Analyzing Fe-Zn system using molecular dynamics, evolutionary neural nets and multi-objective genetic algorithms

Baidurya Bhattacharya, G. R. Dinesh Kumar, Akash Agarwal, Şakir Erkoç, Arunima Singh, Nirupam Chakraborti

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Failure behavior of Zn coated Fe is simulated through molecular dynamics (MD) and the energy absorbed at the onset of failure along with the corresponding strain of the Zn lattice are computed for different levels of applied shear rate, temperature and thickness. Data-driven models are constructed by feeding the MD results to an evolutionary neural network. The outputs of these neural networks are utilized to carry out a multi-objective optimization through genetic algorithms, where the best possible tradeoffs between two conflicting requirements, minimum deformation and maximum energy absorption at the onset of failure, are determined by constructing a Pareto frontier.

Original languageEnglish (US)
Pages (from-to)821-827
Number of pages7
JournalComputational Materials Science
Volume46
Issue number4
DOIs
StatePublished - Oct 1 2009
Externally publishedYes

Fingerprint

neural nets
Neural Nets
Multi-objective Genetic Algorithm
Molecular Dynamics
System Dynamics
genetic algorithms
Molecular dynamics
Genetic algorithms
molecular dynamics
Neural networks
Energy absorption
Multiobjective optimization
Evolutionary Neural Networks
Shear deformation
Energy Absorption
energy absorption
tradeoffs
Pareto
Data-driven
Multi-objective Optimization

Keywords

  • Artificial neural networks
  • Fe-Zn system
  • Genetic algorithms
  • Hot-dip galvanizing
  • Molecular dynamics
  • Multi-objective optimization

ASJC Scopus subject areas

  • Computer Science(all)
  • Chemistry(all)
  • Materials Science(all)
  • Mechanics of Materials
  • Physics and Astronomy(all)
  • Computational Mathematics

Cite this

Analyzing Fe-Zn system using molecular dynamics, evolutionary neural nets and multi-objective genetic algorithms. / Bhattacharya, Baidurya; Dinesh Kumar, G. R.; Agarwal, Akash; Erkoç, Şakir; Singh, Arunima; Chakraborti, Nirupam.

In: Computational Materials Science, Vol. 46, No. 4, 01.10.2009, p. 821-827.

Research output: Contribution to journalArticle

Bhattacharya, Baidurya ; Dinesh Kumar, G. R. ; Agarwal, Akash ; Erkoç, Şakir ; Singh, Arunima ; Chakraborti, Nirupam. / Analyzing Fe-Zn system using molecular dynamics, evolutionary neural nets and multi-objective genetic algorithms. In: Computational Materials Science. 2009 ; Vol. 46, No. 4. pp. 821-827.
@article{d77ea90e60ec4202a8b6286b7dde5f88,
title = "Analyzing Fe-Zn system using molecular dynamics, evolutionary neural nets and multi-objective genetic algorithms",
abstract = "Failure behavior of Zn coated Fe is simulated through molecular dynamics (MD) and the energy absorbed at the onset of failure along with the corresponding strain of the Zn lattice are computed for different levels of applied shear rate, temperature and thickness. Data-driven models are constructed by feeding the MD results to an evolutionary neural network. The outputs of these neural networks are utilized to carry out a multi-objective optimization through genetic algorithms, where the best possible tradeoffs between two conflicting requirements, minimum deformation and maximum energy absorption at the onset of failure, are determined by constructing a Pareto frontier.",
keywords = "Artificial neural networks, Fe-Zn system, Genetic algorithms, Hot-dip galvanizing, Molecular dynamics, Multi-objective optimization",
author = "Baidurya Bhattacharya and {Dinesh Kumar}, {G. R.} and Akash Agarwal and Şakir Erko{\cc} and Arunima Singh and Nirupam Chakraborti",
year = "2009",
month = "10",
day = "1",
doi = "10.1016/j.commatsci.2009.04.023",
language = "English (US)",
volume = "46",
pages = "821--827",
journal = "Computational Materials Science",
issn = "0927-0256",
publisher = "Elsevier",
number = "4",

}

TY - JOUR

T1 - Analyzing Fe-Zn system using molecular dynamics, evolutionary neural nets and multi-objective genetic algorithms

AU - Bhattacharya, Baidurya

AU - Dinesh Kumar, G. R.

AU - Agarwal, Akash

AU - Erkoç, Şakir

AU - Singh, Arunima

AU - Chakraborti, Nirupam

PY - 2009/10/1

Y1 - 2009/10/1

N2 - Failure behavior of Zn coated Fe is simulated through molecular dynamics (MD) and the energy absorbed at the onset of failure along with the corresponding strain of the Zn lattice are computed for different levels of applied shear rate, temperature and thickness. Data-driven models are constructed by feeding the MD results to an evolutionary neural network. The outputs of these neural networks are utilized to carry out a multi-objective optimization through genetic algorithms, where the best possible tradeoffs between two conflicting requirements, minimum deformation and maximum energy absorption at the onset of failure, are determined by constructing a Pareto frontier.

AB - Failure behavior of Zn coated Fe is simulated through molecular dynamics (MD) and the energy absorbed at the onset of failure along with the corresponding strain of the Zn lattice are computed for different levels of applied shear rate, temperature and thickness. Data-driven models are constructed by feeding the MD results to an evolutionary neural network. The outputs of these neural networks are utilized to carry out a multi-objective optimization through genetic algorithms, where the best possible tradeoffs between two conflicting requirements, minimum deformation and maximum energy absorption at the onset of failure, are determined by constructing a Pareto frontier.

KW - Artificial neural networks

KW - Fe-Zn system

KW - Genetic algorithms

KW - Hot-dip galvanizing

KW - Molecular dynamics

KW - Multi-objective optimization

UR - http://www.scopus.com/inward/record.url?scp=70249094618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70249094618&partnerID=8YFLogxK

U2 - 10.1016/j.commatsci.2009.04.023

DO - 10.1016/j.commatsci.2009.04.023

M3 - Article

AN - SCOPUS:70249094618

VL - 46

SP - 821

EP - 827

JO - Computational Materials Science

JF - Computational Materials Science

SN - 0927-0256

IS - 4

ER -