Design of T-shaped tube hydroforming using finite element and artificial neural network modeling

Tube hydroforming (THF) is a frequently used manufacturing method in the industry, especially on automotive and aircraft industries. Compared with other manufacturing processes, THF provides parts with better quality and lower production costs. This paper proposes a design approach to estimate the T-shaped THF parameters, such as counter force, axial feed, and internal pressure, through finite element (FE) and artificial neural network (ANN) modeling. A numerical database is built through Taguchi’s L27 orthogonal array of experiments to train the ANN. The micromechanical damage model of Gurson-Tvergaard-Needleman is used with an elastoplastic approach to describe the material behavior. This study aims to find the combinations of THF parameters that maximize the bulge ratio and minimize the thinning ratio and wrinkling. The numerical results obtained by the FE model show good correlation with the results predicted by the ANN.