第42卷第7期 Vol. 42No. 7
假压技术
FORGING & STAMPING TECHNOLOGY
锂离子电池电芯铝塑膜外壳冲压成形工艺
赵
越，肖艳春，崔佳，于盼，关玉明
（河北工业大学机械工程学院，天津300130）
2017年7月 Jul.2017
摘要：通过正交试验，应用有限元仿真，对影响锂离子电池铝塑膜外壳冲压成形质量的各工艺参数的显著性进行分析，得出凸模圆角半径与凹模摩擦系数的选择对铝塑膜冲压工艺质量影响较大，利用数值模拟以及BP神经网络与遗传算法极值寻优，对锂离子电池铝塑膜的冲压成形工艺参数（凸模角半径、冲压速度、凹模摩擦系数以及压边力）进行优化。优化后的工艺参数使得锂离子电池铝塑膜的最大减薄率减少10%。实验证明，成形铝塑膜外壳的边角位置碱薄最为严重，是影响成形铝塑膜外壳整体质量的关键性固素，可以作为衡量锂离子电池铝塑膜外壳成形质量检验的标准。
关键词：锂离子电池：铝塑膜：冲压；正交试验；BP神经网络；遗传算法 DOI: 10. 13330/j. issn. 1000-3940. 2017. 07. 009
中图分类号：TP391
文献标识码：A
文章编号：1000-3940（2017）07-0048-07
Stamping process of aluminum plastic film shell for Li-ion battery core
Zhao Yue, Xiao Yanchun, Cui Jia, Yu Pan, Guan Yuming
( School of Mechanical Engineering, Hebei University of Technology, Tianjin 300130, China)
Abstract: The significance of each process parameter which effects on stamping forming quality of aluminum plastic flm shell for lithium ion batery was analyzed by orthogonal test and FE simulation, and it shows that the punch fllet radius and die friction coefficient are the most significant. Then, the process parameters including punch fillet radius, stamping speed, die friction coefficient and blank holder force were optimized by numerical simulation and extremum seeking method eombining BP neural network with genetic algorithm. There-fore, the maximum thinning rate of aluminum plastic film of lithium ion battery is reduced by 10% after optimization. Experiments show that the thinning rate of the cormer position of aluminum plastic film shell is the maximum and the key factor affecting the overall quality of aluminum plastic film shell. Thus, it can be: used as quality inspection standard of aluminum plastic film shell for lithium ion battery. Key words : lithium ion battery: aluminum plastic film; stamping; orthogonal test; BP neural network; genetic algorithm
随着软包锂离子电池的广泛应用，对软包锂离
收稿日期：20170213；修订日期：20170506 基金项目：天津市科技特员项目（14JCTPJ(00532）
作者简介：赵越（1992-），男，硕士研究生 E-mail:516162010@ qq com
通讯作者：关玉明（1957-），男，博士，教授，博士生导师 E-mail: gyuming@ 163. com
Zhang X B, Sun Y, Dai S. Study on the peediction technology of variable blank-holding force for deep drawing forming of cup shaped parts based on radial busis neural netwerk [J]. Mechani-cal Design, 2007, 24 (8) : 36 38
田银.基于RBF神经网路的变压边力优化研究D]-成都：
[12]
西南交通大学，2015
Tian Y. Research on the Optimization of Variable Blank Holder Force Based on RBF Neural Nehrork [ D]. Chengdu: Southwest Jiaotong University , 2015.
[13]
Kamali K. Application of a hybrid GA BP optimized neural net
万方数据
子电池过充安全性能的关注度也越来越高，为防止软包装锂离子电池在过充、短路等不正常操作下，引起起火甚至爆炸，需要铝塑膜具有一定的延展性，以便起到缓冲作用。因此，铝塑膜多采用PP和PE 相结合的复合隔膜层依次隔离电芯电极的措施实现过充保护。但同时，该外壳也存在一定的缺陷，由于铝塑膜材料的基体较薄，很容易在产品生产过程中发生破损，给生产带来不便。
work foe springhuck estimation in sheet metal foming proces [A] Joint Congress on Fuzy and Intelligent Systems [C]. Iran, 2007
[14] Zoan B, Alpaslan. Artificial neural etwoeks for the cost estimation
of stamping dies [J]. Neural Computing and Applications, 2014, 25 (3) : 717 726.
[15]
赵军，马瑞，王风琴，等，盒形件拉深智能化控制关键技术研究[J].塑性工程学报，2005，12（3)：6770
Zhao J, Ma R, Wang F Q, et al. Study on the key technologies o intelligent control for rectangular bos deep drawing [J]. Journal of Plasticity Engineering, 2005, 12 (3) : 67 70.