Combined inverse system method and neural network for designing nonlinear excitation control law

In this paper, an inverse system method (ISM), which is a simple exact linearization method for nonlinear system design, has been employed to design a nonlinear excitation control law of synchronous generator, and neural network is proposed for the controller to provide desired controller output. The main motivation is to exploit generalization capabilities of neural networks to interpolate between training data, and thus to deal with system parametric uncertainties caused by a large sudden fault. Simulation results show that transient stability of the perturbed power system can be improved.