Prediction of Vibration Characteristics of a Composite Rotor Blade via Deep Neural Networks

Seungho Yoo; Inho Jeong; Hyejin Kim; Haeseong Cho; Taejoo Kim; Youngjung Kee

doi:10.5139/JKSAS.2022.50.5.317

Prediction of Vibration Characteristics of a Composite Rotor Blade via Deep Neural Networks

Seungho Yoo
, Inho Jeong
, Hyejin Kim
, Haeseong Cho^*
, Taejoo Kim
, Youngjung Kee

^*Corresponding author for this work

Department of Aerospace Engineering

Jeonbuk National University
Korea Aerospace Research Institute

Research output: Contribution to journal › Journal article › peer-review

Abstract

In this paper, a deep neural network(DNN) model for predicting the vibration characteristics of the composite rotor blade with c-spar cross section was developed. Herein, the present DNN model is defined by using the natural frequencies obtained through the in-house code based on the nonlinear co-rotational(CR) shell element. For the present DNN model, the accuracy of the model was evaluated via the data with a random distribution of thickness and a tendency to decrease in thickness along the blade span.

Original language	English
Pages (from-to)	317-323
Number of pages	7
Journal	Journal of the Korean Society for Aeronautical and Space Sciences
Volume	50
Issue number	5
DOIs	https://doi.org/10.5139/JKSAS.2022.50.5.317
State	Published - 2022.05

Keywords

Composite Rotor Blade
Cross Section Design
Deep Neural Network
Natural Frequency

Quacquarelli Symonds(QS) Subject Topics

Engineering - Mechanical

Access to Document

10.5139/JKSAS.2022.50.5.317

Cite this

@article{9ca792555e304349bd78bd5c1b271f8c,

title = "Prediction of Vibration Characteristics of a Composite Rotor Blade via Deep Neural Networks",

abstract = "In this paper, a deep neural network(DNN) model for predicting the vibration characteristics of the composite rotor blade with c-spar cross section was developed. Herein, the present DNN model is defined by using the natural frequencies obtained through the in-house code based on the nonlinear co-rotational(CR) shell element. For the present DNN model, the accuracy of the model was evaluated via the data with a random distribution of thickness and a tendency to decrease in thickness along the blade span.",

keywords = "Composite Rotor Blade, Cross Section Design, Deep Neural Network, Natural Frequency",

author = "Seungho Yoo and Inho Jeong and Hyejin Kim and Haeseong Cho and Taejoo Kim and Youngjung Kee",

note = "Publisher Copyright: {\textcopyright} 2022 The Korean Society for Aeronautical and Space Sciences.",

year = "2022",

month = may,

doi = "10.5139/JKSAS.2022.50.5.317",

language = "English",

volume = "50",

pages = "317--323",

journal = "Journal of the Korean Society for Aeronautical and Space Sciences",

issn = "1225-1348",

number = "5",

}

TY - JOUR

T1 - Prediction of Vibration Characteristics of a Composite Rotor Blade via Deep Neural Networks

AU - Yoo, Seungho

AU - Jeong, Inho

AU - Kim, Hyejin

AU - Cho, Haeseong

AU - Kim, Taejoo

AU - Kee, Youngjung

PY - 2022/5

Y1 - 2022/5

N2 - In this paper, a deep neural network(DNN) model for predicting the vibration characteristics of the composite rotor blade with c-spar cross section was developed. Herein, the present DNN model is defined by using the natural frequencies obtained through the in-house code based on the nonlinear co-rotational(CR) shell element. For the present DNN model, the accuracy of the model was evaluated via the data with a random distribution of thickness and a tendency to decrease in thickness along the blade span.

AB - In this paper, a deep neural network(DNN) model for predicting the vibration characteristics of the composite rotor blade with c-spar cross section was developed. Herein, the present DNN model is defined by using the natural frequencies obtained through the in-house code based on the nonlinear co-rotational(CR) shell element. For the present DNN model, the accuracy of the model was evaluated via the data with a random distribution of thickness and a tendency to decrease in thickness along the blade span.

KW - Composite Rotor Blade

KW - Cross Section Design

KW - Deep Neural Network

KW - Natural Frequency

UR - https://www.scopus.com/pages/publications/85143423260

U2 - 10.5139/JKSAS.2022.50.5.317

DO - 10.5139/JKSAS.2022.50.5.317

M3 - Journal article

AN - SCOPUS:85143423260

SN - 1225-1348

VL - 50

SP - 317

EP - 323

JO - Journal of the Korean Society for Aeronautical and Space Sciences

JF - Journal of the Korean Society for Aeronautical and Space Sciences

IS - 5

ER -

Prediction of Vibration Characteristics of a Composite Rotor Blade via Deep Neural Networks

Abstract

Keywords

Quacquarelli Symonds(QS) Subject Topics

Access to Document

Other files and links

Fingerprint

Cite this