Diagnosing failed distribution transformers using neural networks

An Artificial Neural Networks (ANN) system was developed for distribution t ransformer's failure diagnosis. The diagnosis was based on the latest stand ards and expert experiences in this field. The ANN was trained utilizing Ba ck Propagation Algorithm using a real (out of the field) data obtained from utilities distribution networks transformer's failures. The ANN consists o f six individual ANN according to six important factors used to give certai n outputs. These factors are: the age of the transform, the weather conditi on, if there are any damaged bushings?, if there are any damaged casing or enclosure?, if there is oil leakage?, and if there are any faults in the wi ndings?. The six ANNs are combined in one ANN to give all the outputs of th e individual six ANNs. The developed ANN can be used to give recommended co mplete diagnosis for working transformers to avoid possible failures depend ing on their operating conditions. Good diagnosis accuracy is obtained. wit h the proposed approach applied and with the analysis of the attainable res ults.