A matrix fraction description-based identification algorithm for MIMO ARMAX models 

Mohamed Akroum[1], Kamel Hariche.

  Department of Electrical and Electronic Engineering, M'hamed Bougara University, 35000 Boumerdes, Algeria.
[1] Corresponding author; E-mail: m_akroum@yahoo.com
In this paper, the recently introduced MIMO linear multi stage autoregressive moving average with exogenous excitation (LMS-ARMAX) algorithm is simplified and reformulated to be useful in control applications. The algorithm solves the identification problem by performing a sequence of filtering, linear least squares and deconvolution operations on the system input-output data instead of the usual nonlinear minimization techniques applied to such ARMAX models. The algorithm is applied to data gathered from a simulated quad

To read the full article,
please log in:
If you haven't registered already,
you can do so for free:
Copyright 2000-2011 Professor F.R. Hall & Dr I. Oraifige, University of Wolverhampton.
close this window