Robust asymptotic stabilization of uncertain nonlinear systems using Artificial Neural Networks with application to power systems

The problem of robust stabilization for uncertain nonlinear systems is considered in this paper. The controlled systems are not restricted to the strict feedback form any more. The robust stabilization controller is designed based on backstepping approach with using artificial neural networks (ANN) to account for the uncertain terms. A new adaptive algorithm is proposed to update the weights of ANN such that all signals in the closed-loop systems are bounded and the states are convergent asymptotically to the equilibrium through the proposed controller. A speed governor is designed for single-machine infinite-bus system based on the design scheme proposed in this paper and the simulation results illustrate the utility of the proposed scheme.