锻压技术

耳片压合衬套冷挤压强化中芯棒拉拔力的IGWO-BP预测及验证

英文标题：IGWO-BP prediction and verification on mandrel drawing force in cold extrusion strengthening of lug press-fit bushing

作者：易志东1 黎向锋1 郑泽庭1 唐伟2 李文生2 刘烨欣2

单位：1. 南京航空航天大学机电学院 2. 航天精工股份有限公司

关键词：冷挤压强化芯棒拉拔力灰狼算法神经网络模型预测精度

分类号：TG335

出版年,卷(期):页码：2025,50(8):123-130

摘要：

芯棒拉拔力对于研究耳片压合衬套冷挤压过程的强化效果具有重要意义，而预测不同加工参数下的芯棒拉拔力有助于寻找最佳的冷挤压强化参数，在提高冷挤压强化效果的同时避免断棒现象的发生。首先，建立耳片压合衬套冷挤压强化过程的有限元仿真模型，获得压合衬套冷挤压过程中芯棒拉拔力曲线，并对芯棒拉拔力最大值进行实验验证。其次，通过Tent混沌初始化、收敛因子改进和自适应动态权重对GWO-BP神经网络模型进行改进，对不同挤压量、衬套壁厚、芯棒工作段长度及芯棒过渡圆弧半径下的芯棒拉拔力最大值进行预测。结果表明，相较于SVM、BP和GWO-BP模型，改进后的IGWO-BP神经网络模型的预测精度更高，最大误差不超过3.05%，可为企业实际生产提供理论依据。

The mandrel drawing force is of great significance for studying the strengthening effect of the cold extrusion process for lug press-fit bushings, and predicting the mandrel drawing force under different processing parameters can help to identify the optimal cold extrusion strengthening parameters, improve the strengthening effect and avoid the occurrence of mandrel breakage. Therefore, firstly, a finite element simulation model for the cold extrusion strengthening process of lug press-fit bushings was established, the mandrel drawing force curve during the process was obtained, and the maximum mandrel drawing force was experimentally verified. Secondly, the GWO-BP neural network model was improved by Tent chaotic initialization, convergence factor modification and adaptive dynamic weighting, and the maximum mandrel drawing forces under different extrusion amounts, bushing wall thicknesses, mandrel working section lengths and mandrel transition arc radii were predicted. The results show that compared with the SVM, BP, and GWO-BP models, the improved IGWO-BP neural network model has higher prediction accuracy, with the maximum error of no more than 3.05%, providing a theoretical basis for the actual production in enterprise.

基金项目：

国家自然科学基金联合基金项目（U20A20293）；天津市紧固连接技术企业重点实验室开放课题（HTJG-TJ-YJ-2024-2002）；苏州市科技成果转化专项（No.SZC202317）

作者简介：易志东（2000-），男，硕士研究生 E-mail：482786598@qq.com 通信作者：黎向锋（1971-），女，博士，教授 E-mail：fxli@nuaa.edu.cn

参考文献：

[1]唐伟, 林忠亮, 吴保全, 等. 双孔耳片衬套冷挤压强化的残余应力和疲劳寿命[J]. 塑性工程学报, 2023, 30(2): 55-63.

Tang W, Lin Z L, Wu B Q, et al. Residual stress and fatigue life for cold expansion strengthening of bushing in double-hole lug [J]. Journal of Plasticity Engineering, 2023, 30(2): 55-63.

[2]Tang C Z, Li H W, Li K S, et al. Data-driven fatigue life prediction of small-deep holes in a nickel-based superalloy after a cold expansion process[J]. International Journal of Fatigue, 2024, 181: 108159.

[3]Wang J, Lei X, Zeng F, et al. Design of a novel cold expansion tool for deep small holes based on FEM simulations and experimental study[J]. The International Journal of Advanced Manufacturing Technology, 2024, 130(9): 4933-4949.

[4]Su R, Huang L, Xu C, et al. Factors influencing residual stresses in cold expansion and their effects on fatigue life-A review[J]. Coatings, Multidisciplinary Digital Publishing Institute, 2023, 13(12): 2037.

[5]Liu K, Zhou L, Yang X, et al. Finite element simulation of the cold expansion process with split sleeve in 7075 aluminum alloy[J]. Journal of The Institution of Engineers (India): Series C, 2021, 102(2): 361-374.

[6]梁勇楠, 杨长勇, 刘飞, 等. 基于数值模拟的孔构件挤压强化疲劳寿命预测[J]. 南京航空航天大学学报, 2023, 55(3): 471-480.

Liang Y N, Yang C Y, Liu F, et al. Prediction of fatigue life of hole components cold expansion strengthening based on numerical simulation [J]. Journal of Nanjing University of Aeronautics and Astronautics, 2023, 55(3): 471-480.

[7]董卫萍, 高飞, 邢欣, 等. 开缝衬套冷挤压强化工艺对7050铝合金孔连接结构疲劳寿命的影响[J]. 工具技术, 2021, 55(12): 68-72.

Dong W P, Gao F, Xing X, et al. Effect of cold extrusion strengthening technology of split-sleeve bushing on fatigue life of 7050 Al alloy hole connection structure [J]. Tool Technology, 2021, 55(12): 68-72.

[8]唐伟, 林忠亮, 吴保全, 等. 孔结构压合衬套冷挤压强化的疲劳寿命试验研究[J]. 航空精密制造技术, 2022, 58(4): 11-15, 41.

Tang W, Lin Z L, Wu B Q, et al. Test study on fatigue life of cold extrusion strengthening bushings for hole structure[J]. Aviation Precision Manufacturing Technology, 2022, 58(4): 11-15, 41.

