Active parametric identification of stochastic linear discrete systems in the frequency domain

摘要

Under consideration are some theoretical and applied aspects of the active identification of the multidimensional stochastic linear discrete systems in the frequency domain which are described by models in the state space. Original results are obtained in the case that the parameters of mathematical models to be estimated appear in various combinations in the state and control matrices, as well as in the perturbation matrix and the covariation matrices of the dynamic noise and measurement errors. By an example of a system controlling a boring machine, the efficiency and sensibility is shown of applying the active identification procedure.