Optimization of Drawbeads for Springback Based on RSM and NSGA-II

To improve material flow of sheet metal, draw beads are used to prevent wrinkling and springback during deep drawing process. Firstly, taking BenchMark2 "S-Rail-08" of NUMSIHEET’2008 as a study case, based on the orthogonal tests of finite element simulation of stamping process, a springback prediction model which adopts response surface method (RSM) was proposed to predict the springback influenced by draw beads parameters approximately. Then, in order to reduce springback, non-dominated sorting genetic algorithm (NSGA-II), is implemented to inverse and optimize both geometry and layout parameters of draw beads cost-efficiently. Finally, the validation of optimal parameters set and the feasible of this optimize approach are confirmed by finite element simulation of S-Rail springback.

[1]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[2]  Wei Zhang,et al.  Prediction and optimization on springback and process parameters of S-Rail forming , 2010, 2010 International Conference on Mechanic Automation and Control Engineering.

[3]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..