Conditionally optimal iterative filters (Q1281020)

Conditionally optimal iterative filters are proposed. They are built up on the basis of the theory of conditionally optimal discrete filters (in the sence of Pugachev) intended for filtering random processes described by nonlinear difference equations. As in the calculations involved with the theory of conditionally optimal filtering, here all the calculations for finding the gains of iterative filters rely only on the use of a priori information on both the structure of the difference equations that determine the random processes and on a class of admissible filters. The calculations do not use the results of current observations and thus they can be performed beforehand in designing the filters. The filtering process can be carried out in real time. The theory of conditionally optimal filters allows to design filters of different structures, for example, filters of a dimension that is higher than the dimension of the initial system. In this case, the equations for the filters can be given in an equivalent form, but more efficiently with respect to the amount of computer time taken to implement the filters. An example is given.