On machine learning assisted data-driven bridging of FSDT and HOZT for high-fidelity uncertainty quantification of laminated composite and sandwich plates
On machine learning assisted data-driven bridging of FSDT and HOZT for high-fidelity uncertainty quantification of laminated composite and sandwich plates
First-order shear deformation theory (FSDT) is less accurate compared to higher-order theories like higher-order zigzag theory (HOZT).In case of large-scale simulation-based analyses like uncertainty quantification and optimization using FSDT, such errors propagate and accumulate over multiple realizations, leading to significantly erroneous results. Consideration of higher-order theories results in significantly increased computational expenses, even though these theories are more accurate. The aspect of computational efficiency becomes more critical when thousands of realizations are necessary for the analyses. Here we propose to exploit Gaussian process-based machine learning for creating a computational bridging between FSDT and HOZT, wherein the accuracy of HOZT can be achieved while having the low computational expenses of FSDT. The machine learning augmented FSDT algorithm is referred to here as modified FSDT (mFSDT), based on which extensive deterministic results and Monte Carlo simulation-assisted probabilistic results are presented for the free vibration analysis of shear deformation sensitive structures like laminated composite and sandwich plates considering various configurations. The proposed algorithm of bridging different laminate theories is generic in nature and it can be utilized further in a range of other static and dynamic analyses concerning composite plates and shells for accurate, yet efficient results.
Data-driven stochastic natural frequency analysis, Gaussian process regression, Higher order zigzag theory (HOZT), Machine learning assisted laminate theory, Modified first-order shear deformation theory (mFSDT), Monte Carlo simulation
Vaishali, Vaishali
f129101a-6555-4e0e-9912-65b2a7145586
Mukhopadhyay, Tanmoy
2ae18ab0-7477-40ac-ae22-76face7be475
Naskar, Susmita
5f787953-b062-4774-a28b-473bd19254b1
Dey, Sudip
4d0ea608-5444-44b4-acc0-ba7004a5f76c
15 January 2023
Vaishali, Vaishali
f129101a-6555-4e0e-9912-65b2a7145586
Mukhopadhyay, Tanmoy
2ae18ab0-7477-40ac-ae22-76face7be475
Naskar, Susmita
5f787953-b062-4774-a28b-473bd19254b1
Dey, Sudip
4d0ea608-5444-44b4-acc0-ba7004a5f76c
Vaishali, Vaishali, Mukhopadhyay, Tanmoy, Naskar, Susmita and Dey, Sudip
(2023)
On machine learning assisted data-driven bridging of FSDT and HOZT for high-fidelity uncertainty quantification of laminated composite and sandwich plates.
Composite Structures, 304, [116276].
(doi:10.1016/j.compstruct.2022.116276).
Abstract
First-order shear deformation theory (FSDT) is less accurate compared to higher-order theories like higher-order zigzag theory (HOZT).In case of large-scale simulation-based analyses like uncertainty quantification and optimization using FSDT, such errors propagate and accumulate over multiple realizations, leading to significantly erroneous results. Consideration of higher-order theories results in significantly increased computational expenses, even though these theories are more accurate. The aspect of computational efficiency becomes more critical when thousands of realizations are necessary for the analyses. Here we propose to exploit Gaussian process-based machine learning for creating a computational bridging between FSDT and HOZT, wherein the accuracy of HOZT can be achieved while having the low computational expenses of FSDT. The machine learning augmented FSDT algorithm is referred to here as modified FSDT (mFSDT), based on which extensive deterministic results and Monte Carlo simulation-assisted probabilistic results are presented for the free vibration analysis of shear deformation sensitive structures like laminated composite and sandwich plates considering various configurations. The proposed algorithm of bridging different laminate theories is generic in nature and it can be utilized further in a range of other static and dynamic analyses concerning composite plates and shells for accurate, yet efficient results.
Text
FSDT and HOZT Paper_31.03.2022 r01
- Accepted Manuscript
More information
Accepted/In Press date: 26 September 2022
Published date: 15 January 2023
Additional Information:
Funding Information:
Vaishali acknowledges the MoE, Govt. of India, for the support provided during this work. TM acknowledges the initiation grant from IIT Kanpur.
Publisher Copyright:
© 2022 Elsevier Ltd
Keywords:
Data-driven stochastic natural frequency analysis, Gaussian process regression, Higher order zigzag theory (HOZT), Machine learning assisted laminate theory, Modified first-order shear deformation theory (mFSDT), Monte Carlo simulation
Identifiers
Local EPrints ID: 471110
URI: http://eprints.soton.ac.uk/id/eprint/471110
ISSN: 0263-8223
PURE UUID: d237ba12-accc-4386-8b15-8001f0921393
Catalogue record
Date deposited: 26 Oct 2022 17:06
Last modified: 10 Oct 2024 04:01
Export record
Altmetrics
Contributors
Author:
Vaishali Vaishali
Author:
Tanmoy Mukhopadhyay
Author:
Sudip Dey
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics