Identification and optimization of AB2 phases using principal component analysis, evolutionary neural nets, and multiobjective genetic algorithms

Akash Agarwal, Frank Pettersson, Arunima Singh, Chang Sun Kong, Henrik Saxén, Krishna Rajan, Shuichi Iwata, Nirupam Chakraborti

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Available data for a large number of AB2 compounds were subjected to a rigorous study using a combination of Principal Component Analysis (PCA) technique, multiobjective genetic algorithms, and neural networks that evolved through genetic algorithms. The identification of various phases and phase-groups were very successfully done using a decision tree approach. Since the variable hyperspaces for the different phases were highly intersecting in nature, a cumulative probability index was defined for the formation of individual compounds, which was maximized along with Pauling's electronegativity difference. The resulting Pareto-frontiers provided further insight into the nature of bonding prevailing in these compounds.

Original languageEnglish (US)
Pages (from-to)274-281
Number of pages8
JournalMaterials and Manufacturing Processes
Volume24
Issue number3
DOIs
StatePublished - Mar 1 2009
Externally publishedYes

Fingerprint

Principal component analysis
Genetic algorithms
Neural networks
Electronegativity
Decision trees
AB-2 compound

Keywords

  • AB2 compounds
  • Data mining
  • Decision tree
  • Evolutionary algorithm
  • Genetic algorithms
  • Laves phase
  • Multiobjective optimization
  • Neural network
  • Principal component analysis

ASJC Scopus subject areas

  • Materials Science(all)
  • Mechanics of Materials
  • Mechanical Engineering
  • Industrial and Manufacturing Engineering

Cite this

Identification and optimization of AB2 phases using principal component analysis, evolutionary neural nets, and multiobjective genetic algorithms. / Agarwal, Akash; Pettersson, Frank; Singh, Arunima; Kong, Chang Sun; Saxén, Henrik; Rajan, Krishna; Iwata, Shuichi; Chakraborti, Nirupam.

In: Materials and Manufacturing Processes, Vol. 24, No. 3, 01.03.2009, p. 274-281.

Research output: Contribution to journalArticle

Agarwal, Akash ; Pettersson, Frank ; Singh, Arunima ; Kong, Chang Sun ; Saxén, Henrik ; Rajan, Krishna ; Iwata, Shuichi ; Chakraborti, Nirupam. / Identification and optimization of AB2 phases using principal component analysis, evolutionary neural nets, and multiobjective genetic algorithms. In: Materials and Manufacturing Processes. 2009 ; Vol. 24, No. 3. pp. 274-281.
@article{491a57313a2b4b8aa0232cebc46bd4bc,
title = "Identification and optimization of AB2 phases using principal component analysis, evolutionary neural nets, and multiobjective genetic algorithms",
abstract = "Available data for a large number of AB2 compounds were subjected to a rigorous study using a combination of Principal Component Analysis (PCA) technique, multiobjective genetic algorithms, and neural networks that evolved through genetic algorithms. The identification of various phases and phase-groups were very successfully done using a decision tree approach. Since the variable hyperspaces for the different phases were highly intersecting in nature, a cumulative probability index was defined for the formation of individual compounds, which was maximized along with Pauling's electronegativity difference. The resulting Pareto-frontiers provided further insight into the nature of bonding prevailing in these compounds.",
keywords = "AB2 compounds, Data mining, Decision tree, Evolutionary algorithm, Genetic algorithms, Laves phase, Multiobjective optimization, Neural network, Principal component analysis",
author = "Akash Agarwal and Frank Pettersson and Arunima Singh and Kong, {Chang Sun} and Henrik Sax{\'e}n and Krishna Rajan and Shuichi Iwata and Nirupam Chakraborti",
year = "2009",
month = "3",
day = "1",
doi = "10.1080/10426910802678321",
language = "English (US)",
volume = "24",
pages = "274--281",
journal = "Materials and Manufacturing Processes",
issn = "1042-6914",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Identification and optimization of AB2 phases using principal component analysis, evolutionary neural nets, and multiobjective genetic algorithms

AU - Agarwal, Akash

AU - Pettersson, Frank

AU - Singh, Arunima

AU - Kong, Chang Sun

AU - Saxén, Henrik

AU - Rajan, Krishna

AU - Iwata, Shuichi

AU - Chakraborti, Nirupam

PY - 2009/3/1

Y1 - 2009/3/1

N2 - Available data for a large number of AB2 compounds were subjected to a rigorous study using a combination of Principal Component Analysis (PCA) technique, multiobjective genetic algorithms, and neural networks that evolved through genetic algorithms. The identification of various phases and phase-groups were very successfully done using a decision tree approach. Since the variable hyperspaces for the different phases were highly intersecting in nature, a cumulative probability index was defined for the formation of individual compounds, which was maximized along with Pauling's electronegativity difference. The resulting Pareto-frontiers provided further insight into the nature of bonding prevailing in these compounds.

AB - Available data for a large number of AB2 compounds were subjected to a rigorous study using a combination of Principal Component Analysis (PCA) technique, multiobjective genetic algorithms, and neural networks that evolved through genetic algorithms. The identification of various phases and phase-groups were very successfully done using a decision tree approach. Since the variable hyperspaces for the different phases were highly intersecting in nature, a cumulative probability index was defined for the formation of individual compounds, which was maximized along with Pauling's electronegativity difference. The resulting Pareto-frontiers provided further insight into the nature of bonding prevailing in these compounds.

KW - AB2 compounds

KW - Data mining

KW - Decision tree

KW - Evolutionary algorithm

KW - Genetic algorithms

KW - Laves phase

KW - Multiobjective optimization

KW - Neural network

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=61449104901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61449104901&partnerID=8YFLogxK

U2 - 10.1080/10426910802678321

DO - 10.1080/10426910802678321

M3 - Article

AN - SCOPUS:61449104901

VL - 24

SP - 274

EP - 281

JO - Materials and Manufacturing Processes

JF - Materials and Manufacturing Processes

SN - 1042-6914

IS - 3

ER -