On-line order estimation and parameter identification for linear stochastic feedback control systems (CARMA model)

This paper presents a new recursive estimate method for orders and coefficients of linear stochastic feedback control systems (CARMA model) under the assumption that the upper bounds of system orders are known. The strong consistency of the estimates for orders and coefficients is proved and the convergence rate of coefficient estimates to their true values is also obtained. The estimate algorithm is applied to adaptive tracking of the systems with unknown orders and unknown coefficients. The resulting closed-loop systems are then globally stable and the tracking sample mean square error is minimized as well. Simultaneously, the estimates of the adaptive tracking for orders and coefficients are also strongly consistent. The simulation results given here show that the new developed algorithms of both system identification and adaptive tracking are effective. (C) 2002 Elsevier Science Ltd. All rights reserved.