The Identification Reserch a Kind of Colored Noises Systems
Zhang Yon · Science Technology and Engineering · 2010
ARARX models are an important kind of models of systems with colored noises. The stochastic systems with colored noises as ARARX models(CARAR models) is regarded. The basic idea is to approximate the noise model by using (FIR) models,thus obtaining a special CARMA/ARMAX model. The model can be identified by the extended least squares,comparing with the recursive generalized least squares with data filtered,the FIR-RELS algorithm is simple in principle,is more convenient for computer operation. Simulation results indicate that the system identification satisfies the precision demands if FIR models have high orders.