Use of a mixed structure consisting of a radial basis function (RBF) network and pole-shifting feedback controller for power system stabilizer application is presented in this paper. The RBF network is used to identify the time-varying parameters of the power system. The RBF has a simple structure with a nonlinear hidden layer which constructs local approximations to nonlinear input-output mapping and a linear output layer. The network is capable of fast learning and represents a nonlinear autoregressive moving average model with exogeneous inputs (NARMAX). The NARMAX model is transformed into a linear ARMA model every sampling period and the pole-shift controller is used to calculate the control signal. This process of linearizing a nonlinear system is important because of the widespread industrial acceptance of linear feedback controllers, availability of theoretical and practical results about robustness, and closed-loop stability. Simulation studies carried out on a single-machine infinite bus power system verify the effectiveness of the above approach.