Deadbeat Predictive Controllers

Several new computational algorithms are presented to compute the deadbeat predictive control law that brings the output response to rest after a finite number of time steps. The first algorithm makes use of a multi-step-ahead output prediction to compute the control law without explicitly calculating the controllability matrix. The system identification must be performed first and then the predictive control law is designed. The second algorithm uses the input and output data directly to compute the feedback law. It combines the system identification and the predictive control law into one formulation. The third algorithm uses an observable-canonical form realization to design the predictive controller. The relationship between all three algorithms is established through the use of the state-space representation. All algorithms are applicable to multi-input multi-output systems with disturbance inputs. In addition to the feedback terms, feedforward terms may also be added for disturba..