Title :
Neural network state space identification model
Author :
Wang, Kejun ; Wang, Kecheng ; Li, Guobin
Author_Institution :
Dept. of Autom. Control, Harbin Eng. Univ., China
Abstract :
Proposes a novel special neural network state space identification model for system identification (NNSSIM). This novel neural network model is composed of the state equation and the output equation of the system. The neurons and weights in the novel neural network have a clear physical significance. A dynamic backpropagation training algorithm is developed to train NNSSIM. The convergence of the algorithm is analyzed using the Lyapunov stability theorem and the conditions of convergence are given
Keywords :
Lyapunov methods; backpropagation; convergence; discrete time systems; identification; neural nets; nonlinear dynamical systems; state-space methods; Lyapunov stability theorem; convergence; dynamic backpropagation training algorithm; neural network state space identification model; output equation; state equation; system identification; Algorithm design and analysis; Backpropagation algorithms; Convergence; Equations; Heuristic algorithms; Lyapunov method; Neural networks; Neurons; State-space methods; System identification;
Conference_Titel :
Systems, Man, and Cybernetics, 1996., IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-3280-6
DOI :
10.1109/ICSMC.1996.571313
