Variable structure neural network based direct adaptive robust control of uncertain systems

Direct adaptive robust state feedback and output feedback controllers are proposed for the output tracking control of a class of uncertain systems with disturbance. The proposed controllers employ self-organizing raised-cosine radial basis function networks, which are capable of determining their structures dynamically, to approximate unknown system dynamics. Radial basis functions of the network can be added or removed on-line in order to ensure the desired tracking accuracy and the computational efficiency simultaneously. The closed-loop systems are characterized by the guaranteed transient response and the final tracking accuracy. The performance of the proposed output feedback controller is illustrated by numerical simulations.