Evaluation of used and repaired power transformers using neural networks

Power Transformers are one of the most expensive and the most utilized equipments in transmission and distribution power systems. The application of used and repaired power transformers by industrial consumers is common these days. To insure an acceptable and economic performance of such power transformers, there is a need for evaluation and verification of these equipments. Such decision-makings always call for experts. It is shown that artificial neural networks yield satisfactory results in such cases. In this paper, the authors present a new method based on neural networks with radial basis functions to evaluate and verify power transformers based on the data obtained from practical tests.