Title :
Nonparametric identification of dynamic nonlinear systems
Author :
Krzyzak, Adam ; Sasiadek, Jerzy Z.
Author_Institution :
Dept. of Comput. Sci., Concordia Univ., Montreal, Que., Canada
Abstract :
Nonlinear dynamic block oriented systems of Hammerstein and Wiener type are identified. Hammerstein system consists of a memoryless nonlinearity followed by a dynamic, linear system, while Wiener system is a cascade of a linear dynamic system connected to a memoryless nonlinearity. The class of nonlinearities considered is large and nonparametric. Identification algorithms based on input-output observations are proposed for both systems and their convergence and rates are studied. Simulation results are provided and possible applications of block oriented systems in robotics are discussed
Keywords :
cascade systems; convergence; nonlinear dynamical systems; observers; Hammerstein system; I/O observations; Wiener system; block oriented systems; cascade system; dynamic linear system; input-output observations; memoryless nonlinearity; nonlinear dynamic block oriented systems; nonparametric identification; robotics; Adaptive control; Aerodynamics; Computer science; Convergence; Kernel; Linear systems; Nonlinear dynamical systems; Nonlinear systems; Robots; System identification;
Conference_Titel :
Decision and Control, 1997., Proceedings of the 36th IEEE Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4187-2
DOI :
10.1109/CDC.1997.657907
