Disturbance decoupling of uncertain nonlinear delayed systems

The disturbance decoupling problem is investigated for a class of uncertain delayed nonlinear systems, and a sufficient and necessary condition, under which the output is completely decoupled from the disturbance, is acquired. When the disturbance is measurable, a variable structure decoupling control design scheme is proposed based on the neural network. The scheme utilizes the ability that a neural network can arbitrarily approach a nonlinear function, then introduces a compensation part for the disturbance in the control. Thus the systems can keep the stability and good performance even when the disturbance doesn't satisfy the decoupling condition.Effectiveness of the proposed scheme is tested by an illustrative example.