网站首页期刊简介编委会过刊目录投稿指南广告合作征订与发行联系我们English
基于BP神经网络的镁合金轮毂旋转挤压工艺
英文标题:Rotary extrusion process for magnesium alloy wheel hub based on BP neural network
作者:王剑锋 
单位:包头铁道职业技术学院 
关键词:镁合金 轮毂 BP神经网络 挤压成形 DEFORM-3D 
分类号:TG316.11
出版年,卷(期):页码:2020,45(6):111-115
摘要:

以镁合金轮毂挤压成形工艺为研究对象,采用有限元分析软件DEFORM-3D对其成形工艺进行模拟。为使制件成形效果达到最佳,选取凸模冲压速度、凹模旋转速度、成形温度作为输入层,以成形后制件的损伤值和应变标准差为输出层,通过构建关于工艺参数的BP神级网络对输入、输出层参数关系进行拟合。并采用遗传算法,基于构建的神经网络寻求最优解。得出最优参数组合为:凸模冲压速度为5.0 mm·s-1、凹模旋转速度为30 r·min-1、成形温度为380 ℃,采用最优参数进行试模,制件成形效果良好,与预测结果基本一致,验证了有限元模拟和优化的正确性,为实际生产提供指导。

For the extrusion process of magnesium alloy wheel hub, the forming process was simulated by finite element analysis software DEFORM-3D. In order to achieve the best forming effect of part, the stamping speed of punch, the rotational speed of die and the forming temperature were selected as the input layer, the damage value and the strain standard deviation of formed parts were chosen as the output layer, and the relationship between input layer and output layer parameters was fit by constructing the BP neural network about process parameters. Furthermore, the optimal solution was found by genetic algorithm based on the constructed neural network. And the optimum parameter combination is the stamping speed of punch of 5.0 mm·s-1, the rotational speed of die of 30 r·min-1 and the forming temperature of 380 ℃. Finally, the actual forming process was conducted by optimal parameters. And the forming effect of part is good, which is basically consistent with the predicted results to verify the correctness of the finite element simulation and optimization and provides guidance for actual production.

基金项目:
内蒙古自治区高等学校科学研究项目(NJZC350)
作者简介:
王剑锋(1974-),男,硕士,高级讲师 E-mail:yishizhi25592588@163.com
参考文献:


[1]刘建鹏, 王震虎,林启权,等.基于正交试验的铝代钢冲压成形工艺参数优化
[J].塑性工程学报, 2018,25(5):110-116.


Liu J P, Wang Z H, Lin Q Q,et al.Optimization of stamping process parameters for aluminum instead of steel based on orthogonal experiment
[J].Journal of Plasticity Engineering,2018,25(5):110-116.



[2]程少博, 于建民,张治民,等.响应面法优化镁合金杯形件旋转挤压参数的研究
[J].热加工工艺,2019, 48(7):136-141.


Chen S B, Yu J M, Zhang Z M,et al. Study on rotary extrusion parameters of magnesium alloy cup parts optimized by response surface method
[J].Hot Working Technology,2019, 48(7):136-141.



[3]刘奇, 李保永,秦中环,等.铝合金空间异形薄壁构件塑性成形工艺
[J].锻压技术,2018,43(11):42-47.


Liu Q, Li B Y, Qin Z H,et al.Study on plastic forming process of aluminium alloy spatially shaped thin-walled components
[J].Forging & Stamping Technology,2018,43(11):42-47.



[4]刘泽, 张星,于建民,等.“肚大口小”筒形件的缩口挤压成形工艺研究
[J].热加工工艺,2018,47(7):115-120.


Liu Z, Zhang X, Yu J M,et al.Research on necking extrusion forming process of cylindrical parts with “Big Belly and Small Mouth”
[J].Hot Working Technology,2018,47(7):115-120.



[5]张文毓. 镁合金挤压技术的研究进展
[J].世界制造技术与装备市场,2018,(4):59-62.


Zhang W S.Research progress of magnesium alloy extrusion technology
[J].World Manufacturing Engineering & Market,2018,(4):59-62.



[6]郭一萍, 陈刚,李睿,等.基于塑性损伤阈值的镁合金构件成形工艺优化
[J].兵器材料科学与工程, 2014, 37(4): 95-97.


Guo Y P, Chen G, Li R,et al.Optimization on forming process of magnesium alloy part based on plastic damage threshold
[J].Ordnance Material Science and Engineering,2014,37(4): 95-97.



[7]潘玲, 李明.基于神经网络的钒钛改性镁合金汽车轮圈锻造工艺优化
[J].热加工工艺,2018,47(3):167-169,173.


Pan L, Li M.Forging process optimization of vanadium-titanium modified magnesium alloy automobile wheel rim based on neural network
[J]. Hot Working Technology,2018,47(3):167-169,173.



[8]温玥, 陈章华.基于各向异性损伤理论的AZ31B镁合金管材热态内压成形性能
[J].机械工程学报,2019,55(18): 70-77.


Wen Y, Chen Z H.Failure analysis of the tube hydroforming process based on anisotropic damage coupling model
[J]. Journal of Mechanical Engineering,2019,55(18): 70-77.



[9]毛志翔, 鲁世红,李正芳,等.电加热渐进成形工艺参数优化及成形温度预测
[J].热加工工艺,2019,48(19):100-103.


Mao Z X, Lu S H, Li Z F,et al.Optimization of process parameters and prediction of forming temperature for electro-heating incremental forming
[J]. Hot Working Technology,2019,48(19):100-103.



[10]孙宪萍, 杨兵,刘强强,等.基于BP神经网络与遗传算法的温挤压模具优化设计
[J].润滑与密封,2017,42(4):84-88.


Sun X P,Yang B, Lin Q Q,et al. Warm extrusion die wear optimization design based on BP neural network and genetic algorithm
[J]. Lubrication Engineering,2017,42(4):84-88.



[11]郭强, 郑燕萍,朱伟庆,等.DP-780高强钢车身侧围板成形质量优化
[J].塑性工程学报,2019,26(1):40-45.


Guo Q, Zheng Y P,Zhu W Q,et al.Quality optimization of side plate forming for DP-780 high strength steel body
[J].Journal of Plasticity Engineering,2019,26(1):40-45.



[12]骆志高, 王祥,李举,等.遗传算法与惩罚函数法在辗轧成形工艺参数优化中的应用
[J].中国机械工程, 2009, 20(14):1704-1707.


Luo Z G, Wang X, Li J,et al.Application of genetic algorithm and penalty function method in roll-forming process parameters optimization
[J].China Mechanical Engineering, 2009, 20(14):1704-1707.

服务与反馈:
本网站尚未开通全文下载服务】【加入收藏
《锻压技术》编辑部版权所有

中国机械工业联合会主管 北京机电研究所有限公司 中国机械工程学会塑性工程分会主办
联系地址:北京市海淀区学清路18号 邮编:100083
电话:+86-010-82415085 传真:+86-010-62920652
E-mail: fst@263.net(稿件) dyjsjournal@163.com(广告)
京ICP备07007000号-9