Estimation of Tailor-Welded Blank Parameters for Acceptable Tensile Behaviour Using ANN
The tensile and forming behavior of Tailor-welded blanks (TWB) is influenced by many parameters like thickness ratio, strength ratio, and weld conditions in a synergistic fashion. It is necessary to predict suitable TWB conditions for achieving better stamped product made of welded blanks. This work primarily aims at developing an artificial neural network (ANN) model to predict the TWB parameters for acceptable tensile behavior of welded blanks made of steel grade and aluminium alloy base materials. The important tensile characteristics of TWB like limit strains, failure location, minimum thickness, strain path are considered within chosen range of varied blank and weld condition. Through out the work, ABAQUS 6.7-2® finite element (FE) code is used to simulate the tensile behavior and to generate data required for training the ANN. Predicted results from ANN model are compared and validated with FE simulation. The predictions from ANN are with acceptable prediction errors.
KeywordsTWB Parameters Inverse Modeling Neural Networks Parameter Estimation
- 1.The Ultra Light Steel Auto body, http://www.ulsab.org
- 3.Anand, D., Boudreau, G., Andreychuk, P., Chen, D.L., Bhole, S.D.: Forming Behaviour of Tailor (Laser) Welded Blanks of Automotive Steel Sheet. Canadian J. Metallurgy and Mat. Sc. 45(2), 187–197 (2006)Google Scholar
- 7.Saravana Kumar, G., Kalra, P.K., Dhande, S.G.: Parameter Estimation for B-spline Curve Fitting using Neural Networks. In: 2nd International Conference on CIRAS, Singapore, p. 127 (2003)Google Scholar