A neural network approach to fault diagnosis for power systems

An approach to fault diagnosis for large scale power systems is presented, based on hierarchical distributed neural networks. Several independent neural networks in the same level are used to diagnose the faults within a substation. One higher level neural network which makes use of some outputs from lower level as its inputs is used to diagnose the faults in transmission lines. A combined gradient learning algorithm with advantages of both gradient and conjugate gradient algorithms is employed for training the neural networks. This learning algorithm converges faster than the error back propagation algorithm. Comparisons between the proposed approach and the single neural network approach are made for a model substation and a model power system. Simulation results show that this approach is very encouraging.<>