Identification and Optimization of AB2 Phases Using Principal Component Analysis, Evolutionary Neural Nets, and Multiobjective Genetic Algorithms

A1 Originalartikel i en vetenskaplig tidskrift (referentgranskad)

Interna författare/redaktörer

Publikationens författare: Agarwal A, Pettersson F, Singh A, Kong CS, Saxen H, Rajan K, Iwata S, Chakraborti N
Publiceringsår: 2009
Tidskrift: Materials and Manufacturing Processes
Tidskriftsakronym: MATER MANUF PROCESS
Volym: 24
Nummer: 3
Artikelns första sida, sidnummer: 274
Artikelns sista sida, sidnummer: 281
Antal sidor: 8
ISSN: 1042-6914


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.


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

Senast uppdaterad 2020-22-02 vid 06:02