锻压技术

AZ31B镁合金电流辅助旋压回弹角预测及工艺参数优化

英文标题：Prediction on springback angle and process parameter optimization in electro-assisted spinning for AZ31B magnesium alloy

作者：王辉廖旭洲蔡继文詹玉婷

单位：南京航空航天大学

关键词：电流辅助旋压回弹角 AZ31B镁合金 BP神经网络正交实验

分类号：TG306

出版年,卷(期):页码：2022,47(8):29-34

摘要：

在金属旋压工艺中，回弹是一种无法避免的成形缺陷，为了减小旋压制件的回弹，在电流辅助旋压的基础上，以AZ31B镁合金旋压件为研究对象，通过正交实验探究了电流强度、主轴转速、旋压轮进给速率与回弹角的关系，对实验结果进行了极差分析和方差分析，得到了工艺参数对回弹角的影响规律及最小回弹角的工艺参数组合。以实验数据作为训练样本，建立了BP神经网络模型进行回弹角预测，将实验得到的工艺参数组合作为输入，进行回弹角预测及实验验证，结果表明：BP神经网络模型的预测结果与实验结果的相对误差小于3%，能够较准确地预测回弹角，为实际生产和进一步的实验研究提供了理论指导。

Springback is one of the unavoidable forming defect in metal spinning process. Therefore, in order to reduce the springback of spinning parts，on the basis of electro-assisted spinning, for AZ31B magnesium alloy spinning parts, the relationship between current intensity, spindle rotate speed, spinning roller feeding rate and springback angle was explored by orthogonal experiment, and the experiment results were analyzed by range analysis and variance analysis to obtain the influence laws of process parameters on the springback angle and the process parameters combination of the minimum springback angle. Then, taking the experimental data as training sample, the BP neural network model was established to predict the springback angle, and the combination of the process parameters obtained in the experiment was used as input to predict the springback angle and conduct the experimental verification. The results show that the relative error between the BP neural network model prediction results and the experiment results is less than 3%, which can accurately predict the springback angle. Furthermore，it provides theoretical guidance for actual production and further experimental research.

基金项目：

南京航空航天大学科技创新基金(NS2016052)

作者简介：王辉（1978-），男，博士，讲师，E-mail：wh508@nuaa.edu.cn；通信作者：廖旭洲（1995-），男，硕士研究生，E-mail：2909615591@qq.com

参考文献：

[1]徐洪烈. 强力旋压技术[M]. 北京:国防工业出版社, 1984.

Xu H L.Power Spinnig Technology [M]. Beijing：National Defense Industry Press,1984.

[2]李姗, 王伯健.变形镁合金的研究与开发应用[J].热加工工艺,2007，(6):65-68.

Li S, Wang B J. Research and application development of wrought magnesium alloy [J].Hot Working Technology,2007，(6):65-68.

[3]蒋斌, 刘文君,肖旅,等.航空航天用镁合金的研究进展[J].上海航天,2019,36(2):22-30.

Jiang B，Liu W J,Xiao L,et al. Development of magnesium alloys for aerospace application[J]. Aerospace Shanghai,2019,36(2):22-30.

[4]李晓光, 杨文兵,单易,等.轻合金电致塑性成形技术研究进展[J].模具技术,2020，(4):56-63.

Li X G,Yang W B, Shan Y,et al. Development of electroplastic forming technique for light alloys[J]. Die and Mould Technology,2020，(4):56-63.

[5]Conrad H. Thermally activated deformation of metals[J]. JOM, 1964, 16(7):582-588.

[6]Troitskii O A,Likhtman V I. The anisotropy of the action of electron and radiation on the deformation of zine single crystal in the brittle state[J]. Soviet Physics Doklady,1963,17(148):332-334.

[7]Conrad H， Troitskii O A. The electroplastic effect in metals[J]. Strength of Materials, 1984,16(2):277-281.

[8]周政. BP神经网络的发展现状综述[J].山西电子技术,2008，(2):90-92.

Zhou Z. Survey of current progress in BP neural network[J]. Shanxi Electronic Technology,2008，(2):90-92.

[9]吉梦雯, 樊文欣,张涛,等.基于BP神经网络的连杆衬套强力旋压轴线直线度预测[J].塑性工程学报,2018,25(1):137-141.

Ji M W,Fan W X, Zhang T,et al. Prediction of axial straightness of connecting rod bushing power spinning based on BP neural network[J]. Journal of Plasticity Engineering,2018,25(1):137-141.

[10]冯志刚, 樊文欣,赵俊生,等.基于BP神经网络的强力旋压成形连杆衬套壁厚预测[J].热加工工艺,2014,43(3):129-130，134.

Feng Z G, Fan W X, Zhao J S,et al. Wall thickness prediction of connecting rod bushing of power spinning forming based on BP neural network[J]. Hot Working Technology,2014,43(3):129-130，134.

[11]张敏, 黎向锋,左敦稳,等.基于主成分分析的BP神经网络内螺纹冷挤压成形质量预测[J].中国机械工程,2012,23(1):51-54.

Zhang M, Li X F,Zuo D W,et al. Forming quality forecast for internal threads formed by cold extrusion based on principal component analysis and neural networks[J]. China Mechanical Engineering,2012,23(1):51-54.

[12]范有发, 李东南, 陈文哲. AZ31B 镁合金板材旋压成形工艺研究[J]. 中国机械工程, 2012, 23(11):1272-1275.

Fan Y F,Li D N, Chen W Z. Study on spinning process of AZ31B magnesium alloy sheet[J]. China Mechanical Engineering, 2012, 23(11):1272-1275.

[13]Wang L F, Huang G S, Li H C, et al. Influence of strain rate on microstructure and formability of AZ31B magnesium alloy sheets[J]. Transactions of Nonferrous Metals Society of China, 2013, 23(4):916-922.

[14]毛柏平, 汪发春,赵云豪,等.钛合金旋压性能的试验研究[J].稀有金属,2004，28(1):271-273.

Mao B P,Wang F C,Zhao Y H,et al.Study on spinning properties of titanium alloy[J].Chinese Journal of Rare Metals,2004，28(1):271-273.

[15]邱轶兵. 试验设计与数据处理[M]. 合肥：中国科学技术大学出版社, 2008.

Qiu Y B. Experiment Design and Data Processing[M]. Hefei：University of Science and Technology of China Press, 2008.

服务与反馈：

【文章下载】【加入收藏】