Research on stamping forming prediction of aluminum alloy sheet based on RBF neural network

Abstract In order to accurately predict and reduce the possible defects in stamping process of an aluminum alloy sheet, simulation data sheet thickness for 6016 were obtained by Hill’48 yield criterion based on finite element ABAQUS/Explicit solver. Taking blank holder force, friction coefficient, speed, die clearance as input parameters, radial basis function (RBF) network model predicting maximum thinning rate was established. The results show that RBF constructed this paper has high precision can reflect complex relationship between parameters well comparing neural prediction results. It is great significance improve optimization efficiency actual experimental cost.