The Use of genetic algorithm and neural network to predict rate-dependent tensile flow behaviour of AA5182-O sheets

• Published in: Materials & design Vol. 94; pp. 262 - 273
• Main Authors: Jenab, Arash, Sari Sarraf, Iman, Green, Daniel E., Rahmaan, Taamjeed, Worswick, Michael J.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.03.2016
• Subjects: 5000 series aluminium alloys; Accuracy; Aluminum base alloys; Artificial neural network; Computer simulation; Constitutive relationships; Genetic algorithm; Genetic algorithms; Mathematical models; Moderate strain rates; Neural networks; Phenomenological constitutive model; Tensile tests; Artificial neural network; Genetic algorithm; 5000 series aluminium alloys; Phenomenological constitutive model; Moderate strain rates
• ISSN: 0264-1275; 1873-4197
• DOI: 10.1016/j.matdes.2016.01.038

In this study, the tensile flow behaviour of AA5182-O sheet was experimentally obtained in different material directions (RD, DD, and TD) at strain rates ranging from 0.001 to 1000s−1 and predicted by means of both phenomenological models and neural networks (NNs). Constants in Johnson–Cook (JC), Khan–Huang–Liang (KHL), and modified Voce were calculated using genetic algorithm (GA) and linear regression analysis and used to simulate the uniaxial tension tests. Two types of feed-forward back-propagation neural networks were also trained and validated to predict the rheological behaviour of the alloy without the limitations of a mathematical function. The weights and bias values of each network were then used to simulate uniaxial tensile deformation. Subsequently, the results were compared with experimental flow curves and accuracy parameters were calculated. It was found that the modified Voce constitutive equation was able to predict the flow behaviour of AA5182-O with better accuracy than JC and KHL models. Also, the NN was found to be the most accurate method of predicting the anisotropic rate-dependant behaviour of AA5182-O. [Display omitted] •At high strain rates, flow stress of AA5182-O increases with increasing strain rate.•Phenomenological models are able to reasonably predict flow behaviour of AA5182-O.•Modified Voce gives better predictions when compared with KHL and JC models.•ANN exhibit the most accurate flow behaviour predictions when used in FE simulations.