锻压技术

汽车后围内板冲压工艺的高斯扰动粒子群优化

英文标题：Stamping process optimization of automobile rear inner panel based on Gaussian perturbation particle swarm

作者：胡锦达

分类号：TG386.1

出版年,卷(期):页码：2020,45(12):46-52

摘要：

为了提高汽车后围内板的制件质量，提出了基于高斯扰动粒子群算法的冲压工艺优化方法。针对冲压工艺流程，选择拉延工艺参数作为优化参数，以可以反映制件质量的参数作为目标参数，建立了优化目标函数。设计了4因素4水平的正交实验，并使用单隐含层BP神经网络对实验数据进行拟合。以粒子群算法为基础，提出了精英粒子分阶段高斯扰动策略，从而设计了基于高斯扰动粒子群算法的优化模型求解方法，得到了拉延工艺的最优参数。经模拟仿真成形和试制件验证，采用优化后的冲压工艺未出现起皱和开裂现象，验证了优化冲压工艺的有效性。

To improve the quality of automobile rear inner panel, based on Gaussian perturbation particle swarm algorithm, the stamping process optimization method was proposed, and for the stamping process, drawing process parameters were chosen as optimizing parameters. Then, the parameters reflecting workpiece quality were chosen as objective parameters, and the optimizing objective function was built. Furthermore, the orthogonal experiment with four factors and four levels was designed, and the experiment data were fit by BP neutral network with single hidden layer. On the basis of particle swarm algorithm, the elite particles staged gaussian perturbation strategy was put forward, and based on Gaussian perturbation particle swarm algorithm, the solving method of optimizing model was designed to obtain the optimal parameters of drawing process. Finally, it was clarified by simulation forming and trial workpiece that there was no wrinkling and cracking in the optimized stamping process, which proves the validity of optimized stamping process.

基金项目：

黑龙江省应用技术研发计划重大项目(GA17A401)

胡锦达（1981-），女，硕士，副教授 E-mail：1607164419@qqcom

参考文献：

［1］王海玲, 陈世涛, 崔礼春. 汽车车门内板冲压工艺方案及修边整形模设计
［J］. 锻压技术, 2019, 44(1):92-98.

Wang H L, Chen S T, Cui L C. Stamping process scheme and trimmingsizing die design of automobile door inner panel
［J］. Forging & Stamping Technology, 2019, 44(1):92-98.

［2］刘志峰, 秦利民, 黄海鸿, 等. 冲压工艺低碳成形优化方法研究
［J］. 合肥工业大学学报：自然科学版, 2019, 42(1):1-7.

Liu Z F, Qin L M, Huang H H, et al. Research on low carbon forming optimization method for stamping process
［J］. Journal of Hefei University of Technology：Natural Science, 2019, 42(1):1-7.

［3］林浩波，刘军辉，吴立国. 基于遗传算法的防撞钢梁热冲压成形工艺优化
［J］. 塑性工程学报，2019, 26(5):65-69.

Lin H B, Liu J H, Wu L G. Optimization of hot stamping process for anticollision beam based on genetic algorithms
［J］. Journal of Plasticity Engineering, 2019, 26(5):65-69.

［4］袁小江, 张秋菊. 基于ST14材料冲压工艺有限元分析应用
［J］. 制造技术与机床, 2013，(5):36-38.

Yuan X J, Zhang Q J. The applications of finite element analysis based on ST14 material stamping process
［J］. Manufacturing Technology & Machine Tool, 2013，(5):36-38.

［5］高博. 基于有限元模型的电动汽车PMSM参数分析及应用
［D］. 成都：电子科技大学，2018.

Gao B. Analysis and Application of Electric Vehicle PMSM Parameters Based on Finite Element Model
［D］. Chengdu: University of Electronic Science and Technology, 2018.

［6］龙玲, 张健, 董洁, 等. 基于随机聚焦搜索算法的汽车后围内板冲压工艺优化设计
［J］. 锻压技术, 2018, 43(5):154-159.

Long L, Zhang J, Dong J, et al. Optimization of stamping process design for automobile body lower back panel based on stochastic focusing search algorithm
［J］. Forging & Stamping Technology, 2018, 43(5):154-159.

［7］程刚, 郭永存, 胡坤, 等. 永磁涡流调速器传动性能分析与正交实验优化
［J］. 机械科学与技术, 2018, 37(12):150-157.

Cheng G, Guo Y C, Hu K, et al. Transmission characteristics analysis and orthogonal experimental optimization of the permanent magnet eddy current coupling
［J］. Mechanical Science and Technology for Aerospace Engineering, 2018, 37(12):150-157.

［8］祝阳. 汽车后门外板冲压成形优化及其回弹分析
［D］.镇江：江苏大学，2018.

Zhu Y. Optimization of Press Forming and the Springback Analysis of Automobile Rear Door Outer Panel
［D］. Zhenjiang: Jiangsu University, 2018.

［9］薛萍, 宋岩亮. 改进蚁群算法与BP网络融合预测铅酸蓄电池SOC
［J］. 哈尔滨理工大学学报, 2016，21(6)：95-99.

Xue P, Song Y L. The prediction of leadacid battery remaining capacity based on improved ant colony algorithm and BP network
［J］. Journal of Harbin University of Science and Technology, 2016，21(6)：95-99.

［10］陈鹏. 基于VB的单隐含层BP神经网络编程及验证
［J］. 计算机时代, 2018,(5):45-47.

Chen P. Programming & verification of a single hidden layer BP neural network with VB
［J］. Computer Era, 2018,(5):45-47.

［11］李敏, 曲大义, 张西龙, 等. 基于粒子群算法的神经网络的驾驶意图识别
［J］. 科学技术与工程, 2018, 18(36):266-270.

Li M, Qu D Y, Zhang X L, et al. Driving intention identification based on neural network optimized by particle swarm optimization
［J］. Science Technology and Engineering, 2018, 18(36):266-270.

［12］陈立芳, 陈哲超, 王维民, 等. 基于自适应粒子群优化的非稳态自动平衡控制算法研究
［J］. 振动与冲击, 2018, 37(24):148-153.

Chen L F, Chen Z C, Wang W M, et al. Nonstationary autobalancing control based on adaptive particle swarm optimization
［J］. Journal of Vibration and Shock, 2018, 37(24):148-153.

服务与反馈：

【文章下载】【加入收藏】