Adaptive Input Design for Identification of Output Error Model with Constrained Output

Abstract

This paper considers the identification of output error (OE) model, for the case of constrained output variance. The constraint plays a very important role in the process industry, in the reduction of degradation of product quality. In this paper, it is shown, in the form of theorem, that the optimal input signal, with constrained output, is achieved by a minimum variance controller together with stochastic reference. The key problem is that the optimal input depends on the system parameters to be identified. In order to overcome this problem, it is the proposed two-stage adaptive procedure a) obtaining an initial model using PRBS as input signal b) application of adaptive minimum variance controller together with the stochastic variable reference, in order to generate input signals for system identification Theoretical results are illustrated by simulations.