Home > Research > Publications & Outputs > A parametric study of adhesive bonded joints wi...

Electronic data

  • Accepted_Manuscript (2)

    Rights statement: This is the author’s version of a work that was accepted for publication in Composites Part B: Engineering. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Composites Part B: Engineering, 217, 2021 DOI: 10.1016/j.compositesb.2021.108894

    Accepted author manuscript, 1.94 MB, PDF document

    Embargo ends: 14/04/22

    Available under license: CC BY-NC-ND

Links

Text available via DOI:

View graph of relations

A parametric study of adhesive bonded joints with composite material using black-box and grey-box machine learning methods: Deep neuron networks and genetic programming

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

A parametric study of adhesive bonded joints with composite material using black-box and grey-box machine learning methods : Deep neuron networks and genetic programming. / Gu, Zewen; Liu, Yiding; J.Hughes, Darren; Ye, Jianqiao; Hou, Xiaonan.

In: Composites Part B: Engineering, Vol. 217, 108894, 15.07.2021.

Research output: Contribution to journalJournal articlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{1f2dd8747a6f440f8e404feab01f06ca,
title = "A parametric study of adhesive bonded joints with composite material using black-box and grey-box machine learning methods: Deep neuron networks and genetic programming",
abstract = "The aerospace, automotive and marine industries have witnessed a rapid increase of using adhesive bonded joints due to their advantages in joining dissimilar and/or new engineering materials. Joint strength is the key property in evaluating the capability of the adhesive joint. In this paper, developments of black-box and grey-box machine learning (ML) models are presented to allow accurate predictions of the failure load of single lap joints by considering a mix of continuous and discrete design (geometry and material) variables. Firstly, the failure loads of 300 single lap joint samples with different geometry/material parameters are calculated by FE models to generate a data set of which accuracy is validated by experimental results. Then, a deep neuron network (black-box) and a genetic programming (grey-box) model are developed for accurately predicting the failure load of the joint. Based on both ML models, a case study is conducted to explore the relationships between specific design variables and overall mechanical performances of the single lap adhesive joint, and optimal designs of structure and material can be obtained.",
author = "Zewen Gu and Yiding Liu and Darren J.Hughes and Jianqiao Ye and Xiaonan Hou",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in Composites Part B: Engineering. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Composites Part B: Engineering, 217, 2021 DOI: 10.1016/j.compositesb.2021.108894 ",
year = "2021",
month = jul,
day = "15",
doi = "10.1016/j.compositesb.2021.108894",
language = "English",
volume = "217",
journal = "Composites Part B: Engineering",
issn = "1359-8368",
publisher = "ELSEVIER SCI LTD",

}

RIS

TY - JOUR

T1 - A parametric study of adhesive bonded joints with composite material using black-box and grey-box machine learning methods

T2 - Deep neuron networks and genetic programming

AU - Gu, Zewen

AU - Liu, Yiding

AU - J.Hughes, Darren

AU - Ye, Jianqiao

AU - Hou, Xiaonan

N1 - This is the author’s version of a work that was accepted for publication in Composites Part B: Engineering. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Composites Part B: Engineering, 217, 2021 DOI: 10.1016/j.compositesb.2021.108894

PY - 2021/7/15

Y1 - 2021/7/15

N2 - The aerospace, automotive and marine industries have witnessed a rapid increase of using adhesive bonded joints due to their advantages in joining dissimilar and/or new engineering materials. Joint strength is the key property in evaluating the capability of the adhesive joint. In this paper, developments of black-box and grey-box machine learning (ML) models are presented to allow accurate predictions of the failure load of single lap joints by considering a mix of continuous and discrete design (geometry and material) variables. Firstly, the failure loads of 300 single lap joint samples with different geometry/material parameters are calculated by FE models to generate a data set of which accuracy is validated by experimental results. Then, a deep neuron network (black-box) and a genetic programming (grey-box) model are developed for accurately predicting the failure load of the joint. Based on both ML models, a case study is conducted to explore the relationships between specific design variables and overall mechanical performances of the single lap adhesive joint, and optimal designs of structure and material can be obtained.

AB - The aerospace, automotive and marine industries have witnessed a rapid increase of using adhesive bonded joints due to their advantages in joining dissimilar and/or new engineering materials. Joint strength is the key property in evaluating the capability of the adhesive joint. In this paper, developments of black-box and grey-box machine learning (ML) models are presented to allow accurate predictions of the failure load of single lap joints by considering a mix of continuous and discrete design (geometry and material) variables. Firstly, the failure loads of 300 single lap joint samples with different geometry/material parameters are calculated by FE models to generate a data set of which accuracy is validated by experimental results. Then, a deep neuron network (black-box) and a genetic programming (grey-box) model are developed for accurately predicting the failure load of the joint. Based on both ML models, a case study is conducted to explore the relationships between specific design variables and overall mechanical performances of the single lap adhesive joint, and optimal designs of structure and material can be obtained.

U2 - 10.1016/j.compositesb.2021.108894

DO - 10.1016/j.compositesb.2021.108894

M3 - Journal article

VL - 217

JO - Composites Part B: Engineering

JF - Composites Part B: Engineering

SN - 1359-8368

M1 - 108894

ER -