Prediction of Springback of the One-axle Rotary Shaping Based on Artificial Neural Network

One-axle rotary shaping with elastic medium (RSEM) is a kind of advanced sheet metal forming process. The research object in this paper was the springback of aluminous U-section. Orthogonal method was utilized to design the simulation experiments, the forming and springback of the workpiece were simulated successfully with Finite Element Simulation software, and the main factors impacting on RSEM were analyzed. The simulation results were used as the training samples of the Artificial Neural Network (ANN) to set up the ANN prediction model of RSEM process. The prediction results were verified against the experiment data, and small discrepancy in those two was observed. It demonstrated that the combination of orthogonal test, numerical simulation and neural network could effectively predict the springback of RSEM, and may guide the development of precision forming technology, the design efficiency of process parameters would be improved in this way.