Yield strength modelling of formed material using evolutionary computational method

Leo Gusel (Avtor), Rebeka Rudolf (Avtor)

Povzetek

In this paper we propose an evolutionary computation approach for the modelling of yield strength in formed material. One of the most general evolutionary computation methods is genetic programming, which was used in our research. Genetic programming is an automated method for creating a working computer program from a problemćs high-level statement. Genetic programming does this by genetically breeding a population of computer programs using the principles of Darwinianćs natural selection and biologically inspired operations. During our research, material was cold formed by drawing using different process parameters and then determining yield strengths (dependent variable) of the specimens. On the basis of a training data set, various different genetic models for yield strength distribution were developed during simulated evolution. The accuracies of the best models were proved by a testing data set and comparing between the genetic and regression models. The research showed that very accurate genetic models can be developed by the proposed approach.

Ključne besede

metal forming;yield strength;genetic programming;modelling;

Podatki

Jezik:	Angleški jezik
Leto izida:	2009
Tipologija:	1.01 - Izvirni znanstveni članek
Organizacija:	UM FS - Fakulteta za strojništvo
UDK:	620.1
COBISS:	13042966
ISSN:	0354-6306
Št. ogledov:	1762
Št. prenosov:	30
Ocena:	0 (0 glasov)
Metapodatki:

Ostali podatki

Sekundarni jezik:	Angleški jezik
URN:	URN:SI:UM:
Strani:	str. 29-37
Letnik:	ǂVol. ǂ15
Zvezek:	ǂbr. ǂ1
Čas izdaje:	2009
Ključne besede (UDK):	applied sciences;medicine;technology;uporabne znanosti;medicina;tehnika;engineering;technology in general;inženirstvo;tehnologija na splošno;materials testing;commercial materials;power stations;economics of energy;preiskava materiala;blagoznanstvo;energetske centrale;energetika;
ID:	990852