Artificial neural networks (ANNs) have large input-error tolerance ranges a
nd can be used as classifiers. Utilizing this property, a neural network-ba
sed detector, which identifies the faulty line directly by taking current a
nd voltage patterns as feature vectors, has been designed. The quality of c
lassification is not dependent on the transmission model, but rather on the
net topology, training set, and the choice of learning law. A feed-forward
multilayer perceptron, using the Back-Propagation. Learning Algorithm, has
been used to realize an optimal classifier. The classification quality, by
simulating certain faults on the lines, has demonstrated the capability of
the proposed approach for distribution pourer system protection.