[9]姜廷宇, 王洋, 王鹏, 等. TB6钛合金孔二次挤压残余应力及疲劳寿命仿真研究[J]. 航空制造技术, 2021, 64(9): 77-84.

Jiang T Y, Wang Y, Wang P, et al. Simulation study on residual stress and fatigue life of TB6 titanium alloy hole after double cold expansion[J]. Aeronautical Manufacturing Technology, 2021, 64(9): 77-84.

[10]刘儒军, 黄翔, 黄海鸿, 等. 压合衬套二次冷挤压强化数值仿真与实验研究[J]. 机械科学与技术, 2024, 43(7): 1142-1150.

Liu R J, Huang X, Huang H H, et al. Numerical simulation and experimental study on secondary cold extrusion strengthening of pressed bush[J]. Mechanical Science and Technology, 2024, 43(7): 1142-1150.

[11]Chakherlou T N, Shahriary P, Akbari A. Experimental and numerical investigation on the fretting fatigue behavior of cold expanded Al-alloy 2024-T3 plates[J]. Engineering Failure Analysis, 2021, 123: 105324.

[12]Liu H, Hu D, Wang R, et al. Experimental and numerical investigations on the influence of cold expansion on low cycle fatigue life of bolt holes in aeroengine superalloy disk at elevated temperature[J]. International Journal of Fatigue, 2020, 132: 105390.

[13]杨赫然, 李帅, 孙兴伟, 等. 基于改进松鼠搜索算法优化神经网络的数控机床进给系统热误差预测[J]. 仪器仪表学报, 2024, 45(1): 60-69.

Yang H R, Li S, Sun X W, et al. Thermal error prediction of CNC machine tool feed system based on neural network optimized by improved squirrel search algorithm[J]. Chinese Journal of Scientific Instrument, 2024, 45(1): 60-69.

[14]朱必武,蒋昊,刘筱,等.基于改进PSO-BP神经网络预测中高应变速率轧制AZ31镁合金板的抗拉强度[J/OL].中国有色金属学报,1-17[2025-05-25].http://kns.cnki.net/kcms/detail/43.1238.TG.20240305.1529.003.html.

Zhu B W, Jiang H, Liu X, et al. Prediction of the tensile strength of AZ31 magnesium alloy sheet rolled at medium-high strain rate based on improved PSO-BP neural network[J/OL]. The Chinese Journal of Nonferrous Metals, 1-17[2025-05-25]. http://kns.cnki.net/kcms/detail/43.1238.TG.20240305.1529.003.html.

[15]谢媛媛, 王华, 徐振华, 等. 基于PGWO-BP神经网络的管材自由弯曲精确成形参数预测[J]. 锻压技术, 2023, 48(3): 116-125.

Xie Y Y, Wang H, Xu Z H, et al. Prediction on precise forming parameters for free bending of tube based on PGWO-BP neural network[J]. Forging & Stamping Technology, 2023, 48(3): 116-125.

[16]曾权, 李鑫, 王克鲁, 等. 基于GA-BP和PSO-BP神经网络的SLM GH3625高温合金残余应力预测研究[J]. 塑性工程学报, 2024, 31(3): 193-199.

Zeng Q, Li X, Wang K L, et al. Study on residual stress prediction of SLM GH3625 high temperature alloy based on GA-BP and PSO-BP neural networks[J]. Journal of Plasticity Engineering, 2024, 31(3): 193-199.

[17]胡啸, 薛霖, 景洁, 等. 基于改进SSA-GA-BP神经网络的热连轧轧制力预测[J]. 塑性工程学报, 2023, 30(8): 122-129.

Hu X, Xue L, Jing J, et al. Rolling force prediction of hot continuous rolling based on improved SSA-GA-BP neural network[J]. Journal of Plasticity Engineering, 2023, 30(8): 122-129.

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

[19]鲍伟, 任超. 基于GWO-BP神经网络的电池SOC预测方法研究[J]. 计算机应用与软件, 2022, 39(9): 65-71.

Bao W, Ren C. Study on battery SOC prediction method based on GWO-BP neural network[J]. Computer Applications and Software, 2022, 39(9): 65-71.

[20]Yu B, Xu C, Wang X, et al. Evolution of cold-expanded microstructure with aging temperature and its influence on fatigue performance of hole structure at elevated temperature[J]. Journal of Alloys and Compounds, 2024, 970: 172562.

[21]Zuo D, Jin S, Liu J, et al. Numerical simulation on the dynamic cold extrusion of bolted single-lap Al/Al joint under interference-fit[J]. Journal of Physics: Conference Series, IOP Publishing, 2024, 2746(1): 012041.

[22]Zwolak M, S′liwa R. Analysis of the influence of dies geometry on the process extrusion force and properties of the extrudate obtained in the process of cold extrusion of 7075 aluminum alloy by the KOBO method[J]. Materials Science-Poland, 2024, 42(1): 92-106.

[23]林忠亮,白清顺,唐伟,等.压合衬套冷挤压强化的残余应力的数值模拟[J].材料导报,2024,38(3):192-199.

Lin Z L, Bai Q S, Tang W, et al. Numerical simulation of residual stress for compression bushing cold expansion strengthening[J]. Materials Review, 2024, 38(3): 192-199.

[24]Li H, Lyu T, Shui Y, et al. An Improved grey wolf optimizer with weighting functions and its application to Unmanned Aerial Vehicles path planning[J]. Computers and Electrical Engineering, 2023, 111: 108893.

服务与反馈：

【文章下载】【加入收藏】