Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification
This paper proposes improving the structure of the 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 i...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Baghdad
2019-04-01
|
| Series: | Journal of Engineering |
| Subjects: | |
| Online Access: | http://joe.uobaghdad.edu.iq/index.php/main/article/view/818 |
| _version_ | 1797760681740599296 |
|---|---|
| author | Ahmed Sabah Al-Araji Shaymaa Jafe'er Al-Zangana |
| author_facet | Ahmed Sabah Al-Araji Shaymaa Jafe'er Al-Zangana |
| author_sort | Ahmed Sabah Al-Araji |
| collection | DOAJ |
| description | This paper proposes improving the structure of the 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. Two learning algorithms are used to adjust the parameters weight of the hybrid neural structure with its serial-parallel configuration; the first one is supervised learning algorithm based Back Propagation Algorithm (BPA) and the second one is an intelligent algorithm namely Particle Swarm Optimization (PSO) algorithm. The numerical simulation results show that the hybrid NARMA-L2 controller with PSO algorithm is more accurate than BPA in terms of achieving fast learning and adjusting the parameters model with minimum number of iterations, minimum number of neurons in the hybrid network and the smooth output one step ahead prediction controller response for the nonlinear CSTR system without oscillation. |
| first_indexed | 2024-03-12T19:02:06Z |
| format | Article |
| id | doaj.art-326081f069ad475f90c7f9ed056101e2 |
| institution | Directory Open Access Journal |
| issn | 1726-4073 2520-3339 |
| language | English |
| last_indexed | 2024-03-12T19:02:06Z |
| publishDate | 2019-04-01 |
| publisher | University of Baghdad |
| record_format | Article |
| series | Journal of Engineering |
| spelling | doaj.art-326081f069ad475f90c7f9ed056101e22023-08-02T06:30:54ZengUniversity of BaghdadJournal of Engineering1726-40732520-33392019-04-0125410.31026/j.eng.2019.04.06Design of New Hybrid Neural Controller for Nonlinear CSTR System based on IdentificationAhmed Sabah Al-Araji0Shaymaa Jafe'er Al-Zangana1Control & Systems Eng. Dept. University of TechnologyControl & Systems Eng. Dept. University of TechnologyThis paper proposes improving the structure of the 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. Two learning algorithms are used to adjust the parameters weight of the hybrid neural structure with its serial-parallel configuration; the first one is supervised learning algorithm based Back Propagation Algorithm (BPA) and the second one is an intelligent algorithm namely Particle Swarm Optimization (PSO) algorithm. The numerical simulation results show that the hybrid NARMA-L2 controller with PSO algorithm is more accurate than BPA in terms of achieving fast learning and adjusting the parameters model with minimum number of iterations, minimum number of neurons in the hybrid network and the smooth output one step ahead prediction controller response for the nonlinear CSTR system without oscillation.http://joe.uobaghdad.edu.iq/index.php/main/article/view/818NARMA-L2Model, MLP neural Network, Modified Elman Neural Network, Back Propagation Algorithm, Particle Swarm Optimization, Nonlinear CSTR System. |
| spellingShingle | Ahmed Sabah Al-Araji Shaymaa Jafe'er Al-Zangana Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification Journal of Engineering NARMA-L2Model, MLP neural Network, Modified Elman Neural Network, Back Propagation Algorithm, Particle Swarm Optimization, Nonlinear CSTR System. |
| title | Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification |
| title_full | Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification |
| title_fullStr | Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification |
| title_full_unstemmed | Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification |
| title_short | Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification |
| title_sort | design of new hybrid neural controller for nonlinear cstr system based on identification |
| topic | NARMA-L2Model, MLP neural Network, Modified Elman Neural Network, Back Propagation Algorithm, Particle Swarm Optimization, Nonlinear CSTR System. |
| url | http://joe.uobaghdad.edu.iq/index.php/main/article/view/818 |
| work_keys_str_mv | AT ahmedsabahalaraji designofnewhybridneuralcontrollerfornonlinearcstrsystembasedonidentification AT shaymaajafeeralzangana designofnewhybridneuralcontrollerfornonlinearcstrsystembasedonidentification |