Title :
Strongly consistent recursive regression estimation under depended observations
Author :
Chernyshov, K.R.
Author_Institution :
Inst. of Control Sci., Moscow, Russia
Abstract :
The paper is focused on establishing strong consistency of recursive estimates of nonlinear characteristics of dynamic systems. To describe the shape of the nonlinearities, the regression function kernel type estimates are used. Within the approach presented, a feature of the technique is considering a case of mutually dependent observations. Simultaneously, only mild and easy verified assumptions with respect to the system´s input and output processes, as well as to the external disturbances, are involved
Keywords :
identification; nonlinear systems; recursive estimation; depended observations; nonlinear characteristics; nonlinear dynamic system model; nonlinearity shape; recursive regression estimation; regression function kernel type estimates; strong consistency; system estimation; system identification; Control systems; Kernel; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Random processes; Recursive estimation; Shape; Stochastic systems; System identification;
Conference_Titel :
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
Conference_Location :
Geneva
Print_ISBN :
0-7803-5482-6
DOI :
10.1109/ISCAS.2000.857381
