Prediction Health Index Using Machine Learning and Its Correlation with Transformer Age on Historical Data

The transformer is a vital of equipment in the power transmission and distribution system. Optimum use of transformers can increase the economic value and reliability of electricity supply. Power apparatus is expected to operate close to or exceed the design life of the transformer. Health index (HI) is used to provide a general assessment of the condition of the transformer. In determining the health index, it can be done using conventional methods or non-conventional methods. According to the IEEE loading guide lines, the age of the transformer ranges from 25-30 years. The “effective age” of the transformer can be determined by the probability of failure of insulation system or which can be based on HI. In this study, transformer oil testing was used to determine the health index and calculate the age of the transformer. The parameters used are BDV, Water, Acid, IFT, DGA, and 2-furaldhyde. In this study, 79 transformer oil sample data were used which had known health indexes from field assessments. The health index method uses calculation, ANN, and naïve Bayes methods. Parameters affecting the health index BDV (r = 0.57), water (r = -0.55), 2FAL (r = -0.58), and acetylene (r = - 0.25). Parameters that affect the life of the transformer are BDV (r = 0.45), water (r = -0.66), Acid (r = -0.53), IFT (r = - 0.49), 2FAL (r = - 0.58), and CO2 (r = -0.40). Parameters BDV, water, and 2 FAL have a significant correlation in determining the health index and predicting the life of the transformer. Parameters 2FAL and water are related to chemical reactions in the insulation system which result in aging of the transformer. With the deteriorating condition of the transformer (HI), it further increases the possibility of initial disturbance to failure of the transformer.