Input and output constrained adaptive generalized predictive control for diagonal CARIMA model

An improved constrained mulitivariable generalized predictive control algorithm (ICMGPC) for CARIMA (controlled autoregressive integrated moving average) model having diagonal matrics A and C was developed to simplify the design and implementation of ICMGPC when considering input and output constraints. The identification and model output predication problems of multivariable process with m inputs and n outputs are transformed into those of a series of subprocesses with m inputs and single output by utilizing the structure characteristic of the diagonal CARIMA model. The input and output constraints of the control system are also analyzed in detail. This method separates items depending upon model parameters from those depending upon input and output historical data in model output prediction, objective function and constraint condition, which simplifies the implementation of ICMGPC. Its validity is demonstrated by comparative experiment results obtained from a nonlinear liquid level equipment controlled by DCS.