Computational machine learning representation for the flexoelectricity effect in truncated pyramid structures

Khader M. Hamdia, Hamid Ghasemi, Xiaoying Zhuang, Naif Alajlan, Timon Rabczuk

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this study, machine learning representation is introduced to evaluate the flexoelectricity effect in truncated pyramid nanostructure under compression. A NonUniform Rational B-spline (NURBS) based IGA formulation is employed to model the flexoelectricity. We investigate 2D system with an isotropic linear elastic material under plane strain conditions discretized by 45×30 grid of B-spline elements. Six input parameters are selected to construct a deep neural network (DNN) model. They are the Young's modulus, two dielectric permittivity constants, the longitudinal and transversal flexoelectric coefficients and the order of the shape function. The outputs of interest are the strain in the stress direction and the electric potential due flexoelectricity. The dataset are generated from the forward analysis of the flexoelectric model. 80% of the dataset is used for training purpose while the remaining is used for validation by checking the mean squared error. In addition to the input and output layers, the developed DNN model is composed of four hidden layers. The results showed high predictions capabilities of the proposed method with much lower computational time in comparison to the numerical model.

Original languageEnglish
Pages (from-to)79-87
Number of pages9
JournalComputers, Materials and Continua
Volume59
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Pyramid
B-spline
Neural Network Model
Learning systems
Machine Learning
2-D Systems
Output
Electric Potential
Young's Modulus
Plane Strain
Elastic Material
Permittivity
Shape Function
Nanostructures
Mean Squared Error
Splines
Compression
Grid
Formulation
Evaluate

Keywords

  • Deep neural networks
  • Flexoelectricity
  • Isogeometric analysis
  • Machine learning prediction

ASJC Scopus subject areas

  • Biomaterials
  • Modelling and Simulation
  • Mechanics of Materials
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Computational machine learning representation for the flexoelectricity effect in truncated pyramid structures. / Hamdia, Khader M.; Ghasemi, Hamid; Zhuang, Xiaoying; Alajlan, Naif; Rabczuk, Timon.

In: Computers, Materials and Continua, Vol. 59, No. 1, 01.01.2019, p. 79-87.

Research output: Contribution to journalArticle

Hamdia, Khader M. ; Ghasemi, Hamid ; Zhuang, Xiaoying ; Alajlan, Naif ; Rabczuk, Timon. / Computational machine learning representation for the flexoelectricity effect in truncated pyramid structures. In: Computers, Materials and Continua. 2019 ; Vol. 59, No. 1. pp. 79-87.
@article{f17c65359371477aa8a6f60165638c0c,
title = "Computational machine learning representation for the flexoelectricity effect in truncated pyramid structures",
abstract = "In this study, machine learning representation is introduced to evaluate the flexoelectricity effect in truncated pyramid nanostructure under compression. A NonUniform Rational B-spline (NURBS) based IGA formulation is employed to model the flexoelectricity. We investigate 2D system with an isotropic linear elastic material under plane strain conditions discretized by 45×30 grid of B-spline elements. Six input parameters are selected to construct a deep neural network (DNN) model. They are the Young's modulus, two dielectric permittivity constants, the longitudinal and transversal flexoelectric coefficients and the order of the shape function. The outputs of interest are the strain in the stress direction and the electric potential due flexoelectricity. The dataset are generated from the forward analysis of the flexoelectric model. 80{\%} of the dataset is used for training purpose while the remaining is used for validation by checking the mean squared error. In addition to the input and output layers, the developed DNN model is composed of four hidden layers. The results showed high predictions capabilities of the proposed method with much lower computational time in comparison to the numerical model.",
keywords = "Deep neural networks, Flexoelectricity, Isogeometric analysis, Machine learning prediction",
author = "Hamdia, {Khader M.} and Hamid Ghasemi and Xiaoying Zhuang and Naif Alajlan and Timon Rabczuk",
year = "2019",
month = "1",
day = "1",
doi = "10.32604/cmc.2019.05882",
language = "English",
volume = "59",
pages = "79--87",
journal = "Computers, Materials and Continua",
issn = "1546-2218",
publisher = "Tech Science Press",
number = "1",

}

TY - JOUR

T1 - Computational machine learning representation for the flexoelectricity effect in truncated pyramid structures

AU - Hamdia, Khader M.

AU - Ghasemi, Hamid

AU - Zhuang, Xiaoying

AU - Alajlan, Naif

AU - Rabczuk, Timon

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this study, machine learning representation is introduced to evaluate the flexoelectricity effect in truncated pyramid nanostructure under compression. A NonUniform Rational B-spline (NURBS) based IGA formulation is employed to model the flexoelectricity. We investigate 2D system with an isotropic linear elastic material under plane strain conditions discretized by 45×30 grid of B-spline elements. Six input parameters are selected to construct a deep neural network (DNN) model. They are the Young's modulus, two dielectric permittivity constants, the longitudinal and transversal flexoelectric coefficients and the order of the shape function. The outputs of interest are the strain in the stress direction and the electric potential due flexoelectricity. The dataset are generated from the forward analysis of the flexoelectric model. 80% of the dataset is used for training purpose while the remaining is used for validation by checking the mean squared error. In addition to the input and output layers, the developed DNN model is composed of four hidden layers. The results showed high predictions capabilities of the proposed method with much lower computational time in comparison to the numerical model.

AB - In this study, machine learning representation is introduced to evaluate the flexoelectricity effect in truncated pyramid nanostructure under compression. A NonUniform Rational B-spline (NURBS) based IGA formulation is employed to model the flexoelectricity. We investigate 2D system with an isotropic linear elastic material under plane strain conditions discretized by 45×30 grid of B-spline elements. Six input parameters are selected to construct a deep neural network (DNN) model. They are the Young's modulus, two dielectric permittivity constants, the longitudinal and transversal flexoelectric coefficients and the order of the shape function. The outputs of interest are the strain in the stress direction and the electric potential due flexoelectricity. The dataset are generated from the forward analysis of the flexoelectric model. 80% of the dataset is used for training purpose while the remaining is used for validation by checking the mean squared error. In addition to the input and output layers, the developed DNN model is composed of four hidden layers. The results showed high predictions capabilities of the proposed method with much lower computational time in comparison to the numerical model.

KW - Deep neural networks

KW - Flexoelectricity

KW - Isogeometric analysis

KW - Machine learning prediction

UR - http://www.scopus.com/inward/record.url?scp=85064858465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064858465&partnerID=8YFLogxK

U2 - 10.32604/cmc.2019.05882

DO - 10.32604/cmc.2019.05882

M3 - Article

AN - SCOPUS:85064858465

VL - 59

SP - 79

EP - 87

JO - Computers, Materials and Continua

JF - Computers, Materials and Continua

SN - 1546-2218

IS - 1

ER -