Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems

Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems

In this research, a comparative study of two recurrent neural networks, nonlinear autoregressive with exogenous input (NARX) neural network and nonlinear autoregressive moving average (NARMA-L2), and a feedforward neural network (FFNN) is performed for their ability to provide adaptive control of no...

Full description

Bibliographic Details
Main Authors: Khadija El Hamidi, Mostafa Mjahed, Abdeljalil El Kari, Hassan Ayad
Format: Article
Language:English
Published: Hindawi Limited 2020-01-01
Series:Modelling and Simulation in Engineering
Online Access:http://dx.doi.org/10.1155/2020/8642915
id doaj-90ce90247eb545bf89313dc8b3f9642e
record_format Article
spelling doaj-90ce90247eb545bf89313dc8b3f9642e2020-11-25T03:44:06ZengHindawi LimitedModelling and Simulation in Engineering1687-55911687-56052020-01-01202010.1155/2020/86429158642915Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic SystemsKhadija El Hamidi0Mostafa Mjahed1Abdeljalil El Kari2Hassan Ayad3Laboratory of Electric Systems and Telecommunications, Cadi-Ayyad University, Marrakesh 4000, MoroccoMathematics and Systems Department, Royal School of Aeronautics, Marrakesh 40000, MoroccoLaboratory of Electric Systems and Telecommunications, Cadi-Ayyad University, Marrakesh 4000, MoroccoLaboratory of Electric Systems and Telecommunications, Cadi-Ayyad University, Marrakesh 4000, MoroccoIn this research, a comparative study of two recurrent neural networks, nonlinear autoregressive with exogenous input (NARX) neural network and nonlinear autoregressive moving average (NARMA-L2), and a feedforward neural network (FFNN) is performed for their ability to provide adaptive control of nonlinear systems. Three dynamical nonlinear systems of different complexity are considered. The aim of this work is to make the output of the plant follow the desired reference trajectory. The problem becomes more challenging when the dynamics of the plants are assumed to be unknown, and to tackle this problem, a multilayer neural network-based approximate model is set up which will work in parallel to the plant and the control scheme. The network parameters are updated using the dynamic backpropagation (BP) algorithm.http://dx.doi.org/10.1155/2020/8642915
collection DOAJ
language English
format Article
sources DOAJ
author Khadija El Hamidi
Mostafa Mjahed
Abdeljalil El Kari
Hassan Ayad
spellingShingle Khadija El Hamidi
Mostafa Mjahed
Abdeljalil El Kari
Hassan Ayad
Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems
Modelling and Simulation in Engineering
author_facet Khadija El Hamidi
Mostafa Mjahed
Abdeljalil El Kari
Hassan Ayad
author_sort Khadija El Hamidi
title Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems
title_short Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems
title_full Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems
title_fullStr Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems
title_full_unstemmed Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems
title_sort adaptive control using neural networks and approximate models for nonlinear dynamic systems
publisher Hindawi Limited
series Modelling and Simulation in Engineering
issn 1687-5591
1687-5605
publishDate 2020-01-01
description In this research, a comparative study of two recurrent neural networks, nonlinear autoregressive with exogenous input (NARX) neural network and nonlinear autoregressive moving average (NARMA-L2), and a feedforward neural network (FFNN) is performed for their ability to provide adaptive control of nonlinear systems. Three dynamical nonlinear systems of different complexity are considered. The aim of this work is to make the output of the plant follow the desired reference trajectory. The problem becomes more challenging when the dynamics of the plants are assumed to be unknown, and to tackle this problem, a multilayer neural network-based approximate model is set up which will work in parallel to the plant and the control scheme. The network parameters are updated using the dynamic backpropagation (BP) algorithm.
url http://dx.doi.org/10.1155/2020/8642915
work_keys_str_mv AT khadijaelhamidi adaptivecontrolusingneuralnetworksandapproximatemodelsfornonlineardynamicsystems
AT mostafamjahed adaptivecontrolusingneuralnetworksandapproximatemodelsfornonlineardynamicsystems
AT abdeljalilelkari adaptivecontrolusingneuralnetworksandapproximatemodelsfornonlineardynamicsystems
AT hassanayad adaptivecontrolusingneuralnetworksandapproximatemodelsfornonlineardynamicsystems
_version_ 1715130634744102912

Similar Items