2
IRUS Total
Downloads
  Altmetric

A machine learning assisted multifidelity modelling methodology to predict 3D stresses in the vicinity of design features in composite structures

File Description SizeFormat 
1-s2.0-S0020768324003056-main.pdfPublished version9.92 MBAdobe PDFView/Open
Title: A machine learning assisted multifidelity modelling methodology to predict 3D stresses in the vicinity of design features in composite structures
Authors: Imran Azeem, OA
Pinho, ST
Item Type: Journal Article
Abstract: Multifidelity global–local finite element (FE) analyses are typically used to predict damage initiation hotspots around repetitive design features in large composite structures, such as composite airframes. We propose the use of machine learning (ML) methods to accelerate these analyses. We demonstrate this ML assisted framework for the stress analysis of a hole in plate feature in an aerospace C-spar structure. To enable this framework, we develop the following original features: a computationally efficient sampling scheme; a work-equivalent boundary condition homogenisation scheme; a volume averaged ply-by-ply stress approach; and a sequential long-short term memory neural network reformulated from a time basis to a stacking sequence basis with further bi-directionality customisation. Overall, we show that the developed method results in high-accuracy prediction of 3D stresses, with over two orders of magnitude reduction in modelling and simulation time compared to FE analyses.
Issue Date: 1-Sep-2024
Date of Acceptance: 23-Jun-2024
URI: http://hdl.handle.net/10044/1/112623
DOI: 10.1016/j.ijsolstr.2024.112946
ISSN: 0020-7683
Publisher: Elsevier
Journal / Book Title: International Journal of Solids and Structures
Volume: 301
Copyright Statement: © 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Publication Status: Published
Article Number: 112946
Online Publication Date: 2024-06-24
Appears in Collections:Aeronautics
Faculty of Engineering



This item is licensed under a Creative Commons License Creative Commons