Parametric identification of discrete-time SISO systems

Abstract

The paper presents a method for the parametric identification of linear time-invariant discrete systems. The input and output data sequences of the system are initially transformed into information-bearing sequences of much lower order through the use of discrete Laguerre series. The parameter identification problem then becomes one of finding the solution to an overdetermined set of equations. Data transformation into the Laguerre spectrum is achieved through a fast and efficient computational algorithm which inherently possesses noise-reduction properties.