Design of new hybrid neural structure for modeling and controlling nonlinear systems
Other Title(s)
تصميم هيكل عصبي هجين جديد لمنذجة و السيطرة المنظومات اللاخطية
Joint Authors
al-Zankana, Shayma Jafar
al-Araji, Ahmad Sabah Abd al-Amir
Source
Issue
Vol. 25, Issue 2 (28 Feb. 2019), pp.116-135, 20 p.
Publisher
University of Baghdad College of Engineering
Publication Date
2019-02-28
Country of Publication
Iraq
No. of Pages
20
Main Subjects
Engineering & Technology Sciences (Multidisciplinary)
Topics
Abstract EN
This paper proposes a new structure of the hybrid neural controller based on the identification model for nonlinear systems.
The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems.
Weight parameters of the hybrid neural structure with its serial-parallel configuration are adapted by using the Back propagation learning algorithm.
The ability of the proposed hybrid neural structure for nonlinear system has achieved a fast learning with minimum number of epoch, minimum number of neurons in the hybrid network, high accuracy in the output without oscillation response as well as useful model for a one step ahead prediction controller for the nonlinear CSTR system that is used in the MATLAB simulation.
American Psychological Association (APA)
al-Araji, Ahmad Sabah Abd al-Amir& al-Zankana, Shayma Jafar. 2019. Design of new hybrid neural structure for modeling and controlling nonlinear systems. Journal of Engineering،Vol. 25, no. 2, pp.116-135.
https://search.emarefa.net/detail/BIM-892592
Modern Language Association (MLA)
al-Araji, Ahmad Sabah Abd al-Amir& al-Zankana, Shayma Jafar. Design of new hybrid neural structure for modeling and controlling nonlinear systems. Journal of Engineering Vol. 25, no. 2 (Feb. 2019), pp.116-135.
https://search.emarefa.net/detail/BIM-892592
American Medical Association (AMA)
al-Araji, Ahmad Sabah Abd al-Amir& al-Zankana, Shayma Jafar. Design of new hybrid neural structure for modeling and controlling nonlinear systems. Journal of Engineering. 2019. Vol. 25, no. 2, pp.116-135.
https://search.emarefa.net/detail/BIM-892592
Data Type
Journal Articles
Language
English
Notes
Includes appendix : p. 127-135
Record ID
BIM-892592