On nonparametric modeling spinning systems with delay

This article is devoted to the construction of a new class of models under incomplete information. In this article we will discuss multidimensional inertial-free objects, where the output vector components are stochastically dependent, but the nature of this dependence is not known to us. Constructing a model of a multidimensional inertial-free object, when the input and output vectors are not linear, leads to the necessity to solve the problems of systems of implicit func- tions. It should also be noted that the form of these functions is unknown up to parameters. So there is a need to use T-processes, when predicting output variables is carried out by known input. Thus there is a system of nonlinear im- plicit equations which form is unknown at the initial stage of the statement of the identification problem, but it is only known that this or that component of the output depends on other variables that determines the state of the object. Proceeding from the above, a nontrivial situation arises that solves a system of implicit nonlinear equations under the conditions when the equations themselves are not in the usual sense. Consequently, the model of the object can not be constructed using the existing theory of identification because of the lack of a priori information. Therefore, the solu- tion of this system can be represented in the form of some successive algorithmic chain of the T-model. The main goal of this paper is to solve the identification problem for multidimensional inertia-free objects with de- lay, in the presence of T-processes, i.e. construction of T-models under conditions of nonparametric uncertainty. In this case, to predict the output variables by the known input, it becomes necessary to use a step-by-step solution of the prob- lem under consideration. In the article some calculations of the T-process simulation will be presented, which showed the high efficiency of the proposed technology of forecasting the values of the output variables by the known input.