No Cover Image

Journal article 27 views 2 downloads

The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning / Tanmoy Chatterjee, Aniekan Essien, Ranjan Ganguli, Michael Friswell

Neural Computing and Applications

Swansea University Authors: Tanmoy Chatterjee, Michael Friswell

  • 57491.pdf

    PDF | Version of Record

    The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License

    Download (1.27MB)

Abstract

This paper addresses the influence of manufacturing variability of a helicopter rotor blade on its aeroelastic responses. An aeroelastic analysis using finite elements in spatial and temporal domains is used to compute the helicopter rotor frequencies, vibratory hub loads, power required and stabili...

Full description

Published in: Neural Computing and Applications
ISSN: 0941-0643 1433-3058
Published: Springer Science and Business Media LLC 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57491
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-08-02T09:50:47Z
last_indexed 2021-09-11T03:20:22Z
id cronfa57491
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-09-10T17:26:05.3251224</datestamp><bib-version>v2</bib-version><id>57491</id><entry>2021-08-02</entry><title>The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning</title><swanseaauthors><author><sid>5e637da3a34c6e97e2b744c2120db04d</sid><firstname>Tanmoy</firstname><surname>Chatterjee</surname><name>Tanmoy Chatterjee</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>5894777b8f9c6e64bde3568d68078d40</sid><firstname>Michael</firstname><surname>Friswell</surname><name>Michael Friswell</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-08-02</date><deptcode>AERO</deptcode><abstract>This paper addresses the influence of manufacturing variability of a helicopter rotor blade on its aeroelastic responses. An aeroelastic analysis using finite elements in spatial and temporal domains is used to compute the helicopter rotor frequencies, vibratory hub loads, power required and stability in forward flight. The novelty of the work lies in the application of advanced data-driven machine learning (ML) techniques, such as convolution neural networks (CNN), multi-layer perceptron (MLP), random forests, support vector machines and adaptive Gaussian process (GP) for capturing the nonlinear responses of these complex spatio-temporal models to develop an efficient physics-informed ML framework for stochastic rotor analysis. Thus, the work is of practical significance as (i) it accounts for manufacturing uncertainties, (ii) accurately quantifies their effects on nonlinear response of rotor blade and (iii) makes the computationally expensive simulations viable by the use of ML. A rigorous performance assessment of the aforementioned approaches is presented by demonstrating validation on the training dataset and prediction on the test dataset. The contribution of the study lies in the following findings: (i) The uncertainty in composite material and geometric properties can lead to significant variations in the rotor aeroelastic responses and thereby highlighting that the consideration of manufacturing variability in analyzing helicopter rotors is crucial for assessing their behaviour in real-life scenarios. (ii) Precisely, the substantial effect of uncertainty has been observed on the six vibratory hub loads and the damping with the highest impact on the yawing hub moment. Therefore, sufficient factor of safety should be considered in the design to alleviate the effects of perturbation in the simulation results. (iii) Although advanced ML techniques are harder to train, the optimal model configuration is capable of approximating the nonlinear response trends accurately. GP and CNN followed by MLP achieved satisfactory performance. Excellent accuracy achieved by the above ML techniques demonstrates their potential for application in the optimization of rotors under uncertainty.</abstract><type>Journal Article</type><journal>Neural Computing and Applications</journal><volume>0</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0941-0643</issnPrint><issnElectronic>1433-3058</issnElectronic><keywords>Helicopter rotor; Aeroelastic; Stochastic; Machine learning</keywords><publishedDay>17</publishedDay><publishedMonth>7</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-07-17</publishedDate><doi>10.1007/s00521-021-06288-w</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>AERO</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>Engineering and Physical Sciences Research Council through the award of the Programme Grant &#x2019;Digital Twins for Improved Dynamic Design&#x2019;, grant number EP/R006768.</funders><lastEdited>2021-09-10T17:26:05.3251224</lastEdited><Created>2021-08-02T10:48:57.3113575</Created><path><level id="1">College of Engineering</level><level id="2">Engineering</level></path><authors><author><firstname>Tanmoy</firstname><surname>Chatterjee</surname><order>1</order></author><author><firstname>Aniekan</firstname><surname>Essien</surname><order>2</order></author><author><firstname>Ranjan</firstname><surname>Ganguli</surname><order>3</order></author><author><firstname>Michael</firstname><surname>Friswell</surname><order>4</order></author></authors><documents><document><filename>57491__20502__50ab8dbfe0424c53bf1800c2625179c4.pdf</filename><originalFilename>57491.pdf</originalFilename><uploaded>2021-08-02T10:50:10.6424798</uploaded><type>Output</type><contentLength>1327988</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><action/><documentNotes>The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-09-10T17:26:05.3251224 v2 57491 2021-08-02 The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning 5e637da3a34c6e97e2b744c2120db04d Tanmoy Chatterjee Tanmoy Chatterjee true false 5894777b8f9c6e64bde3568d68078d40 Michael Friswell Michael Friswell true false 2021-08-02 AERO This paper addresses the influence of manufacturing variability of a helicopter rotor blade on its aeroelastic responses. An aeroelastic analysis using finite elements in spatial and temporal domains is used to compute the helicopter rotor frequencies, vibratory hub loads, power required and stability in forward flight. The novelty of the work lies in the application of advanced data-driven machine learning (ML) techniques, such as convolution neural networks (CNN), multi-layer