锻压技术

汽车踏板横梁翻边过程中的回弹预测

英文标题：Springback prediction of automobile pedal beam during flanging process

作者：沈洪喆朱兴元石文华

单位：武汉理工大学

关键词：踏板横梁 GRNN神经网络回弹预测 MATLAB 回弹角光滑因子数值模拟

分类号：TG386

出版年,卷(期):页码：2017,42(11):42-46

摘要：

以汽车踏板横梁为研究对象，结合数值模拟技术与GRNN神经网络对零件翻边过程中的回弹情况进行预测。首先采用Autoform对踏板横梁翻边过程进行模拟，并与相同参数下实际零件回弹角进行对比，验证模拟结果的准确性和可替代性。再通过设计正交试验获取不同参数组合下各检测点的回弹角数据作为样本数据，并在MATLAB中对GRNN神经网络进行训练。为保证预测精度，设置多组光滑因子进行训练，发现光滑因子为0.1时，网络具有最优的逼近性能和预测性能，并作为最终网络模型进行检验。通过预测结果与真实结果进行对比，发现预测误差最大为4.3%，满足生产要求。研究表明，GRNN神经网络对板料翻边回弹预测既具有较高效率，又具有较高的精度。

For automobile pedal beam, the springback in flanging process was predicted by combining numerical simulation technology with GRNN neural network. At first, the process of pedal beam flanging was simulated by software Autoform, and their springback angles were compared with the actual ones under the same parameters to verify the accuracy and substitutability of simulation results. Then, the springback angle data of each detection point with different parameters were obtained by the orthogonal test, and the GRNN neural network was trained by MATLAB. In order to ensure the accuracy of prediction, the multiple sets of spread factors were trained. Furthermore, when the spread factor is 0.1, the network has the best approximation performance and prediction performance, which is regarded as the final network model to test, and the maximum error between prediction results and actual measurement results is 4.3% which satisfies requirements of production. The results show that the GRNN neural network is of high efficiency and high precision for the springback prediction in sheet metal flanging.

基金项目：

作者简介：沈洪喆（1992-），男，硕士研究生 E-mail：362457847@qq.com 通讯作者: 朱兴元(1964-)，男，博士，副教授 E-mail: zhu.xingyuan@hotmail.com

参考文献：

[1]曹建国.金属冲压成形工艺与模具设计[M].北京：中国铁道出版社,2015.

Cao J G. Metal Stamping Process and Mould Design [M].Beijing: China Railway Publishing House, 2015.

[2]王晓莉，穆瑞，张咏琴. 基于BP神经网络的薄板成形回弹仿真预测[J]. 锻压技术，2016，41(6)：146-149.

Wang X L, Mu R, Zhang Y Q. Numerical prediction of springback in sheet metal forming based on BP neural network [J]. Forging & Stamping Technology, 2016，41(6):146-149.

[3]戴欣平，倪昀. 基于BP神经网络的汽车车身覆盖件回弹预测[J]. 热加工工艺，2012，41(9)：100-103.

Dai X P, Ni J. Prediction of springback of automobile body covering based on BP neural network [J]. Hot Working Technology, 2012，41(9):100-103.

[4]赵鹏,吕琳,邓明,等.轿车后横梁冲压回弹问题分析和成形工艺改进[J].锻压技术，2015,40(6):25-27.

Zhao P, Lyu L, Deng M, et al. Analysis of the stamping springback and improvement of the forming process for back beam of car[J].Forging & Stamping Technology,2015,40(6):25-27.

[5]刘海燕，金霞. 板料成形的回弹预测方法研究[J]. 机械制造与自动化，2008，37(6)：40-44.

Liu H Y, Jin X. Springback prediction method research of sheet metal forming [J]. Machine Building & Automation, 2008，37(6):40-44.

[6]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.

[7]郭斌，孟令启，杜勇，等. 基于GRNN神经网络的中厚板轧机厚度预测[J]. 中南大学学报：自然科学版，2011，42(4):960-965.

Guo B, Meng L Q, Du Y, et al. Thickness prediction of medium plate mill based on GRNN neural network[J]. Journal of Central South University：Science and Technology, 2011, 42(4):960-965.

[8]张德丰. MATLAB神经网络应用设计[M]. 北京：机械工业出版社，2009.

Zhang D F. Application Design of MATLAB Neural Network [M]. Beijing: China Machine Press, 2009.

[9]张德丰. MATLAB神经网络仿真与应用[M]. 北京：电子工业出版社，2009.

Zhang D F. Simulation and Application of MATLAB Neural Network [M]. Beijing: Publishing House of Electronics Industry, 2009.

服务与反馈：

【文章下载】【加入收藏】