This work presents the application of a neuro-fuzzy model for alarm processing and fault location in power systems. Different techniques to establish the fuzzy relations among alarm patterns and fault occurrences in power systems are examined. Fuzzy relations are constructed and form a database that is employed to train artificial neural networks. The artificial neural networks have alarm patterns as inputs and each output neuron is responsible for estimating the degree of membership of a specific system component into the class of faulted components. Tests are performed with a 7-bus test system and with part of a real brazilian system.
Power system protection; Alarm processing; Fuzzy logic; Artificial neural networks
