Advanced Method of Parametric Identification of Tolerance Estimations of the Interval Vector of Discrete Dynamic Models Parameters

Abstract

The problem of parametric identification of interval discrete dynamic models is considered in the article. It is shown that to solve this problem it is necessary to solve an interval system of nonlinear algebraic equations, the solutions area of which is nonconvex and incoherent. An improved method for parametric identification of interval estimates of discrete dynamic models' parameters is proposed. It in contrast to the existing one, maximizes the volume of the detected subarea of solutions of the interval system of nonlinear algebraic equations in the parameter space. Carried out the comparison of the results of application of the proposed and existing method for identification of interval estimates of parameters of model.