An Application of Neural Network Solutions to Modeling of Diode Laser Assisted Forming Process of AA6082 Thin Sheets


Article Preview

In this paper a neural network approach is used to model the diode laser assisted forming process. In particular thin sheets of Aluminum alloy AA 6082 were bended in the elastic range and then treated with a diode laser with the aim to reduce the spring back phenomenon. Experimental tests were performed to study the influence of the process parameters such as laser power, laser speed and starting elastic deformation on the evolution of forming process. In particular the heating effects on the elastic properties of the material was studied. A statistical approach is used to define the experimental plan and discuss the experimental results. Interesting trend of the effects of the diode laser on the forming process were found. Subsequently in order to predict the residual inflexion, during the laser forming, a multilayer feedforward artificial neural network has been implemented. A sensitivity analysis on the artificial neural network model is used to show the significance of all the input data employed. As a result of sensitivity analysis, a check between experimental and calculated trends for each investigated variables was performed, which revealed an appreciable fit between data displayed.



Main Theme:

Edited by:

F. Micari, M. Geiger, J. Duflou, B. Shirvani, R. Clarke, R. Di Lorenzo and L. Fratini




S. Guarino et al., "An Application of Neural Network Solutions to Modeling of Diode Laser Assisted Forming Process of AA6082 Thin Sheets", Key Engineering Materials, Vol. 344, pp. 325-332, 2007

Online since:

July 2007




[1] Narkeeran Narasimhan, Michael Lovell, Finite Elements in Analysis and Design 33 (1999) 29}42.

DOI: 10.1016/s0168-874x(99)00009-8

[2] F. Lana, J. Chena, J. Linb, Journal of Materials Processing Technology 177 (2006) 382-385.

[3] L.M. Geng, R.H. Wagoner, Int. J. Mech. Sci. 44 (2002) 123-148.

[4] K.P. Li, W.P. Carden, R.H. Wagoner, Simulation of springback, Int. J. Mech. Sci. 44 (2002) 103-122.

[5] F. Lan, J. Chen, J. Lin, et al., J. Plast. Eng. 11 (5) (2004) 78-84.

[6] Yongjun Shi, Zhenqiang Yao, Hong Shen, Jun Hu, International Journal of Machine Tools & Manufacture 46 (2006) 1689-1697.

DOI: 10.1016/j.ijmachtools.2005.09.016

[7] Edson Costa Santos, Masanari Shiomi, _, Kozo Osakada, Tahar Laoui, International Journal of Machine Tools & Manufacture 46 (2006) 1459-1468.

DOI: 10.1016/j.ijmachtools.2005.09.005

[8] Hong Shen , Yongjun Shi, Zhenqiang Yao, Jun Hu, Computational Materials Science 37 (2006) 593-598.

DOI: 10.1016/j.commatsci.2005.12.030

[9] A.J. Skinner, J.Q. Broughton, Modelling Simul. Mater Sci Eng. 3 (1995) pp.371-390.

[10] S. Pernot, C. H. Lamarque, Neural Networks 12 (1999) pp.371-392.

[11] K. Levenberg, Quart. Appl. Math. 2 (1944) pp.164-168.

[12] D. Marquardt, J. Soc. Ind. Appl. Math. 11 (1963) pp.431-441.

Fetching data from Crossref.
This may take some time to load.