Nonlinear model validation using novel correlation tests

Model validation is the final step of system identification, which is to check the goodness of the estimated models. In the present study, novel first order correlation tests named omni-directional auto-correlation functions and omni-directional cross-correlation functions are proposed to check the validity of a wide class of nonlinear dynamic models. Compared to the other first order and higher order correlation tests based approaches, the new methodology enhances the power of nonlinear correlation detection and provides a more comprehensive and effective solution. The efficiency and effectiveness of the new methodology are demonstrated through simulation studies and comparison with the other correlation tests based approaches.