Title :
A new model with neural network structure for nonlinear identification
Author :
Ni, Xianfeng ; Verbruggen, H.B. ; Krijgsman, A.J.
Author_Institution :
Control Lab., Delft Univ. of Technol., Netherlands
Abstract :
In this paper, a new model for nonlinear system identification is presented. It consists of two parts: a linear part and a static nonlinear output part. The linear part is a linear combination of the model´s outputs, and the static nonlinear function maps the output of the linear part to the model´s output. This model can be applied to represent a relatively large class of nonlinear dynamic systems with fading memory. Nonlinear system identification with this new model is applied to two simulation examples of a discrete-time system and a complicated missile dynamics to demonstrate the performance and efficiency of the proposed method
Keywords :
backpropagation; discrete time systems; feedforward neural nets; identification; missiles; neural net architecture; nonlinear dynamical systems; discrete-time system; dynamic backpropagation; fading memory; identification; missile dynamics; multilayer neural networks; neural network structure; nonlinear dynamic systems; static nonlinear output; Control system synthesis; Electronic mail; Fading; Laboratories; Missiles; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Vectors;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549243
