Nonparametric methods for the identification of linear parameter varying systems

In this paper, we consider the identification of linear parameter varying (LPV) systems. By taking a nonparametric approach, we do not impose a priori parameterizations on the model structure, nor is it assumed that a natural parameterization is suggested from an analytical understanding of the underlying process. In this case, it is shown that the LPV identification problem reduces to a closely related problem in nonlinear system identification. By referring to previous results, we offer a dispersion-based cost criterion and a sufficient condition on the exogenous parameter under which asymptotic convergence of the identified LPV system is assured almost surely.