Multi-fidelity machine learning based uncertainty quantification of progressive damage in composite laminates through optimal data fusion
Multi-fidelity machine learning based uncertainty quantification of progressive damage in composite laminates through optimal data fusion
Recently machine learning (ML) based approaches have gained significant attention in dealing with computationally intensive analyses such as uncertainty quantification of composite laminates. However, high-fidelity ML model construction is computationally demanding for such high-dimensional problems due to the required large amount of high-fidelity training data. We propose to address this issue effectively through multi-fidelity ML based surrogates which can use a training dataset consisting of optimally distributed high- and low-fidelity simulations. For forming multi-fidelity surrogates of progressive damage in composite laminates, we combine low-fidelity finite element analysis data obtained using Matzenmiller damage model with Hasin failure criteria and high-fidelity finite element analysis data obtained using three-dimensional continuum damage mechanics based model with P Linde's failure criteria. It is shown that there is a significant computational advantage to using the multi-fidelity surrogate approach as compared to conventional single-fidelity surrogates. Such computational advantage through optimal data fusion without compromising accuracy becomes crucial for the subsequent data-driven uncertainty quantification and sensitivity analysis of composites involving thousands of realizations. Ply orientations come out to be the most sensitive parameters to matrix damage, fibre damage and reaction force in composite laminates. The degree of uncertainty in the output quantities depend on the input-level stochastic variations. For example, a combined stochastic variation of ±10% in material properties and ±10° in ply orientations lead to 1.85%, 16.98% and 11.24% coefficient of variation in the matrix damage, fibre damage and reaction force respectively. In general, the numerical results obtained based on the efficient data-driven approach strongly suggest that source-uncertainty of composites significantly influences the progressive damage evolution and global mechanical behaviour, leading to the realization of the importance of adopting an inclusive analysis framework considering such inevitable random variabilities.
Continuum damage mechanics, Gaussian process, Multi-fidelity surrogates, Sensitivity analysis of composites, Stochastic progressive damage, Uncertainty quantification of composites
Chahar, R.S.
86a2f62a-407d-4711-97a9-a493aef34e84
Mukhopadhyay, T.
2ae18ab0-7477-40ac-ae22-76face7be475
Chahar, R.S.
86a2f62a-407d-4711-97a9-a493aef34e84
Mukhopadhyay, T.
2ae18ab0-7477-40ac-ae22-76face7be475
Chahar, R.S. and Mukhopadhyay, T.
(2023)
Multi-fidelity machine learning based uncertainty quantification of progressive damage in composite laminates through optimal data fusion.
Engineering Applications of Artificial Intelligence, 125, [106647].
(doi:10.1016/j.engappai.2023.106647).
Abstract
Recently machine learning (ML) based approaches have gained significant attention in dealing with computationally intensive analyses such as uncertainty quantification of composite laminates. However, high-fidelity ML model construction is computationally demanding for such high-dimensional problems due to the required large amount of high-fidelity training data. We propose to address this issue effectively through multi-fidelity ML based surrogates which can use a training dataset consisting of optimally distributed high- and low-fidelity simulations. For forming multi-fidelity surrogates of progressive damage in composite laminates, we combine low-fidelity finite element analysis data obtained using Matzenmiller damage model with Hasin failure criteria and high-fidelity finite element analysis data obtained using three-dimensional continuum damage mechanics based model with P Linde's failure criteria. It is shown that there is a significant computational advantage to using the multi-fidelity surrogate approach as compared to conventional single-fidelity surrogates. Such computational advantage through optimal data fusion without compromising accuracy becomes crucial for the subsequent data-driven uncertainty quantification and sensitivity analysis of composites involving thousands of realizations. Ply orientations come out to be the most sensitive parameters to matrix damage, fibre damage and reaction force in composite laminates. The degree of uncertainty in the output quantities depend on the input-level stochastic variations. For example, a combined stochastic variation of ±10% in material properties and ±10° in ply orientations lead to 1.85%, 16.98% and 11.24% coefficient of variation in the matrix damage, fibre damage and reaction force respectively. In general, the numerical results obtained based on the efficient data-driven approach strongly suggest that source-uncertainty of composites significantly influences the progressive damage evolution and global mechanical behaviour, leading to the realization of the importance of adopting an inclusive analysis framework considering such inevitable random variabilities.
Text
1-s2.0-S095219762300831X-main
- Version of Record
More information
Accepted/In Press date: 12 June 2023
e-pub ahead of print date: 6 July 2023
Additional Information:
Funding Information:
RSC acknowledges the financial support received through a doctoral scholarship from IIT Kanpur during the research work. TM would like to acknowledge the research support received from the University of Southampton, United Kingdom .
Funding Information:
RSC acknowledges the financial support received through a doctoral scholarship from IIT Kanpur during the research work. TM would like to acknowledge the research support received from the University of Southampton, United Kingdom.
Keywords:
Continuum damage mechanics, Gaussian process, Multi-fidelity surrogates, Sensitivity analysis of composites, Stochastic progressive damage, Uncertainty quantification of composites
Identifiers
Local EPrints ID: 483506
URI: http://eprints.soton.ac.uk/id/eprint/483506
ISSN: 0952-1976
PURE UUID: 346b93ed-8c6d-4ec7-803b-baebf0a8b558
Catalogue record
Date deposited: 01 Nov 2023 17:31
Last modified: 18 Mar 2024 04:10
Export record
Altmetrics
Contributors
Author:
R.S. Chahar
Author:
T. Mukhopadhyay
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