Título: Identificação do Sistema Dinâmico Caótico de Chua Usando uma Rede Neural Polinomial
Autores: Guerra, Fábio; Coelho, Leandro dos Santos
Resumo: In this paper, the Group Method of Data Handling(GMDH)-type neural network for chaotic dynamic systems identification is proposed. The GMDH algorithm can be considered as a structural identification technique or a feedforward polynomial neural network with a growing structure during the training process. This polynomial neural network uses Adalines with nonlinear preprocessors. The training of this neural network is realized by learning rule application of Widrow-Hoff. The neural network implementation is evaluate for identification of Chua chaotic system. An experimental study of nonlinear identification of Chua system shows successful results for the proposed approach.
Código DOI: 10.21528/CBRN2003-058
Artigo em PDF: 6CBRN_058.PDF
Arquivo BibTex: 6CBRN_058.bib