An artificial neural network based trouble call analysis

The use of trouble call information for handling service interruption events that exist between primary feeders and customers is discussed in this paper. Artificial neural networks are used for fast pattern recognition and classification of trouble calls such that the time and effort required for service restoration can be reduced. A backpropagation network is chosen as the neural network model. This proposed trouble call analysis system is embedded in an integrated automated mapping, facilities management and geographic information system environment.>