锻压技术

基于PGWO-BP神经网络的管材自由弯曲精确成形参数预测

英文标题：Prediction on precise forming parameters for free bending of tube based on PGWO-BP neural network

单位：1.南京工业大学机械与动力工程学院 2. 江苏集萃智能制造技术研究所有限公司

分类号：TG306

出版年,卷(期):页码：2023,48(3):116-125

摘要：

为了提高管材自由弯曲成形技术的加工精度，针对平面弯管加工精度的成形参数开展精确预测工作，通过建立成形参数预测模型的方法使弯曲半径和弯曲角的实验值与设计值一致。首先,建立有限元仿真模型并通过管材加工实验进行修正，采用优化后的仿真模型建立预测的样本数据库，以有限元仿真得到的弯曲半径和弯曲角作为输入，以弯曲半径和弯曲角的设计值作为输出，结合BP神经网络和灰狼优化算法搭建成形参数预测模型。结果显示，改进后的PGWO-BP神经网络预测的弯曲半径和弯曲角的最大误差不超过2%，同时利用该预测模型开发了管材精确成形的工艺参数确定软件。

In order to improve the processing accuracy of free bending forming technology for tubes, the precise prediction work was conducted on the forming parameters for the processing accuracy of planar bending tubes, and the experimental values of bending radius and bending angle were consistent with the designed values by establishing the prediction model of forming parameters. Firstly, the finite element simulation model was established and modified by tube processing experiments, and the optimized simulation model was used to establish the predicted sample database. Then, taking the bending radius and bending angle obtained by finite element simulation as input, and the designed values of bending radius and bending angle as output, combined with BP neural network and grey wolf optimizer algorithm, the forming parameter prediction model was built. The results show that the improved PGWO-BP neural network predicts the bending radius and bending angle with the maximum error of no more than 2%. At the same time, the prediction model is used to develop the process parameter determination software of tube precision forming.

基金项目：

江苏省重点研发计划项目（BE2019007-3）

作者简介：谢媛媛（1997-），女，硕士研究生 E-mail：xieyuan0207@163.com 通信作者：王华（1978-），男，博士，教授 E-mail：wanghua@njtech.edu.cn

参考文献：

[1]Hagenah H, Vipavc D, Plettke R, et al. Numerical model of tube freeform bending by three-roll-push-bending[A]. Proceedings of 2nd International Conference on Engineering Optimization [C]. Lisbon, 2010.

[2]Strano M, Colosimo B M, Castillo E D. Improved design of a three roll tube bending process under geometrical uncertainties[A]. AIP Conference Proceedings [C]. American: American Institute of Physics, 2011.

[3]Vatter P H, Plettke R. Process model for the design of bent 3-dimensional free-form geometries for the three-roll-push-bending process[J]. Procedia Cirp, 2013, 7: 240-245.

[4]Kawasumi S, Takeda Y, Matsuura D. Precise pipe-bending by 3-RPSR parallel mechanism considering springback and clearances at dies[J]. Transactions of the JSME (in Japanese), 2014, 80(820): 343.

[5]Lu S Q, Fang J, Wang K L. Plastic deformation analysis and forming quality prediction of tube NC bending[J]. Chinese Journal of Aeronautics, 2016, 29(5): 1436-1444.

[6]Wu J J, Zhang Z K, Shang Q, et al. A method for investigating the springback behavior of 3D tubes[J]. International Journal of Mechanical Sciences, 2017, 131: 191-204.

[7]Guo X Z, Xiong H, Li H, et al. Forming characteristics of tube free-bending with small bending radii based on a new spherical connection[J]. International Journal of Machine Tools and Manufacture, 2018, 133: 72-84.

[8]张坚, 双远华, 胡建华, 等. 基于改进的BP神经网络无缝钢管连轧轧制力的预测[J]. 锻压技术, 2022,47(5):153-160.

Zhang J, Shuang Y H, Hu J H, et al. Prediction on rolling force in continuous rolling of seamless steel pipe based on improved BP neural network[J]. Forging & Stamping Technology, 2022, 47(5): 153-160.

[9]Zhang Z K, Wu J K, Liang B, et al. A new strategy for acquiring the forming parameters of a complex spatial tube product in free bending technology[J]. Journal of Materials Processing Technology, 2020, 282: 116662.

[10]Guo X Z, Ma Y N, Chen W L, et al. Simulation and experimental research of the free bending process of a spatial tube[J]. Journal of Materials Processing Technology, 2017, 255: 137-149.

[11]Jiang Z Q, Yang H, Zhan M, et al. Establishment of a 3D FE model for the bending of a titanium alloy tube[J]. International journal of mechanical sciences, 2010, 52(9): 1115-1124.

[12]Kohzadi N, Boyd M S. A comparison of artificial neural network and time series modelsfor forecasting commodity prices[J]. Neurocomputing, 1996, 10(2): 169-181.

[13]Mirjalili S, Mirjalili S M, Lewis A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.

服务与反馈：

【文章下载】【加入收藏】