Identification of the level of contamination and degradation of oil by artificial neural networks

This work presents the development of a new methodology through artificial neural networks to evaluate the level of contamination of the mineral oil used in transformers. This approach also concentrates on estimating the relative aging degree of transformers in relation to the main parameters that represent the degradation of the paper and insulating mineral oil. The results obtained in the simulations proved that the developed technique can be used as an alternative tool to become more suitable planning of the maintenance, allowing the decrease of costs involved in these operations