Excitation control in a synchronous machine via an artificial neural network

This paper presents an application of artificial neural networks (ANN) as a controller for a synchronous machine excitation system. A hierarchical architecture of an ANN is adopted for the controller design, which is used for data mapping and control respectively, based on the backpropagation algorithm (BPA). The controller´s operation does not require a reference model or an inverse system model and it can produce more acceptable control signals than are obtained by using plant errors during its training. The input-output mapping of synchronous machines using ANN´s has been investigated and the controller has been implemented on a complex synchronous machine model. The simulation results are given, showing satisfactory control performance and illustrate the potential of the ANN controller as useful for practical purposes