锻压技术

基于BP神经网络的薄板成形回弹仿真预测

英文标题：Numerical prediction of springback in sheet metal forming based on BP neural network

作者：王晓莉穆瑞张咏琴

单位：连云港职业技术学院

分类号：TG385

出版年,卷(期):页码：2016,41(6):146-149

摘要：

基于薄板成形回弹正交试验的设计，利用Dynaform仿真软件对薄板成形回弹进行数值模拟，仿真结果表明：薄板弯曲成形高度随着模具间隙以及弯曲半径的增大而逐渐减小，随着冲压速度以及摩擦系数的增加而不断增大。以模具间隙、弯曲半径、冲压速度以及摩擦系数为输入层，将薄板弯曲成形高度作为输出层，建立4-12-1的3层BP神经网络。基于正交试验数据进行BP神经网络的训练与测试，BP神经网络预测值与有限元模拟值的误差为2.053%。此外，利用薄板成形模具进行试验验证，试验值与BP神经网络预测值的误差为11.87%，从而验证了BP神经网络的可靠性。

Based on the orthogonal experiment design for springback of sheet metal forming, the springback of sheet metal forming was simulated by finite element software Dynaform. The simulation results show that the forming height of sheet metal decreases with the increase of die clearance and bending radius, while it shows an increasing trend with the rising of stamping speed and friction coefficient. Therefore, taking die clearance, bending radius, stamping speed and friction coefficient as the input layer, forming height as the output layer, three-layer BP neural network of 4-12-1 was established. Training and testing of BP neural network were carried out based on data from the orthogonal experiment, and the error between the predicted value and the simulation value of BP neural network is 2.053%. In addition, forming die of sheet metal is designed to verify the predicted value, and the error between the experimental value and the predicted value of BP neural network is 11.87%. Therefore, the reliability of BP neural network is proved.

基金项目：

基金项目:连云港市中小企业技术创新项目(CK1411)

作者简介：王晓莉（1976-），女，硕士，副教授 E-mail：jslygxpwxl@126.com

参考文献：

［1］吴超, 严勇, 胡志力. 基于BP神经网络的管材数控弯曲多参数优化方法研究[J]. 锻压技术, 2015, 40(6): 131-137.Wu C, Yan Y, Hu Z L. Research on optimization method of multi-parameter in NC tube bending based on BP neural network[J]. Forging & Stamping Technology, 2015, 40(6): 131-137.

［2］扶名福, 范洪春, 张庭芳. BP神经网络在镁合金流变应力预测中的应用[J]. 锻压技术, 2014, 39(7): 10-13.Fu M F, Fan H C, Zhang T F. Flow stress prediction in magnesium alloy based on BP neural networks[J]. Forging & Stamping Technology, 2014,39(7):10-13.

［3］刘奎武, 边巍. 基于Dynaform的波形片成形回弹研究[J]. 锻压技术, 2015, 40(3): 127-130.Liu K W, Bian W. Study on springback in cushion segment forming based on Dynaform[J]. Forging & Stamping Technology, 2015, 40(3): 127-130.

［4］解加庆, 赵捍东, 李飞, 等. 基于正交试验的筒形件旋压工艺优化设计[J]. 锻压技术, 2013, 38(4): 182-185.Xie J Q, Zhao H D, Li F,et al. Optimization design of cylinder spinning technology based on orthogonal experiment[J]. Forging & Stamping Technology, 2013, 38(4): 182-185

［5］李英, 焦洪宇, 牛曙光. 基于Autoform-Sigma的汽车顶盖后横梁冲压工艺参数优化[J]. 锻压技术, 2015, 40(9): 16-20.Li Y, Jiao H Y, Niu S G. Process parameters optimization on rear cross beam of car roof panel based on Autoform-Sigma[J]. Forging & Stamping Technology, 2015, 40(9): 16-20.

［6］占亮, 李霞, 孙礼宾, 等. 基于正交试验的曲轴热锻工艺参数优化[J]. 锻压技术, 2014, 39(7): 10-13.Zhan L, Li X, Sun L B, et al. Design optimization of process parameters of crankshaft die forging based on orthogonal experiment[J]. Forging & Stamping Technology, 2014, 39(7): 10-13.

［7］李毅, 张火土, 李延平, 等. 基于正交试验法的车用侧墙板冲压成形工艺参数分析[J]. 锻压技术, 2012, 37(2): 21-24.Li Y, Zhang H T, Li Y P, et al. Analysis of stamping process parameters on formability of automotive sidewall plate based on orthogonal experiment[J]. Forging & Stamping Technology, 2012, 37(2): 21-24.

［8］姜志宏, 黄信建, 熊洋, 等. 基于正交试验和BP神经网络的板材多点渐进成形工艺优化[J]. 锻压技术, 2015, 40(5): 33-37.Jiang Z H, Huang X J, Xiong Y, et al. Optimization of process parameters for multi-point incremental forming of sheet metal based on orthogonal examination and BP neural network[J]. Forging & Stamping Technology, 2015, 40(5): 33-37.

［9］李涛, 樊文欣, 赵俊生, 等. 基于BP神经网络的强力旋压成形本构关系模型[J]. 锻压技术, 2014, 39(2): 150-153.Li T, Fan W X, Zhao J S, et al. Research on constitutive relation of tube power spinning forming based on BP neural network[J]. Forging & Stamping Technology, 2014, 39(2): 150-153.

［10］张利红, 梁英波, 李晋. 基于BP神经网络的轧机油膜厚度补偿的测试与建模[J]. 锻压技术, 2012, 37(4): 116-119.Zhang L H, Liang Y B, Li J. Measurement and modeling of rolling mill oil film thickness compensation based on BP neural network[J]. Forging & Stamping Technology, 2012, 37(4): 116-119.

服务与反馈：

【文章下载】【加入收藏】