Home > Research > Publications & Outputs > A genetic evolved machine learning approach for...

Links

Text available via DOI:

View graph of relations

A genetic evolved machine learning approach for 3D DEM modelling of anisotropic materials with full consideration of particulate interactions

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

A genetic evolved machine learning approach for 3D DEM modelling of anisotropic materials with full consideration of particulate interactions. / Gu, Zewen; Ding, Xiaoxuan; Hou, Xiaonan et al.
In: Composites Part B: Engineering, Vol. 250, 110432, 01.02.2023.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Gu Z, Ding X, Hou X, Ye J. A genetic evolved machine learning approach for 3D DEM modelling of anisotropic materials with full consideration of particulate interactions. Composites Part B: Engineering. 2023 Feb 1;250:110432. Epub 2022 Nov 29. doi: 10.1016/j.compositesb.2022.110432

Author

Bibtex

@article{15f21a2295864e159d756704862f08c9,
title = "A genetic evolved machine learning approach for 3D DEM modelling of anisotropic materials with full consideration of particulate interactions",
abstract = "Rapid development of multiscale modelling techniques has enabled significant improvement in understanding material failure. However, accurate simulation of general anisotropic materials still remains a great challenge. This is due to the unbalanced number of material parameters required by models of different scales, and it is difficult and sometime impossible to extract micro material properties from known macro properties. This paper proposes a new 3D discrete element model (DEM) to take full interactions between material particles for general anisotropic composite materials. The challenging issue in determining the micro bond properties of the 3 DEM model is resolved by coupling machine learning (ML) technique with the genetic algorithm (GA). The learned bond properties are validated by comparing DEM predicted macro material properties with experimental results. The micro bond properties are further used to predict strength and simulate crack patterns of bolted composite lap joints. The predictions of the ML model agree well with experimental results of the joints.",
keywords = "Deep Neuron Networks, Machine Learning, 3D Discrete Element Method Modelling, Failure of Anisotropic Materials, Bolted joints",
author = "Zewen Gu and Xiaoxuan Ding and Xiaonan Hou and Jianqiao Ye",
year = "2023",
month = feb,
day = "1",
doi = "10.1016/j.compositesb.2022.110432",
language = "English",
volume = "250",
journal = "Composites Part B: Engineering",
issn = "1359-8368",
publisher = "ELSEVIER SCI LTD",

}

RIS

TY - JOUR

T1 - A genetic evolved machine learning approach for 3D DEM modelling of anisotropic materials with full consideration of particulate interactions

AU - Gu, Zewen

AU - Ding, Xiaoxuan

AU - Hou, Xiaonan

AU - Ye, Jianqiao

PY - 2023/2/1

Y1 - 2023/2/1

N2 - Rapid development of multiscale modelling techniques has enabled significant improvement in understanding material failure. However, accurate simulation of general anisotropic materials still remains a great challenge. This is due to the unbalanced number of material parameters required by models of different scales, and it is difficult and sometime impossible to extract micro material properties from known macro properties. This paper proposes a new 3D discrete element model (DEM) to take full interactions between material particles for general anisotropic composite materials. The challenging issue in determining the micro bond properties of the 3 DEM model is resolved by coupling machine learning (ML) technique with the genetic algorithm (GA). The learned bond properties are validated by comparing DEM predicted macro material properties with experimental results. The micro bond properties are further used to predict strength and simulate crack patterns of bolted composite lap joints. The predictions of the ML model agree well with experimental results of the joints.

AB - Rapid development of multiscale modelling techniques has enabled significant improvement in understanding material failure. However, accurate simulation of general anisotropic materials still remains a great challenge. This is due to the unbalanced number of material parameters required by models of different scales, and it is difficult and sometime impossible to extract micro material properties from known macro properties. This paper proposes a new 3D discrete element model (DEM) to take full interactions between material particles for general anisotropic composite materials. The challenging issue in determining the micro bond properties of the 3 DEM model is resolved by coupling machine learning (ML) technique with the genetic algorithm (GA). The learned bond properties are validated by comparing DEM predicted macro material properties with experimental results. The micro bond properties are further used to predict strength and simulate crack patterns of bolted composite lap joints. The predictions of the ML model agree well with experimental results of the joints.

KW - Deep Neuron Networks

KW - Machine Learning

KW - 3D Discrete Element Method Modelling

KW - Failure of Anisotropic Materials

KW - Bolted joints

U2 - 10.1016/j.compositesb.2022.110432

DO - 10.1016/j.compositesb.2022.110432

M3 - Journal article

VL - 250

JO - Composites Part B: Engineering

JF - Composites Part B: Engineering

SN - 1359-8368

M1 - 110432

ER -