尾灯安装加强件拉延工艺的动态NSGA-II多目标优化

Multi-objective optimization of dynamic NSGA-II on drawing process for taillight mounting reinforcement

为了提高车辆尾灯安装加强件的拉延成形质量,提出了基于动态NSGA-II算法的多目标优化方法。以减小最大减薄率和起皱趋势函数为目标建立了多目标优化模型,选择4个拉延筋阻力系数和压边力为优化参数,基于有限元法获得了不同条件下拉延件的性能参数。在NSGA-II算法中引入动态拥挤度计算方法,保持了选择染色体的多样性,提高了动态NSGA-II算法的优化能力。使用动态NSGA-II算法求解多目标优化模型,其Pareto前沿解优于传统NSGA-II算法。根据优化后的参数生产了10个试制件,试制件的最大减薄率和最大增厚率的均值均小于厂家产品的均值,且试制件最大减薄率和最大增厚率的标准差较小,实验结果说明:参数优化后的生产质量和稳定性均得到了提高。

To improve the drawing quality of vehicle taillight mounting reinforcement,based on dynamic NSGA-II algorithm,a multi-objective optimization method was proposed.Then,aiming at reducing the maximum thinning rate and wrinkling trend function,a multi-objective optimization model was established,and taking four drawbead resistance coefficients and blank holder force as the optimization parameters,the performance parameters of drawn parts under different conditions were obtained based on the finite element method.Furthermore,the dynamic congestion calculation method was introduced into NSGA-II algorithm to maintain the diversity of selected chromosomes and improve the optimization ability of dynamic NSGA-II algorithm,and using the dynamic NSGA-II algorithm to solve the multi-objective optimization model,its Pareto frontier solution was superior to that of traditional NSGA-II algorithm.According to the optimized parameters,ten trial pieces were produced,the mean values of the maximum thinning rate and the maximum thickening rate for trial pieces were less than the mean values of products for manufacturer,and the standard deviations of the maximum thinning rate and the maximum thickening rate of the trial pieces were small.The experimental results show that the production quality and stability are improved after the parameters optimization.