimate insulation condition on field operating transformer.