Flutter speed prediction by using deep learning

Deep learning technology has been widely used in various field in recent years. This study intends to use deep learning algorithms to analyze the aeroelastic phenomenon and compare the differences between Deep Neural Network (DNN) and Long Short-term Memory (LSTM) applied on the flutter speed predic...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yi-Ren Wang, Yi-Jyun Wang
Formato:	article
Lenguaje:	EN
Publicado:	SAGE Publishing 2021
Materias:	Mechanical engineering and machinery TJ1-1570
Acceso en línea:	https://doaj.org/article/7a2587ef3bc34340833c3f799ba55d26
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7a2587ef3bc34340833c3f799ba55d26
record_format	dspace
spelling	oai:doaj.org-article:7a2587ef3bc34340833c3f799ba55d262021-11-19T01:33:31ZFlutter speed prediction by using deep learning1687-814010.1177/16878140211062275https://doaj.org/article/7a2587ef3bc34340833c3f799ba55d262021-11-01T00:00:00Zhttps://doi.org/10.1177/16878140211062275https://doaj.org/toc/1687-8140Deep learning technology has been widely used in various field in recent years. This study intends to use deep learning algorithms to analyze the aeroelastic phenomenon and compare the differences between Deep Neural Network (DNN) and Long Short-term Memory (LSTM) applied on the flutter speed prediction. In this present work, DNN and LSTM are used to address complex aeroelastic systems by superimposing multi-layer Artificial Neural Network. Under such an architecture, the neurons in neural network can extract features from various flight data. Instead of time-consuming high-fidelity computational fluid dynamics (CFD) method, this study uses the K method to build the aeroelastic flutter speed big data for different flight conditions. The flutter speeds for various flight conditions are predicted by the deep learning methods and verified by the K method. The detailed physical meaning of aerodynamics and aeroelasticity of the prediction results are studied. The LSTM model has a cyclic architecture, which enables it to store information and update it with the latest information at the same time. Although the training of the model is more time-consuming than DNN, this method can increase the memory space. The results of this work show that the LSTM model established in this study can provide more accurate flutter speed prediction than the DNN algorithm.Yi-Ren WangYi-Jyun WangSAGE PublishingarticleMechanical engineering and machineryTJ1-1570ENAdvances in Mechanical Engineering, Vol 13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Mechanical engineering and machinery TJ1-1570
spellingShingle	Mechanical engineering and machinery TJ1-1570 Yi-Ren Wang Yi-Jyun Wang Flutter speed prediction by using deep learning
description	Deep learning technology has been widely used in various field in recent years. This study intends to use deep learning algorithms to analyze the aeroelastic phenomenon and compare the differences between Deep Neural Network (DNN) and Long Short-term Memory (LSTM) applied on the flutter speed prediction. In this present work, DNN and LSTM are used to address complex aeroelastic systems by superimposing multi-layer Artificial Neural Network. Under such an architecture, the neurons in neural network can extract features from various flight data. Instead of time-consuming high-fidelity computational fluid dynamics (CFD) method, this study uses the K method to build the aeroelastic flutter speed big data for different flight conditions. The flutter speeds for various flight conditions are predicted by the deep learning methods and verified by the K method. The detailed physical meaning of aerodynamics and aeroelasticity of the prediction results are studied. The LSTM model has a cyclic architecture, which enables it to store information and update it with the latest information at the same time. Although the training of the model is more time-consuming than DNN, this method can increase the memory space. The results of this work show that the LSTM model established in this study can provide more accurate flutter speed prediction than the DNN algorithm.
format	article
author	Yi-Ren Wang Yi-Jyun Wang
author_facet	Yi-Ren Wang Yi-Jyun Wang
author_sort	Yi-Ren Wang
title	Flutter speed prediction by using deep learning
title_short	Flutter speed prediction by using deep learning
title_full	Flutter speed prediction by using deep learning
title_fullStr	Flutter speed prediction by using deep learning
title_full_unstemmed	Flutter speed prediction by using deep learning
title_sort	flutter speed prediction by using deep learning
publisher	SAGE Publishing
publishDate	2021
url	https://doaj.org/article/7a2587ef3bc34340833c3f799ba55d26
work_keys_str_mv	AT yirenwang flutterspeedpredictionbyusingdeeplearning AT yijyunwang flutterspeedpredictionbyusingdeeplearning
_version_	1718420617773973504

Flutter speed prediction by using deep learning

Ejemplares similares