Fault diagnosis in electrical power systems using artificial neural networks

Summary form only given. In this work, an ANN-based methodology is proposed for fault location in electrical power systems. A local strategy is adopted, where different ANN classifiers are constructed, each of them being responsible for detecting faulted power system components in a restricted area. The ANNs are able to produce a diagnosis, even in difficult situations, such as the presence of noisy data or protection system failures. Tests are performed using a test system and a real Brazilian power system to illustrate the performance of the proposed algorithm.