Springback Prediction for Complex Sheet Metal Forming Parts Based on Genetic Neural Network

Accurate springback prediction and control is essential for sheet metal forming. In this paper, back propagation (BP) neural network and genetic algorithm (GA) was introduced to predict springback of complex sheet metal forming parts. GA was used to optimize the weights of BP neural network and the results were compared with those of traditional BP neural network and regression model. The comparison indicated that the prediction precision of GA-BP model was rather accurate. The model can be used to predicate springback and provides a theoretical guide for complex sheet metal parts forming, tools designing and die modification.