基于RBF神经网络模型的板料成形变压边力优化

谢延敏; 何育军; 田银

doi:10.3969/j.issn.0258-2724.2016.01.018

基于RBF神经网络模型的板料成形变压边力优化

doi: 10.3969/j.issn.0258-2724.2016.01.018

基金项目:

国家自然科学基金资助项目(51275431)

详细信息

作者简介:
谢延敏(1975-),男,副教授,博士,研究方向为先进塑性加工技术仿真和稳健设计,E-mail:xie_yanmin@swjtu.edu.cn

计量
- 文章访问数: 1090
- HTML全文浏览量: 80
- PDF下载量: 346
- 被引次数: 10
出版历程
- 收稿日期: 2015-06-16
- 刊出日期: 2016-01-25

Optimization of Variable Blank Holder Forces in Sheet Metal Forming Based on RBF Neural Network Model

摘要

摘要: 为了解决变压边力优化过程中RBF(radial basis function )神经网络隐层节点训练难的问题,利用人工智能算法的优越性,建立了基于人工免疫算法的RBF神经网络,并将其用于非线性函数的逼近中.结合分块压边圈与改变压边力控制技术,通过Dynaform软件进行数值模拟获得成形数据,建立了变压边力与成形质量之间的RBF神经网络近似模型.利用人工免疫智能算法对该近似模型进行优化,获得最优压边力参数.将该方法应用于S形梁冲压成形中,与优化前的结果进行比较,采用优化后最优变压边力可以抑制起皱,最大起皱量减少了89.53%.
- 板料成形 /
- 变压边力 /
- 数值模拟 /
- RBF神经网络
Abstract: In order to solve the difficulty of training the hidden layer nodes in radial basis function (RBF) neural network during the optimization of variable blank holder forces,a RBF neural network based on the artificial immune algorithm was established by taking advantages of artificial intelligence algorithms, and then used to approximate a nonlinear function. Using both the block blank holder technology and the variable blank holder force control technology, numerical simulations were conducted in Dynaform to obtain the forming data, and an approximate model of RBF neural network was established between the variable blank holder forces and the forming quality. The approximate model was optimized by artificial immune algorithm to obtain the optimal blank holder force parameters. In addition, the method was applied to the S-rail stamping. The results show that compared with that before optimization, the maximum wrinkle amount was reduced by 89.53%, and wrinkles could be effectively controlled by the optimized variable blank holder forces.
- sheet forming /
- variable blank holder force /
- numerical simulation /
- RBF neural network

HTML全文

参考文献(14)

李少平,郑静风,何丹农. 板料成形参数对拉深成形性能影响的正交分析[J]. 锻压技术,2002,27(3): 27-28. LI Shaoping, ZHENG Jingqiu, HE Dannong. Orthogonal analysis of influence of sheet forming parameters on drawing properties[J]. Forging Stamping Technology, 2002, 27(3): 27-28.

KAZUNARI K, MASAHIRO S, YASUO H, et al. Binding force control of uni-pressure cushion in automobile panel stamping[C]//1995 SAE International Congress and Exposition. Detroit:, 1995: No. 950916.

SIEGERT K, DANNEMANN E, WAGNER S, et al. Closed-loop control system for blank holder forces in deep drawing[J]. Ann CIRP, 1995, 44(1): 251-254.

陈关龙,孙成智,王东川,等. 变压边力对铝合金板冲压成形的影响研究[J]. 塑性工程学报,2005,12(3): 41-45. CHEN Guanlong, SUN Chenzhi, WANG Dongchuan, et al. Mechanism investigation of variable blank-holder forces improving the formability of aluminum alloy sheets during sheet metal forming[J]. Journal of Plasticity Engineering, 2005, 12(3): 41-45.

孙成智,陈关龙,李淑慧,等. 变压边力对矩形件成形性能的影响[J]. 塑性工程学报,2003,10(4): 1226-1229. SUN Chengzhi, CHEN Guanlong, LI Shuhui, et al. The effect of variable blank-holder forces on formability of ractangle box deep drawing[J]. Journal of Plasticity Engineering, 2003, 10(4): 1226-1229.

郑刚,李光耀,孙光永,等.基于近似模型的拉延筋几何参数反求[J]. 中国机械工程,2006,17(19): 1988-1992. ZHENG Gang, LI Guangyao, SUN Guangyong, et al. Geometrical parameter inverse problem for drawbeads based on the approximate model [J]. China Mechanical Engineering, 2006, 17(19): 1988-1992.

苏娟华,张文琼,李丽春. 神经网络与正交试验法结合优化板料成形工艺[J]. 锻压技术,2009,33(1): 154-156. SU Juanhua, ZHANG Wenqiong, LI Lichun. Application of network and orthgonal experiment method in optimization of sheet metal forming process technology[J]. Forging Stamping Technology, 2009, 33(1): 154-156.

周杰,华俊杰,阳德森,等. 基于GS理论与GA-BP网络的板料多目标成形工艺优化[J]. 热加工工艺,2009,38(17): 73-76. ZHOU Jie, HUA Junjie, YANG Desen, et al. Optimization of forming process for sheet metal multi-objective based on GS theory and GA-BP network[J]. Hot Working Process, 2009, 38(17): 73-76.

焦李成,杜海峰,刘芳,等. 免疫优化计算、学习与识别[M]. 北京,科学出版社,2006: 53-92.

郑日荣. 基于欧式距离和精英交叉的免疫算法研究[D]. 广州:华南理工大学,2004.

田银,谢延敏,孙新强,等. 基于鱼群RBF神经网络和改进蚁群算法的拉深成形工艺参数优化[J]. 锻压技术,2014,39(12): 129-136. TIAN Yin, XIE Yanmin, SUN Xinqiang, et al. Process parameters optimization of deep drawing based on fish RBF neural network and improved ant colony algorithm[J]. Forging Stamping Technology, 2014, 39(12): 129-136.

谢延敏,田银,孙新强,等. 基于灰色关联的铝合金板拉深成形扭曲回弹工艺参数优化[J]. 锻压技术,2015,40(3): 25-31. XIE Yanmin, TIAN Yin, SUN Xinqiang, et al. Optimization of twist springback process parameters of aluminum alloy aheet forming based on grey correlation[J]. Forging Stamping Technology, 2015, 40(3): 25-31.

SCHWARZE M, VLADIMIROV I N, REESE S. Sheet metal forming and springback simulation by means of a new reduced integration solid-shell finite element technology[J]. Computer Methods in Applied Mechanics and Engineering, 2011, 200(5/6/7/8): 454-476.

LEE S W, YOON J W, YANG D Y. Comparative investigation into the dynamic explicit and the static implicit method for springback of sheet metal stamping[J]. Engineering Computations, 1999, 16(3): 347-373.

施引文献

期刊类型引用(4)

1.	叶启彬，肖泓宇，田晨，刘名，付沄琳，胡苏. 面向无人机的通信感知一体化系统自干扰消除技术. 西南交通大学学报. 2024(04): 925-932 . 本站查看
2.	王豪，董增寿，康琳，王珍妮. 瑞利信道下全双工中继系统性能研究. 太原科技大学学报. 2019(06): 437-441+446 . 百度学术
3.	汪汉新，汪玉明. 多源多中继协同通信的快速中继选择算法. 中南民族大学学报(自然科学版). 2018(01): 80-84 . 百度学术
4.	龙志鹏，余江，常俊. 一种改进的自适应全双工中继系统中继策略. 计算机科学. 2017(09): 110-114 . 百度学术