Optimization of blank holder force based on CAE and neural network

In this paper, application of blank holder force (BHF) optimization using FEM simulation and neural network was discussed for the drawing of automobile fuel tank. A radial basis function (RBF) neural network model was established to simulate the nonlinear mapping relation between the BHF and sheet forming parameters. The samples needed for training and testing were obtained by FEM simulation. Once the ANN trained successfully, the BHF optimized design could be realized by using the ANN. The result of finite element simulation proved that the formability and quality of sheet were improved under the optimization curve.