Application of radial basis neural network to transform viscoelastic to elastic properties for materials with multiple thermal transitions

Xianbo Xu, Nikhil Gupta

Research output: Contribution to journalArticle

Abstract

Dynamic mechanical analysis is a method to characterize the frequency domain viscoelastic properties including storage and loss moduli. Methods have been developed to transform these properties to time domain and extract elastic modulus over strain rates, which is useful in mechanical design. However, application of these methods becomes increasingly complex for materials containing multiple thermal transitions. Neural networks can provide advantages in solving such problems. As the form of radial basis neural network satisfies the form obtained from time–temperature superposition principle, it is used in the present work with back-propagation to establish the master relation of loss modulus. The influence of regulation factor and neuron number is investigated to find the best parameter set. Then, storage modulus is divided into frequency-dependent and frequency-independent part. Both parts are individually calculated from loss modulus using Kramers–Kronig relation. The linear integral relation of viscoelasticity can transform the storage modulus into time-domain relaxation modulus, which can predict the stress response with specific strain history and temperature. The transformation is tested on ethylene–vinyl acetate. The time-domain elastic properties are extracted and compared with those from tensile tests at room temperature. The transformation achieves an average root mean square error of 3.3% and a maximum error 4.9% between strain rates 10 −6 to 10 −2  s −1 . This process can predict the properties at a wide range of temperatures and frequencies from a single specimen and can be implemented using parallel computing, which is promising for complex material systems.

Original languageEnglish (US)
JournalJournal of Materials Science
DOIs
StatePublished - Jan 1 2019

Fingerprint

Elastic moduli
Neural networks
Strain rate
Viscoelasticity
Dynamic mechanical analysis
Parallel processing systems
Backpropagation
Mean square error
Temperature
Neurons
Acetates
Hot Temperature

ASJC Scopus subject areas

  • Materials Science(all)
  • Mechanics of Materials
  • Mechanical Engineering

Cite this

@article{dcb8228a19d14593a60189c67dd24ac6,
title = "Application of radial basis neural network to transform viscoelastic to elastic properties for materials with multiple thermal transitions",
abstract = "Dynamic mechanical analysis is a method to characterize the frequency domain viscoelastic properties including storage and loss moduli. Methods have been developed to transform these properties to time domain and extract elastic modulus over strain rates, which is useful in mechanical design. However, application of these methods becomes increasingly complex for materials containing multiple thermal transitions. Neural networks can provide advantages in solving such problems. As the form of radial basis neural network satisfies the form obtained from time–temperature superposition principle, it is used in the present work with back-propagation to establish the master relation of loss modulus. The influence of regulation factor and neuron number is investigated to find the best parameter set. Then, storage modulus is divided into frequency-dependent and frequency-independent part. Both parts are individually calculated from loss modulus using Kramers–Kronig relation. The linear integral relation of viscoelasticity can transform the storage modulus into time-domain relaxation modulus, which can predict the stress response with specific strain history and temperature. The transformation is tested on ethylene–vinyl acetate. The time-domain elastic properties are extracted and compared with those from tensile tests at room temperature. The transformation achieves an average root mean square error of 3.3{\%} and a maximum error 4.9{\%} between strain rates 10 −6 to 10 −2  s −1 . This process can predict the properties at a wide range of temperatures and frequencies from a single specimen and can be implemented using parallel computing, which is promising for complex material systems.",
author = "Xianbo Xu and Nikhil Gupta",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s10853-019-03481-0",
language = "English (US)",
journal = "Journal of Materials Science",
issn = "0022-2461",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Application of radial basis neural network to transform viscoelastic to elastic properties for materials with multiple thermal transitions

AU - Xu, Xianbo

AU - Gupta, Nikhil

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Dynamic mechanical analysis is a method to characterize the frequency domain viscoelastic properties including storage and loss moduli. Methods have been developed to transform these properties to time domain and extract elastic modulus over strain rates, which is useful in mechanical design. However, application of these methods becomes increasingly complex for materials containing multiple thermal transitions. Neural networks can provide advantages in solving such problems. As the form of radial basis neural network satisfies the form obtained from time–temperature superposition principle, it is used in the present work with back-propagation to establish the master relation of loss modulus. The influence of regulation factor and neuron number is investigated to find the best parameter set. Then, storage modulus is divided into frequency-dependent and frequency-independent part. Both parts are individually calculated from loss modulus using Kramers–Kronig relation. The linear integral relation of viscoelasticity can transform the storage modulus into time-domain relaxation modulus, which can predict the stress response with specific strain history and temperature. The transformation is tested on ethylene–vinyl acetate. The time-domain elastic properties are extracted and compared with those from tensile tests at room temperature. The transformation achieves an average root mean square error of 3.3% and a maximum error 4.9% between strain rates 10 −6 to 10 −2  s −1 . This process can predict the properties at a wide range of temperatures and frequencies from a single specimen and can be implemented using parallel computing, which is promising for complex material systems.

AB - Dynamic mechanical analysis is a method to characterize the frequency domain viscoelastic properties including storage and loss moduli. Methods have been developed to transform these properties to time domain and extract elastic modulus over strain rates, which is useful in mechanical design. However, application of these methods becomes increasingly complex for materials containing multiple thermal transitions. Neural networks can provide advantages in solving such problems. As the form of radial basis neural network satisfies the form obtained from time–temperature superposition principle, it is used in the present work with back-propagation to establish the master relation of loss modulus. The influence of regulation factor and neuron number is investigated to find the best parameter set. Then, storage modulus is divided into frequency-dependent and frequency-independent part. Both parts are individually calculated from loss modulus using Kramers–Kronig relation. The linear integral relation of viscoelasticity can transform the storage modulus into time-domain relaxation modulus, which can predict the stress response with specific strain history and temperature. The transformation is tested on ethylene–vinyl acetate. The time-domain elastic properties are extracted and compared with those from tensile tests at room temperature. The transformation achieves an average root mean square error of 3.3% and a maximum error 4.9% between strain rates 10 −6 to 10 −2  s −1 . This process can predict the properties at a wide range of temperatures and frequencies from a single specimen and can be implemented using parallel computing, which is promising for complex material systems.

UR - http://www.scopus.com/inward/record.url?scp=85062079308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062079308&partnerID=8YFLogxK

U2 - 10.1007/s10853-019-03481-0

DO - 10.1007/s10853-019-03481-0

M3 - Article

AN - SCOPUS:85062079308

JO - Journal of Materials Science

JF - Journal of Materials Science

SN - 0022-2461

ER -