Identification of factors governing mechanical properties of TRIP-aided steel using genetic algorithms and neural networks

A1 Journal article (refereed)


Internal Authors/Editors


Publication Details

List of Authors: Datta S, Pettersson F, Ganguly S, Saxen H, Chakraborti N
Publisher: TAYLOR & FRANCIS INC
Publication year: 2008
Journal: Materials and Manufacturing Processes
Journal acronym: MATER MANUF PROCESS
Volume number: 23
Issue number: 2
Start page: 130
End page: 137
Number of pages: 8
ISSN: 1042-6914


Abstract

Mechanical properties of transformation induced plasticity (TRIP)-aided multiphase steels are modeled by neural networks using two methods of reducing the network connectivity, viz. a pruning algorithm and a predator prey algorithm, to gain understanding on the impact of steel composition and treatment. The pruning algorithm gradually reduces the complexity of the lower layer of connections, removing less significant connections. In the predator prey algorithm, a genetic algorithm based multi-objective optimization technique evolves neural networks on a Pareto front, simultaneously minimizing training error and network size. The results show that the techniques find parsimonious models and, furthermore, extract useful knowledge from the data.


Keywords

alloy design, evolutionary algorithms, genetic algorithms, multi-objective optimization, neural network, predator-prey, pruning algorithm, TRIP-aided steel

Last updated on 2019-14-11 at 03:32