车辆前纵梁封板冲压的聚集度自适应粒子群优化

Vehicle Front Longitudinal Beam Seal Plate Stamping Optimization Based on Aggregation Adaptive PSO Algorithm

为了提高车辆前纵梁封板的冲压件质量,提出了基于聚集度自适应粒子群算法的冲压工艺优化方法。介绍了前纵梁封板的三维模型、坯料设计结果和冲压成形原理。基于成形极限曲线,以减小冲压件的减薄率、增厚率、回弹量为目标,建立了多目标优化模型。使用复合中心实验法设计了5因素5水平的32组实验,基于Autoform软件获得了实验数据。使用BP神经网络拟合了输入输出间的回归关系,并验证了回归模型的精度。在粒子群算法基础上,依据粒子相似度和种群聚集度,将Levy飞行融入到粒子群算法中,提高粒子多样性和算法优化能力,从而并提出了聚集度自适应粒子群算法。将改进粒子群算法应用于多优化模型求解,改进粒子群算法收敛速度早于传统算法,且改进粒子群算法搜索的目标函数值比传统算法减小了3.71%,说明了改进算法的优越性。经验证,优化后的试制件外观合格,减薄率、增厚率及回弹量均满足质量要求,可以进行批量生产。

In order to improve the quality of stamping parts for vehicle front longitudinal beam sealing plate,a stamping process optimization method based on aggregation degree adaptive particle swarm optimization algorithm was proposed.The three-dimensional model,blank design result and stamping forming principle of front longitudinal beam sealing plate are introduced.Based on the forming limit curve,a multi-objective optimization model was established to reduce the thinning rate,thickening rate and springback of stamping parts.32 groups of experiments with 5 factors and 5 levels were designed by compound center ex-periment method,and the experimental data were obtained based on AutoForm software.BP neural network is used to fit the re-gression relationship between input and output,and the accuracy of the regression model is verified.On the basis of particle swarm optimization(PSO),Levy flight is integrated into PSO according to particle similarity and population aggregation,so as to improve the diversity of particles and the optimization ability of the algorithm.The improved particle swarm optimization algo-rithm is applied to solve multiple optimization models,the convergence speed of the improved particle swarm optimization algo-rithm is earlier than the traditional algorithm,and the objective function value of the improved particle swarm optimization algo-rithm is reduced by 3.71%compared with the traditional algorithm,which shows the advantages of the improved algorithm.After verification,the appearance of the optimized trial parts is qualified,and the thinning rate,thickening rate and springback meet the quality requirements,and can be mass produced.