Abstract:

A new approach for the robust control of uncertain affined nonlinear systems is presented.Based on the certain part of the plant's model identified off line,neural networks are used in identifying the uncertainty on line.Then the robust adaptive control is realized by applying feedback linearizing with the neural networks model and the robustness of the control system is enhanced by sliding model control.Finally,the approach is applied to a collective pitch angle channel for a simplified nonlinear helicopter aerodynamic model with input unmodeled dynamics.Simulation results demonstrate the validity of the approach.

Key words: nonlinear control, uncertainty system, neural network, sliding model control