TY  - CONF
SP  - 327
EP  - 331
N1  - cited By 2; Conference of 1st Australian Control Conference, AUCC 2011 ; Conference Date: 10 November 2011 Through 11 November 2011; Conference Code:88164
Y1  - 2011///
N2  - In this paper the integration of linear and nonlinear models in parallel for nonlinear system identification is investigated. A residuals-based sequential identification algorithm using parallel integration of linear Orthornormal basis filters (OBF) and a nonlinear feedforward (MLP) NN model is used and applied to the nonlinear Van de Vusse reactor. Results show improved extrapolation capability of the proposed method in comparison to conventional MLP NN, and opens up a promising area for further research and analysis. © 2011 ENGINEERS AUSTRALIA & AUSTRALIAN OPTICAL.
A1  - Zabiri, H.
A1  - Ramasamy, M.
A1  - Lemma, T.D.
A1  - Maulud, A.
SN  - 9780858259874
TI  - Integrated OBF-NN models for extrapolation enhancement in conventional neural networks for nonlinear systems
CY  - Melbourne, VIC
AV  - none
KW  - Feed-Forward; Identification algorithms; Non-linear model; Parallel integration; Research and analysis
KW  -  Algorithms; Extrapolation; Identification (control systems); Integration; Nonlinear systems
KW  -  Neural networks
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84856103216&partnerID=40&md5=ba98d3d8a6c153c23edfd7f83ad1865f
ID  - scholars1780
ER  -