Evolutionary Computing for Metals Properties Modelling


Article Preview

During the last decade Genetic Programming (GP) has emerged as an efficient methodology for teaching computers how to program themselves. This paper presents research work which utilizes GP for developing mathematical equations for the response surfaces that have been generated using hybrid modelling techniques for predicting the properties of materials under hot deformation. Collected data from the literature and experimental work on aluminium are utilized as the initial training data for the GP to develop the mathematical models under different deformation conditions and compositions.



Materials Science Forum (Volumes 539-543)

Main Theme:

Edited by:

T. Chandra, K. Tsuzaki, M. Militzer , C. Ravindran




M. F. Abbod et al., "Evolutionary Computing for Metals Properties Modelling", Materials Science Forum, Vols. 539-543, pp. 2449-2454, 2007

Online since:

March 2007




[1] N.L. Cramer: A representation for the adaptive generation of simple sequential programs. In J. J. Grefenstette, ed., Proceedings of the First International Conference on Genetic Algorithms and Their Applications, Erlbaum (1985).

[2] J.R. Koza: Genetic Programming: On the programming of computers by means of natural selection, Cambridge, MA: MIT Press (1992).

[3] C. Ferreira: Gene expression programming: a new adaptive algorithm for solving problems. Complex Systems (2001).

[4] M.F. Abbod, D.A. Linkens and Q. Zhu: Semi-physical modeling of internal states for aluminium alloys. Materials Science and Technology, Vol A333 (2002) pp.397-408.

[5] Zhu, Q., M.F. Abbod, J. Talamantes-Silva, C.M. Sellars, D.A. Linkens and J.H. Beynon: Hybrid modeling of aluminum-magnesium alloys during thermomechanical processing in terms of physically-based, neuro-fuzzy and finite elements models", Acta Mat, Vol 51 (2003).

DOI: https://doi.org/10.1016/s1359-6454(03)00353-7