Presentation 1999/5/13
Identification of Hammerstein System by Neural Networks
Masakatsu Oki, Yasuhide Kobayashi, Tsuyoshi Okita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes new identification schemes with neural networks for Hammerstein system, consisting of a memoryless nonlinear elements in cascade with a dynamic linear subsystem. The order of the linear part and the nonlinear elements are unknown. The nonlinear part is approximated by artificial neural networks and the linear part is approximated by auto-regressive exogenous model. The connection coeffcients of neural networks and the parameters of the linear subsystem are estimated by renewal Back-Propagation method. the order of the linear subsystem and the structures of the neural networks are selected by the minimum description length criterion. It is demonstrated in digital simulation that the proposed identification technique is extremely efficient in the system with high nonlinearities.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hammerstein system / system identification / neural networks / block-oriented model / parameter estimation / model selection
Paper # NLP99-5
Date of Issue

Conference Information
Committee NLP
Conference Date 1999/5/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Identification of Hammerstein System by Neural Networks
Sub Title (in English)
Keyword(1) Hammerstein system
Keyword(2) system identification
Keyword(3) neural networks
Keyword(4) block-oriented model
Keyword(5) parameter estimation
Keyword(6) model selection
1st Author's Name Masakatsu Oki
1st Author's Affiliation Hiroshima City University()
2nd Author's Name Yasuhide Kobayashi
2nd Author's Affiliation Hiroshima City University
3rd Author's Name Tsuyoshi Okita
3rd Author's Affiliation Hiroshima City University
Date 1999/5/13
Paper # NLP99-5
Volume (vol) vol.99
Number (no) 41
Page pp.pp.-
#Pages 8
Date of Issue