Identification of continuous-time Box-Jenkins models with arbitrary time-delay

Abstract

An extended instrumental variable algorithm is proposed for identification of systems with arbitrary time delays. Our algorithm can handle time-delays which may be non-integer multiple of the sampling interval. It is further shown that the proposed approach can achieve the asymptotic Cramér-Rao bound by properly tuning the user's choices. In simulations the algorithm gives unbiased parameter estimates with good statistical accuracy.