Title :
Parameter Identification for Input Nonlinear Output-Error Systems Using the Unknown Variable Estimation
Author :
Shi, Yang ; Ding, Feng
Abstract :
The information vector in the identification model obtained by parameterizing input nonlinear systems contains unknown variables - the noise-free (true) outputs of the system. This is the difficulty of identification. This paper develops a stochastic gradient based identification algorithm by replacing the unknown variable with its estimate. The simulation results show the effectiveness of the proposed algorithms.
Keywords :
gradient methods; nonlinear systems; parameter estimation; stochastic processes; input nonlinear output-error systems; noise-free outputs; parameter identification; stochastic gradient based identification; unknown variable estimation; Additive noise; Algorithm design and analysis; Convergence; Iterative algorithms; Iterative methods; Nonlinear control systems; Nonlinear systems; Parameter estimation; Stochastic resonance; Symmetric matrices;
Conference_Titel :
American Control Conference, 2007. ACC '07
Conference_Location :
New York, NY
Print_ISBN :
1-4244-0988-8
Electronic_ISBN :
0743-1619
DOI :
10.1109/ACC.2007.4282542
