A robust whiteness test for the identification of discrete-time linear models: Use of orthonormal transfer functions

A novel whiteness test of residuals is proposed, which makes use generalized bases orthonormal transfer functions. It can be viewed as a robustified version the classical in sense that it reduces risk type II errors, by introducing frequency weighting assessment flatness residual power spectrum density. This weighting, depends on basis poles, employed for validation reduced order models, when density evaluated over limited band.