Auxiliary model-based maximum likelihood multi-innovation recursive least squares identification for multiple-input multiple-output systems

Abstract

The aim of this paper is to propose novel identification methods for multiple-input multiple-output systems. Through decomposing a system into subsystems, the system identification model is derived. Based on the obtained sub-model, an auxiliary model-based maximum likelihood recursive least squares algorithm is derived for parameter estimation. For further enhancing the estimation accuracy, the auxiliary model-based maximum likelihood multi-innovation recursive least squares (AM-ML-MIRLS) algorithm is proposed based on the proposed algorithm. Simulation results test the proposed algorithms are all effective, and prove that the proposed AM-ML-MIRLS algorithm has the superior performances in capturing the dynamic properties of the system.