Prediction of residual stress profile and optimization of surface conditions induced by laser shock peening process using artificial neural networks
- 40 Downloads
The purpose of this paper is to predict the compressive residual stress profile induced by the laser shock peening process and to optimize the surface conditions on a Ti-6Al-4V titanium super-alloy using the new technology based on the artificial neural networks. This study covers two principal cases: (i) The numerical analysis: the compressive residual stress distribution induced by the laser peening process is simulated based on the finite element method using ABAQUS software (ABAQUS/Explicit code). (ii) The mathematical modeling analysis: the using of the artificial neural network technique has been proposed to predict the residual stress profile induced by the laser shock processing in order to optimize the laser shock peening surface conditions. To train the artificial neural network, we use different numerical experiments measurements as training and test data. The best fitting training data set was obtained with four neurons in the hidden layers. After training and as seen from the mathematical experiments, the calculated residual stress and the damage state are obviously acceptable. The principal goal of this research paper is to predict the surface treatment state induced by the laser shock peening based on the artificial neural networks technique and on the numerical results without making multiple simulations that can take much more time.
KeywordsLaser shock peening Artificial neural network Finite element method Optimal condition Compressive residual stress Prediction
Unable to display preview. Download preview PDF.
This work is carried out thanks to the support and funding allocated to the Unit of Mechanical and Materials Production Engineering (UGPMM/UR17ES43) by the Tunisian Ministry of Higher Education and Scientific Research.
- 4.Ayeb M (2018) Développement d'un modèle de prévision de l'état induit du traitement. Editions universitaires européennes EUE. p 92Google Scholar
- 5.Kay G (2003) Failure modeling of titanium 6Al-4V and aluminum 2024-T3 with the Johnson-Cook material model. Office of Aviation Research, Washington, D.C., p 20591Google Scholar
- 6.Johnson GR, Cook WH (1983) A constitutive model and data for metals subjected to large strains, high strain rates and high temperatures, Proceedings of the 7th International Symposium on Ballistics 54, pp. 541–547Google Scholar
- 11.Ghabeche W (2005) Etude par réseaux de neurones de comportement mécanique d’un matériau ductile—application au HDPE—, Faculté des Sciences, Universite Badji Mokhtar Annaba, Algeria, p 55Google Scholar