perceptron (MLP), random forests, support vector machines and adaptive Gaussian process (GP) for capturing the nonlinear responses of these complex spatio-temporal models to develop an efficient physics-informed ML framework for stochastic rotor analysis. Thus, the work is of practical significance as (i) it accounts for manufacturing uncertainties, (ii) accurately quantifies their effects on nonlinear response of rotor blade and (iii) makes the computationally expensive simulations viable by the use of ML. A rigorous performance assessment of the aforementioned approaches is presented by demonstrating validation on the training dataset and prediction on the test dataset. The contribution of the study lies in the following findings: (i) The uncertainty in composite material and geometric properties can lead to significant variations in the rotor aeroelastic responses and thereby highlighting that the consideration of manufacturing variability in analyzing helicopter rotors is crucial for assessing their behaviour in real-life scenarios. (ii) Precisely, the substantial effect of uncertainty has been observed on the six vibratory hub loads and the damping with the highest impact on the yawing hub moment. Therefore, sufficient factor of safety should be considered in the design to alleviate the effects of perturbation in the simulation results. (iii) Although advanced ML techniques are harder to train, the optimal model configuration is capable of approximating the nonlinear response trends accurately. GP and CNN followed by MLP achieved satisfactory performance. Excellent accuracy achieved by the above ML techniques demonstrates their potential for application in the optimization of rotors under uncertainty. Journal Article Neural Computing and Applications 0 Springer Science and Business Media LLC 0941-0643 1433-3058 Helicopter rotor; Aeroelastic; Stochastic; Machine learning 17 7 2021 2021-07-17 10.1007/s00521-021-06288-w COLLEGE NANME Aerospace Engineering COLLEGE CODE AERO Swansea University Engineering and Physical Sciences Research Council through the award of the Programme Grant ’Digital Twins for Improved Dynamic Design’, grant number EP/R006768. 2021-09-10T17:26:05.3251224 2021-08-02T10:48:57.3113575 College of Engineering Engineering Tanmoy Chatterjee 1 Aniekan Essien 2 Ranjan Ganguli 3 Michael Friswell 4 57491__20502__50ab8dbfe0424c53bf1800c2625179c4.pdf 57491.pdf 2021-08-02T10:50:10.6424798 Output 1327988 application/pdf Version of Record true The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License true eng
title The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning
spellingShingle The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning
Tanmoy, Chatterjee
Michael, Friswell
title_short The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning
title_full The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning
title_fullStr The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning
title_full_unstemmed The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning
title_sort The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning
author_id_str_mv 5e637da3a34c6e97e2b744c2120db04d
5894777b8f9c6e64bde3568d68078d40
author_id_fullname_str_mv 5e637da3a34c6e97e2b744c2120db04d_***_Tanmoy, Chatterjee
5894777b8f9c6e64bde3568d68078d40_***_Michael, Friswell
author Tanmoy, Chatterjee
Michael, Friswell
author2 Tanmoy Chatterjee
Aniekan Essien
Ranjan Ganguli
Michael Friswell
format Journal article
container_title Neural Computing and Applications
container_volume 0
publishDate 2021
institution Swansea University
issn 0941-0643
1433-3058
doi_str_mv 10.1007/s00521-021-06288-w
publisher Springer Science and Business Media LLC
college_str College of Engineering
hierarchytype
hierarchy_top_id collegeofengineering
hierarchy_top_title College of Engineering
hierarchy_parent_id collegeofengineering
hierarchy_parent_title College of Engineering
department_str Engineering{{{_:::_}}}College of Engineering{{{_:::_}}}Engineering
document_store_str 1
active_str 0
description This paper addresses the influence of manufacturing variability of a helicopter rotor blade on its aeroelastic responses. An aeroelastic analysis using finite elements in spatial and temporal domains is used to compute the helicopter rotor frequencies, vibratory hub loads, power required and stability in forward flight. The novelty of the work lies in the application of advanced data-driven machine learning (ML) techniques, such as convolution neural networks (CNN), multi-layer perceptron (MLP), random forests, support vector machines and adaptive Gaussian process (GP) for capturing the nonlinear responses of these complex spatio-temporal models to develop an efficient physics-informed ML framework for stochastic rotor analysis. Thus, the work is of practical significance as (i) it accounts for manufacturing uncertainties, (ii) accurately quantifies their effects on nonlinear response of rotor blade and (iii) makes the computationally expensive simulations viable by the use of ML. A rigorous performance assessment of the aforementioned approaches is presented by demonstrating validation on the training dataset and prediction on the test dataset. The contribution of the study lies in the following findings: (i) The uncertainty in composite material and geometric properties can lead to significant variations in the rotor aeroelastic responses and thereby highlighting that the consideration of manufacturing variability in analyzing helicopter rotors is crucial for assessing their behaviour in real-life scenarios. (ii) Precisely, the substantial effect of uncertainty has been observed on the six vibratory hub loads and the damping with the highest impact on the yawing hub moment. Therefore, sufficient factor of safety should be considered in the design to alleviate the effects of perturbation in the simulation results. (iii) Although advanced ML techniques are harder to train, the optimal model configuration is capable of approximating the nonlinear response trends accurately. GP and CNN followed by MLP achieved satisfactory performance. Excellent accuracy achieved by the above ML techniques demonstrates their potential for application in the optimization of rotors under uncertainty.
published_date 2021-07-17T04:24:14Z
_version_ 1714379245078183936
score 10.830003