锻压技术

A286高温合金薄壁管件冷镦冲连皮力预测及冲头结构参数优化

英文标题：Prediction of cold heading punching force and optimization of punch structure parameters for superalloy A286 thin-walled pipe fittings

作者：莫宁宁1 冯治国1 2 陶亮1 江玉莲1 王程民1

单位：1.贵州大学机械工程学院 2.贵州大学

关键词：A286高温合金薄壁管件冲连皮力冲头前角圆角半径冲连皮间隙

分类号：TG376

出版年,卷(期):页码：2023,48(9):64-70

摘要：

薄壁管件冲连皮力预测与冲头参数优化是冲连皮加工过程中需要考虑的重要问题，基于DEFORM软件对薄壁管件冲连皮过程进行了数值模拟仿真，利用极差分析了冲头前角A、圆角半径r和冲连皮间隙C对最大冲连皮力Fmax的影响程度；建立了BP神经网络模型，预测了薄壁管件冲连皮过程中的最大冲连皮力，相关系数R达到了0.97608；以冲连皮过程中最大冲连皮力最小为优化目标，利用遗传算法优化了冲头结构参数（冲头前角A、圆角半径r和冲连皮间隙C），得到最优的冲头结构参数为冲头前角A=12.8°、圆角半径r=0.2 mm和冲连皮间隙C=0.12 mm;基于仿真实验，验证了优化的冲头结构参数的准确性，为薄壁管件冲连皮过程的优化和冲头结构参数的选择提供了依据。

The prediction of punching force and optimization of punch parameters of thin-walled pipe fittings are important issues to be considered in the punching process. Therefore, the punching process of thin-walled pipe fittings was numerical simulated by software DEFORM, and the influence degrees of front angle A of punch, fillet radius r and punching clearance C on the maximum punching force Fmax were analyzed by using the range analysis. Then, the BP neural network model was established to predict the maximum punching force in the punching process of thin-walled pipe fittings, and the correlation coefficient R reached 0.97608. Furthermore, minimizing the maximum punching force in the punching process as the optimization objective, the genetic algorithm was used to optimize the punching structural parameters, such as front angle A of punch, fillet radius r and punching clearance C, and the optimum punching structural parameters were obtained that the front angle A of punch was 12.8°, the fillet radius r was 0.2 mm and the punching clearance C was 0.12 mm. Finally, based on the simulation experiments, the optimized punch structural parameters were verified to be accurate, which provides a basis for the optimization on the punching process of thin-walled pipe fittings and the selection of punch structural parameters.

基金项目：

国家自然科学基金资助项目（52165042）；贵州科学技术基金重点项目（黔科合基础[2020]1Z049）；贵州省优秀青年人才项目（黔科合平台人才[2021]5617号）；贵阳市科技人才培养项目（筑科合同[2021]43-1号）

作者简介：莫宁宁（1998-），男，硕士研究生 E-mail：monn981012@163.com 通信作者：冯治国（1978-），男，博士，教授 E-mail：zgfeng@gzu.edu.cn

参考文献：

[1]王心可,汪喆,崔荣高,等.冲裁工艺对无取向电工钢叠片磁性能的影响[J].上海交通大学学报,2019,53(9):1115-1121.

Wang X K, Wang Z, Cui R G, et al. Effect of stamping process on magnetic properties of nonoriented electrical steel laminated sheets[J]. Journal of Shanghai Jiao Tong University, 2019, 53(9): 1115-1121.

[2]张大伟,赵升吨,朱成成,等.钛合金实心锭穿孔挤压穿孔过程有限元分析[J].稀有金属材料与工程,2016,45(1):86-91.

Zhang D W, Zhao S D, Zhu C C, et al. Finite element analysis of solid ingot piercing extrusion perforation process of titanium alloy[J]. Rare Metal Materials and Engineering, 2016, 45(1): 86-91.

[3]齐延兵,林俊峰,苏海波,等.冲头形状对液压冲孔塌陷的影响[J].材料科学与工艺,2013,21(1):62-66.

Qi Y B, Lin J F, Su H B, et al. Influence of punch shape on rollover of hydropiercing [J]. Materials Science and Technology, 2013, 21(1): 62-66.

[4]张立娟,常海平,罗文哲，等.A356铝合金车轮轮辋旋压成形工艺优化[J].精密成形工程,2022,14(10):56-62.

Zhang L J, Chang H P, Luo W Z, et al. Optimization of spinning process for A356 aluminum alloy wheel rim [J]. Journal of Netshape Forming Engineering, 2022, 14(10):56-62.

[5]陈鑫. 内螺纹冷挤压成形工艺及成形质量研究[D].汉中：陕西理工大学,2022.

Chen X. Research on Cold Extrusion Forming Process and Forming Quality of Internal Threads[D]. Hanzhong: Shaanxi University of Technology, 2022.

[6]匡青云. 齿形零件精冲成形研究及缺陷控制[D]. 重庆：重庆理工大学,2018.

Kuang Q Y. Research on Fine Blanking Forming of Toothshaped Parts and Defect Control[D]. Chongqing: Chongqing University of Technology, 2018.

[7]孙欢迎,陆春杨,陈前,等.工艺参数对阻燃钛合金包套挤压影响的数值模拟[J].热加工工艺,2017,46(11):166-170.

Sun H Y, Lu C Y, Chen Q, et al. Numerical simulation of the effect of process parameters on the extrusion of flameretardant titanium alloy cladding[J]. Hot Working Technology, 2017, 46(11):166-170.

[8]赵震，陈军，吴公明.冷温热挤压技术[M].北京:电子工业出版社，2008.

Zhao Z, Chen J, Wu G M. Cold Warm Hot Extrusion Technology [M]. Beijing: Publishing House of Electronics Industry, 2008.

[9]孙倩楠,何林.气缸盖罩压铸过程数值模拟及工艺参数优化[J].特种铸造及有色合金,2016,36(1):20-22.

Sun Q N, He L. Numerical simulation of cylinder head cover diecasting process and optimization of process parameters[J]. Special Casting and Nonferrous Alloys,2016,36(1):20-22.

[10]程晨晨,尤波,刘燕,等.基于深度神经网络的个性化睡眠癫痫发作预测[J].模式识别与人工智能,2021,34(4):333-342.

Cheng C C, You B, Liu Y, et al. Personalized sleep seizure prediction based on deep neural networks[J]. Pattern Recognition and Artificial Intelligence,2021,34(4):333-342.

[11]李鑫,史振宇,蒋森河,等.人工神经网络预测刀具磨损和切削力[J].控制理论与应用,2018,35(12):1731-1737.

Li X, Shi Z Y, Jiang S H, et al. Artificial neural networks for predicting tool wear and cutting forces[J]. Control Theory and Applications,2018,35(12):1731-1737.

[12]邹咏楠,罗钧元,李林瑛.基于改进遗传算法的集束型装备调度研究[J].电脑知识与技术,2017,13(4):263-264.

Zou Y N, Luo J Y, Li L Y. Research on clusterbased equipment scheduling based on improved genetic algorithm[J]. Computer Knowledge and Technology, 2017, 13(4):263-264.

[13]Chen Z, Jiang Y B, Tong Z M, et al. Residual stress distribution design for gear surfaces based on genetic algorithm optimization[J]. Materials,2021,14(2)：366.

服务与反馈：

【文章下载】【加入收藏】