Open AccessStability Analysis of Neural Networks‐Based System Identification
Author(s) -
Talel Korkobi,
Mohamed Djemel,
Mohamed Chtourou
Publication year - 2008
Publication title -
modelling and simulation in engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.264
H-Index - 20
eISSN - 1687-5591
pISSN - 1687-5605
DOI - 10.1155/2008/343940
Subject(s) - backpropagation , stability (learning theory) , artificial neural network , convergence (economics) , computer science , lyapunov stability , nonlinear system , rate of convergence , learning rule , identification (biology) , process (computing) , control theory (sociology) , algorithm , artificial intelligence , machine learning , key (lock) , physics , botany , control (management) , computer security , quantum mechanics , economics , biology , economic growth , operating system
This paper treats some problems related to nonlinear systems identification. A stability analysis neural network model for identifying nonlinear dynamic systems is presented. A constrained adaptive stable backpropagation updating law is presented and used in the proposed identification approach. The proposed backpropagation training algorithm is modified to obtain an adaptive learning rate guarantying convergence stability. The proposed learning rule is the backpropagation algorithm under the condition that the learning rate belongs to a specified range defining the stability domain. Satisfying such condition, unstable phenomena during the learning process are avoided. A Lyapunov analysis leads to the computation of the expression of a convenient adaptive learning rate verifying the convergence stability criteria. Finally, the elaborated training algorithm is applied in several simulations. The results confirm the effectiveness of the CSBP algorithm
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom