Application of modified sigma-pi-linked neural network to dynamical system identification

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

3 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of the IEEE Conference on Control Applications
PublisherIEEE
Pages1729-1733
Volume3
Publication statusPublished - 1994

Publication series

Name
Volume3

Conference

TitleProceedings of the 1994 IEEE Conference on Control Applications. Part 3 (of 3)
CityGlasgow, UK
Period24 - 26 August 1994

Abstract

This paper describes the development of a self-feedback Sigma-Pi-linked(Σ-∏) Back-propagation neural network and its applications to dynamical system identification. A self-feedback path is added to each neuron to generate the recursive effect. Each neuron output is recursively related by current input and its preceding output. The introduction of this self-feedback path enables the network to exhibit a dynamic characteristic. Using this complex Σ - ∏-linked architecture, the developed network is capable of performing a system identification for a highly non-linear plant. In the last section of this paper, the function approximation property of this modified network is applied to system identification for different linear and non-linear dynamical systems. This paper also compares the modified network with the conventional Back-propagation neural network. Simulation results show that the function approximation property of the modified network is encouraging and can be successfully applied to nonlinear dynamical system identification.

Citation Format(s)

Application of modified sigma-pi-linked neural network to dynamical system identification. / Chow, T. W S; Fei, Gou; Yam, Y. F.

Proceedings of the IEEE Conference on Control Applications. Vol. 3 IEEE, 1994. p. 1729-1733.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review