Artificial neural network and experimental study of effect of velocity on springback in straight flanging process

• Published in: Indian journal of engineering and materials sciences 2016-06, Vol.23 (2-3), p.159-164
• Main Authors: Panthi, S K, Hora, M S, Ahmed, Meraj
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Flanging; Forming; Learning theory; Mathematical models; Process parameters; Sheet metal; Springback
• ISSN: 0971-4588; 0975-1017

Flanging is one of the sheet metal forming processes that applies in various industries to bend the sheet at a particular angle in automobile and fabrication industries. Springback always remains a major concern in any sheet metal forming process. It is mainly due to elastic recovery of the materials. It is a major failure in any sheet metal bending process and it deviate the final product from the desired geometry. It depends on different geometrical, material and process parameters. This investigation is particularly address the one of process parameter, i.e., effect of velocity on springback in straight flanging process and it is carried out by conducting many experiments. It reveals from this study that the velocity of forming affects the springback in this process and springback angle varies nonlinearly with respect to punch velocity. Back propagation artificial neural network (ANN) model is also introduced to predict the springback angle. A three layered (3-6-1) network is selected and trained it by 32 set of the experimental results. The results of ANN model are compared with experimental results, which show a very good agreement.