Prediction of Deformed Shape in Incremental Sheet Forming Processing Feedforward Neural Network

Abstract

Numerical simulations of the incremental sheet forming (ISF) process using the finite element method (FEM) provide essential information for designing parts in automotive industries. However, solving numerous high-complexity FEM models during the designing phase requires many resources, leading to an increase in the final product's cost. This study presents a feedforward neural network (FFNN) to predict the deformed shape of an AA1050 sheet subjected to an ISF process. FEM solutions obtained from various vertical step size ($\Delta z)$ of the forming tool are used to train and validate the FFNN. The model is then used to predict the deformed shape demonstrating by the displacement in the forming depth direction. The norm of the relative errors between the FFNN solution and FEM solution at the last forming step is about $2 \%$. The predictive results illustrate the feasibility and potential of using FFNN as an efficient surrogate model to replace the time-consuming FEM-based ISF process simulation.