A Study on Barreling Behavior during Upsetting Process using Artificial Neural Networks with Levenberg Algorithm
In this paper back-propagation artificial neural network
(BPANN )with Levenberg–Marquardt algorithm is employed to
predict the deformation of the upsetting process. To prepare a
training set for BPANN, some finite element simulations were
carried out. The input data for the artificial neural network are a set
of parameters generated randomly (aspect ratio d/h, material
properties, temperature and coefficient of friction). The output data
are the coefficient of polynomial that fitted on barreling curves.
Neural network was trained using barreling curves generated by
finite element simulations of the upsetting and the corresponding
material parameters. This technique was tested for three different
specimens and can be successfully employed to predict the
deformation of the upsetting process
[1] N. Selvakumar, P. Ganesan, P. Radha, , R. Narayanasamy, and K.S.
Pandey, "Modelling the effect of particle size and iron content on
forming of Al-Fe composite preforms using neural network", Materials
& Design, Volume 28, Issue 1. 2007, Pages 119-130
[2] Siamak Serajzade, "Prediction of temperature distribution and required
energy in hot forging process by coupling neural networks and finite
element analysis",,MaterialsLetters Volume 61, Issues 14-15
[3] Siamak Serajzadeh"Prediction of thermo- mechanical behavior during
hot upsetting using neural networks" Materials Science and Engineering
in press 2008, Pages 140-147
[4] Zhihong Huanga, Margaret Lucasa, Michael J. Adam Modelling wall
boundary conditions in an elasto-viscoplastic material forming
processJournal of Materials Processing Technology 107 (2000) 267-275.
[5] Elman, J. L., "Finding structure in time", Cognitive Science, vol. 14,
pp.179-211,1990
[6] j.SI," theory and application of supervised learning method based on
gradiant algorithms", J tsinghau univ.vol 37,1997
[7] M.T.HAGEN,"training feed forward network with the levenbergmarquardt
algorithm", IEEE, pp 989-993, 1994.
[1] N. Selvakumar, P. Ganesan, P. Radha, , R. Narayanasamy, and K.S.
Pandey, "Modelling the effect of particle size and iron content on
forming of Al-Fe composite preforms using neural network", Materials
& Design, Volume 28, Issue 1. 2007, Pages 119-130
[2] Siamak Serajzade, "Prediction of temperature distribution and required
energy in hot forging process by coupling neural networks and finite
element analysis",,MaterialsLetters Volume 61, Issues 14-15
[3] Siamak Serajzadeh"Prediction of thermo- mechanical behavior during
hot upsetting using neural networks" Materials Science and Engineering
in press 2008, Pages 140-147
[4] Zhihong Huanga, Margaret Lucasa, Michael J. Adam Modelling wall
boundary conditions in an elasto-viscoplastic material forming
processJournal of Materials Processing Technology 107 (2000) 267-275.
[5] Elman, J. L., "Finding structure in time", Cognitive Science, vol. 14,
pp.179-211,1990
[6] j.SI," theory and application of supervised learning method based on
gradiant algorithms", J tsinghau univ.vol 37,1997
[7] M.T.HAGEN,"training feed forward network with the levenbergmarquardt
algorithm", IEEE, pp 989-993, 1994.
@article{"International Journal of Engineering, Mathematical and Physical Sciences:59686", author = "H.Mohammadi Majd and M.Jalali Azizpour", title = "A Study on Barreling Behavior during Upsetting Process using Artificial Neural Networks with Levenberg Algorithm", abstract = "In this paper back-propagation artificial neural network
(BPANN )with Levenberg–Marquardt algorithm is employed to
predict the deformation of the upsetting process. To prepare a
training set for BPANN, some finite element simulations were
carried out. The input data for the artificial neural network are a set
of parameters generated randomly (aspect ratio d/h, material
properties, temperature and coefficient of friction). The output data
are the coefficient of polynomial that fitted on barreling curves.
Neural network was trained using barreling curves generated by
finite element simulations of the upsetting and the corresponding
material parameters. This technique was tested for three different
specimens and can be successfully employed to predict the
deformation of the upsetting process", keywords = "Back-propagation artificial neural network(BPANN), prediction, upsetting", volume = "5", number = "6", pages = "860-4", }