On-line multivariable identification and control of chemical processes using canonical variate analysis

In this paper an online identification and control strategy is developed for chemical processes. The procedure used for system identification is canonical variate analysis, a method that operates on input-output data sequences batch-wise to provide an optimized state-space model; the resulting models are then used in a multivariable predictive control procedure to yield excellent overall closed-loop results. The resulting adaptive control procedure is demonstrated to have excellent properties for control of a continuous stirred tank reactor with inverse dynamics, delays and nonlinearities.