Damage Material Parameters Identification Using the ANN-GA Method and the Bulge Test

Abstract:

The simulation of the metal forming processes requires accurate constitutive models describing the material behaviour at finite strain, and taking into account several conditions. The choice of a rheological model and the determination of its parameters should be made from a test that generates such conditions. The major difficulty encountered is that there is no experimental test satisfying all these criteria. The use of more than one test seems well adapted, and is utilized to characterize the rheological behaviour at operating conditions corresponding to metal forming applications. Inverse analysis is then considered. Therefore, the difficulty lies with the long computing time that was taken when an optimization procedure is coupled with a finite element computation (FEC) to identify the material parameters. In order to solve the computing time problem, this paper proposes a hybrid identification method based on an artificial neural network and a genetic algorithm (ANN-GA). The proposed strategy is applied to identify the damage material parameters of the AISI 304 steel and using the bulge test.

• Periodical: Key Engineering Materials (Volumes 554-557)
• Pages: 928-935
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.554-557.928
• Online since: June 2013
• Authors: Hamdi Aguir, Hedi Bel Hadj Salah
• Keywords: Artificial Neural Network (ANN), Bulge Test, Damage Model, Genetic Algorithm (GA), Inverse Identification, Metal Forming

References

[1] M. Springmann, M. Kuna, Identification of material parameters of the Rousselier model by non-linear optimization, Computational Materials Science. 26 (2003) 202-209.

DOI: 10.1016/s0927-0256(02)00400-7

[2] B.M. Chaparro, S. Thulillier, L.F. Menezes, P.Y. Manach, J.V. Fernandes, Material parameters identification: gradient-based, genetic and hybrid optimization algorithms, Computational Material Science. 44 (2008) 339-346.

DOI: 10.1016/j.commatsci.2008.03.028

[3] H. Aguir, J.L. Alves, M.C. Oliveira, L.F. Menezes, H. BelHadjSalah, Cazacu and Barlat criterion identification using the cylindrical cup deep drawing test and the coupled artificial neural networks–genetic algorithm method, Key Engineering Materials. 504-506 (2012) 637-642.

DOI: 10.4028/www.scientific.net/kem.504-506.637

[4] J. Lemaître J.L. Chaboche, Mécanique des matériaux solides, Editions Dunod, Paris-France, 1985.

[5] H. Badreddine, Elastoplasticité anisotrope endommageable en transformations finie: Aspects théoriques, numériques et applications, Thèse de doctorat, Université de Technologie de Troyes, 2006.

[6] H. Aguir, A. Chamekh, H. BelHadjSalah, A.Dogui and R.Hambli, Parameter Identification of a Non associative Elasto-plastic Constitutive Model Using ANN and Multi-objective Optimization, International Journal of Material Forming. 2 (2009) 75-82.

DOI: 10.1007/s12289-009-0392-1