A PMF-based subspace method for continuous-time model identification. Application to a multivariable winding process

This paper presents a methodology for system identification of continuous-t ime state-space models from finite sampled input-output signals. The estima tion problem of the consecutive time-derivatives and integrals of the input -output signals is considered. The appropriate frequency characteristcs of a linear filtering based on the Poisson moment functionals in regards to th e derivative or integral estimation problem is shown. The proposed method c ombines therefore the Poisson moment functionals technique with subspace ba sed state-space system identification methods. The developed algorithm is b ased on a generalized singular value decomposition to compensate the noise colouring caused by the linear prefiltering of the input-output data. Rules of thumb are presented to choose the design parameters and new regards to the selection of the Poisson filter cut-off frequency are introduced. Final ly, the proposed method is applied to a multivariable winding processes. Th e experimental results emphasize the applicability of the developed methodo logy.