Dynamic neural network-based robust observers for second-order uncertain nonlinear systems

A dynamic neural network (DNN) based robust observer for second-order uncertain nonlinear systems is developed. The observer structure consists of a DNN to estimate the system dynamics on-line, a dynamic filter to estimate the unmeasurable state and a sliding mode feedback term to account for modeling errors and exogenous disturbances. The observed states are proven to asymptotically converge to the system states though Lyapunov-based stability analysis.