Development of omni-directional correlation functions for nonlinear model validation

摘要: In the present study a set of first order correlation functions are proposed to examine quality wide class identified nonlinear models. The functions, defined as omni-directional integrated into two concise tests provide more effective auto and cross model error diagnosis than other approaches from higher functions. mechanisms novel validity proved in theory demonstrated with numerical analyses. Two simulated case studies, situation incorrectly detected structure estimated parameters, presented illustrate diagnostic power new methodology.