Application of neural networks for power generator and excitation system modeling

The importance of models of power systems has long been recognized. A set of accurate models can be obtained through field tests by means of modern identification methods. In this paper, a method of establishing power system models with the artificial neural networks (ANN) is presented. Both power generators using fast backpropagation neural networks (FBP) and excitation system model using a radial basis function network (RBFN) are developed. The simulation results of field and laboratory tests demonstrate that the application of developed ANN approach to power generator and excitation system modeling with fast training procedure and high precision is promising