Optimal identification discrete systems based on statistical linearization

Some theoretical and applied aspects for optimal parametric estimation of the stochastic nonlinear discrete systems based on statistical linearization are considered for the first time. Original results are obtained in the case that the parameters of mathematical models to be estimated appear in the state and control equations, as well as the initial condition and the covariance matrices of the dynamic noise and measurement errors. An example of optimal parameter estimation for one model structure is shown.