Filtering Identification.Part J:Filtering-Based Auxiliary Model Hierarchical Generalized Extended Parameter Identification for Multivariable Box-Jenkins Systems
For multivariable output-error autoregressive moving average(M-OEARMA)models,which are also called multivariable Box-Jenkins models,this paper investigates and proposes filtered auxiliary model hierarchical generalized extended stochastic gradient identi-fication methods,filtered auxiliary model hierarchical multi-innovation generalized extended stochastic gradient identification methods,filtered auxiliary model hierarchical generalized extended recursive gradient identification methods,filtered auxiliary model hierarchical multi-innovation generalized extended recursive gradient identification methods,filtered aux-iliary model hierarchical generalized extended least squares identification methods,and fil-tered auxiliary model hierarchical multi-innovation generalized extended least squares identi-fication methods by using the filtering identification idea and the auxiliary identification idea from available input-output data.These filtered auxiliary model hierarchical generalized ex-tended identification methods can be extended to other linear and nonlinear multivariable sto-chastic systems with colored noises.
parameter estimationrecursive identificationauxiliary model identificationmulti-innovation identificationhierarchical identificationfiltering identificationleast squaresmultivariable system
万方数据
维普
