Katulev Alexander Nikolaevich, M. F. Malevinsky, G. M. Solomakha, “Multidimensional Statistically Square Filter For Parameter Estimation Of Nonlinear Systems”, Vestnik TVGU. Ser. Prikl. Matem. [Herald of Tver State University. Ser. Appl. Math.], 2013, Issue 4,Pages <nobr>47

Probabilistic Possibilistic Models

Multidimensional Statistically Square Filter For Parameter Estimation Of Nonlinear Systems

Katulev Alexander Nikolaevich^a, M. F. Malevinsky^b, G. M. Solomakha^b

^a Research Center for Air Defense (Tver), the 4th Central Scientific Research Institute of the Ministry of Defense of the Russian Federation.
^b Tver State University

Abstract: Discrete statistically square recurrent filter for estimation of current state for dynamic system with continuous nondifferentiable or uncontinuous nonlinearities is offered. The filter is a development of theoretical statements for statistical approximations of nonlinear dynamic systems which provides in practice quick convergency and high precision of estimation for trajectory parameters of movement for maneuverable objects.

Keywords: Nonlinear, recurrent filter, square-law, stochastic approximation, criterion, estimation, errors, modeling.

UDC: 681.5.015

Received: 10.12.2013
Revised: 15.12.2013