The ability of forecasting flapping frequency of flexible filament by artificial neural network

Artificial Neural Networks (ANNs) are reliable and computationally inexpensive compared to numerical methods such as CFD simulations and experimental investigations in aerodynamics research. In this article, an Artificial Neural Network (ANN) has been introduced to predict the flapping frequencies o...

Full description

Bibliographic Details
Main Authors: M. Fayed, M. Elhadary, H. Ait Abderrahmane, Bassem Nashaat Zakher
Format: Article
Language:English
Published: Elsevier 2019-12-01
Series:Alexandria Engineering Journal
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016819301280
id doaj-b682815b3d19444f8bd238982a3160e2
record_format Article
spelling doaj-b682815b3d19444f8bd238982a3160e22021-06-02T06:48:50ZengElsevierAlexandria Engineering Journal1110-01682019-12-0158413671374The ability of forecasting flapping frequency of flexible filament by artificial neural networkM. Fayed0M. Elhadary1H. Ait Abderrahmane2Bassem Nashaat Zakher3College of Engineering and Technology, American University of the Middle East, Kuwait; Department of Mechanical Engineering, Faculty of Engineering, Alexandria University, EgyptDepartment of Mechanical Engineering, Faculty of Engineering, Alexandria University, Egypt; Corresponding author.Khalifa University of Science and Technology, Masdar Institute, Masdar City, P.O. Box 54224, Abu Dhabi, United Arab EmiratesPharos University in Alexandria (PUA), Mechanical Department, Alexandria, EgyptArtificial Neural Networks (ANNs) are reliable and computationally inexpensive compared to numerical methods such as CFD simulations and experimental investigations in aerodynamics research. In this article, an Artificial Neural Network (ANN) has been introduced to predict the flapping frequencies of a filament placed in a 2-D soap-film tunnel. The multi-layer perception (MLP) networks have been used in developing the Artificial Neural Network while the backpropagation Levenberg-Marquardt algorithm was used to perform the training of the ANN. A part of the experimental data was considered for the training process while the rest for the prediction test of the suggested ANN. The ANN results indicate that it can predict the frequencies of the periodic flapping with good accuracy. However, it fails when the flapping presents amplitude modulation. Keywords: Flapping frequency, Artificial neural network (ANN), Flexible filamenthttp://www.sciencedirect.com/science/article/pii/S1110016819301280
collection DOAJ
language English
format Article
sources DOAJ
author M. Fayed
M. Elhadary
H. Ait Abderrahmane
Bassem Nashaat Zakher
spellingShingle M. Fayed
M. Elhadary
H. Ait Abderrahmane
Bassem Nashaat Zakher
The ability of forecasting flapping frequency of flexible filament by artificial neural network
Alexandria Engineering Journal
author_facet M. Fayed
M. Elhadary
H. Ait Abderrahmane
Bassem Nashaat Zakher
author_sort M. Fayed
title The ability of forecasting flapping frequency of flexible filament by artificial neural network
title_short The ability of forecasting flapping frequency of flexible filament by artificial neural network
title_full The ability of forecasting flapping frequency of flexible filament by artificial neural network
title_fullStr The ability of forecasting flapping frequency of flexible filament by artificial neural network
title_full_unstemmed The ability of forecasting flapping frequency of flexible filament by artificial neural network
title_sort ability of forecasting flapping frequency of flexible filament by artificial neural network
publisher Elsevier
series Alexandria Engineering Journal
issn 1110-0168
publishDate 2019-12-01
description Artificial Neural Networks (ANNs) are reliable and computationally inexpensive compared to numerical methods such as CFD simulations and experimental investigations in aerodynamics research. In this article, an Artificial Neural Network (ANN) has been introduced to predict the flapping frequencies of a filament placed in a 2-D soap-film tunnel. The multi-layer perception (MLP) networks have been used in developing the Artificial Neural Network while the backpropagation Levenberg-Marquardt algorithm was used to perform the training of the ANN. A part of the experimental data was considered for the training process while the rest for the prediction test of the suggested ANN. The ANN results indicate that it can predict the frequencies of the periodic flapping with good accuracy. However, it fails when the flapping presents amplitude modulation. Keywords: Flapping frequency, Artificial neural network (ANN), Flexible filament
url http://www.sciencedirect.com/science/article/pii/S1110016819301280
work_keys_str_mv AT mfayed theabilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
AT melhadary theabilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
AT haitabderrahmane theabilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
AT bassemnashaatzakher theabilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
AT mfayed abilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
AT melhadary abilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
AT haitabderrahmane abilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
AT bassemnashaatzakher abilityofforecastingflappingfrequencyofflexiblefilamentbyartificialneuralnetwork
_version_ 1721407640171446272