Disturbance observer based dead-beat control of multi-input systems with unknown disturbances and bounded inputs using discrete-time higher order sliding mode

This article proposes a new robust dead-beat controller for multivariable systems using multirate sampled data. Applying a discrete-time higher order sliding mode control approach, the proposed dead-beat controller design uses the state-space nominal model (model without disturbances) of the system and its controllability indices to compute the state feedback matrix. The obtained control annihilates the system state in a minimal number of sampling periods. For example, a heuristic procedure for selecting a sampling time is considered in order to keep maximal amplitudes of control inputs within the allowable limits. Since the dead-beat control has poor robustness, a new discrete-time supertwisting disturbance observer is used to suppressed disturbance effects. Stability analysis of the proposed observer has shown that it is suitable for Lipschitz type of disturbances. The sampling period of the disturbance observer is generally smaller than the control sampling period. Properties of the proposed control system are demonstrated in simulation examples.