An ABAQUS® plug-in for generating virtual data required for inverse analysis of unidirectional composites using artificial neural networks

School of Engineering

Associated organisational units

Electronic data

Manuscript_Final
Rights statement: The final publication is available at Springer via http://dx.doi.org/10.1007/s00366-021-01525-1
Accepted author manuscript, 1.77 MB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License

Text available via DOI:

https://doi.org/10.1007/s00366-021-01525-1
Final published version
Available under license: CC BY: Creative Commons Attribution 4.0 International License

Keywords

Artificial neural networks, Finite element modelling, Periodic boundary conditions, Plug-in, Unidirectional lamina, ABAQUS, Boundary conditions, Inverse problems, Neural networks, 3D finite element model, Fiber-array, Inverse analysis, Plug-ins, Uncertain material properties, Unidirectional composites, Unit cells, Virtual data, Finite element method

View graph of relations

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

An ABAQUS® plug-in for generating virtual data required for inverse analysis of unidirectional composites using artificial neural networks. / Ismail, Y.; Wan, L.; Chen, J. et al.
In: Engineering with Computers, Vol. 38, No. 5, 5, 31.10.2022, p. 4323-4335.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Bibtex

@article{eaa8c01d07134a0793319bc25e124f07,

title = "An ABAQUS{\textregistered} plug-in for generating virtual data required for inverse analysis of unidirectional composites using artificial neural networks",

abstract = "This paper presents a robust ABAQUS{\textregistered} plug-in called Virtual Data Generator (VDGen) for generating virtual data for identifying the uncertain material properties in unidirectional lamina through artificial neural networks (ANNs). The plug-in supports the 3D finite element models of unit cells with square and hexagonal fibre arrays, uses Latin-Hypercube sampling methods and robustly imposes periodic boundary conditions. Using the data generated from the plug-in, ANN is demonstrated to explicitly and accurately parameterise the relationship between fibre mechanical properties and fibre/matrix interphase parameters at microscale and the mechanical properties of a UD lamina at macroscale. The plug-in tool is applicable to general unidirectional lamina and enables easy establishment of high-fidelity micromechanical finite element models with identified material properties. ",

keywords = "Artificial neural networks, Finite element modelling, Periodic boundary conditions, Plug-in, Unidirectional lamina, ABAQUS, Boundary conditions, Inverse problems, Neural networks, 3D finite element model, Fiber-array, Inverse analysis, Plug-ins, Uncertain material properties, Unidirectional composites, Unit cells, Virtual data, Finite element method",

author = "Y. Ismail and L. Wan and J. Chen and J. Ye and D. Yang",

year = "2022",

month = oct,

day = "31",

doi = "10.1007/s00366-021-01525-1",

language = "English",

volume = "38",

pages = "4323--4335",

journal = "Engineering with Computers",

issn = "0177-0667",

publisher = "Springer",

number = "5",

}

RIS

TY - JOUR

T1 - An ABAQUS® plug-in for generating virtual data required for inverse analysis of unidirectional composites using artificial neural networks

AU - Ismail, Y.

AU - Wan, L.

AU - Chen, J.

AU - Ye, J.

AU - Yang, D.

PY - 2022/10/31

Y1 - 2022/10/31

N2 - This paper presents a robust ABAQUS® plug-in called Virtual Data Generator (VDGen) for generating virtual data for identifying the uncertain material properties in unidirectional lamina through artificial neural networks (ANNs). The plug-in supports the 3D finite element models of unit cells with square and hexagonal fibre arrays, uses Latin-Hypercube sampling methods and robustly imposes periodic boundary conditions. Using the data generated from the plug-in, ANN is demonstrated to explicitly and accurately parameterise the relationship between fibre mechanical properties and fibre/matrix interphase parameters at microscale and the mechanical properties of a UD lamina at macroscale. The plug-in tool is applicable to general unidirectional lamina and enables easy establishment of high-fidelity micromechanical finite element models with identified material properties.

AB - This paper presents a robust ABAQUS® plug-in called Virtual Data Generator (VDGen) for generating virtual data for identifying the uncertain material properties in unidirectional lamina through artificial neural networks (ANNs). The plug-in supports the 3D finite element models of unit cells with square and hexagonal fibre arrays, uses Latin-Hypercube sampling methods and robustly imposes periodic boundary conditions. Using the data generated from the plug-in, ANN is demonstrated to explicitly and accurately parameterise the relationship between fibre mechanical properties and fibre/matrix interphase parameters at microscale and the mechanical properties of a UD lamina at macroscale. The plug-in tool is applicable to general unidirectional lamina and enables easy establishment of high-fidelity micromechanical finite element models with identified material properties.

KW - Artificial neural networks

KW - Finite element modelling

KW - Periodic boundary conditions

KW - Plug-in

KW - Unidirectional lamina

KW - ABAQUS

KW - Boundary conditions

KW - Inverse problems

KW - Neural networks

KW - 3D finite element model

KW - Fiber-array

KW - Inverse analysis

KW - Plug-ins

KW - Uncertain material properties

KW - Unidirectional composites

KW - Unit cells

KW - Virtual data

KW - Finite element method

U2 - 10.1007/s00366-021-01525-1

DO - 10.1007/s00366-021-01525-1

M3 - Journal article

VL - 38

SP - 4323

EP - 4335

JO - Engineering with Computers

JF - Engineering with Computers

SN - 0177-0667

IS - 5

M1 - 5

ER -

Research

Associated organisational units

Electronic data

Links

Text available via DOI:

Keywords