Direct neural adaptive control applied to synchronous generator

This paper investigates the application of neural networks to control a synchronous generator based on a direct adaptive control scheme. Use of a neural network to model the dynamic system is avoided by making use of the sign of the Jacobian of the plant. This will substantially reduce the complexity and the computation time of the control algorithm. The controller is trained online using the backpropagation algorithm which gives an adaptive attribute to the controller. Simulation results are presented to complement the theoretical discussion.