方锥件渐进成形工艺优化  

Incremental Forming Process Optimization of Square Cone-shaped Part

作　　者：赵伟[1] 詹艳然[2] 吴胜威 杨凯程 

机构地区：[1]福州大学至诚学院,福建福州350108 [2]福州大学机械工程及自动化学院,福建福州350108

出　　处：《热加工工艺》2014年第23期108-112,共5页Hot Working Technology

基　　金：福建省自然科学基金资助项目(2008J0153);福建省大学生创新创业项目(201313470019)

摘　　要：针对渐进成形中板料严重减薄、易开裂和尺寸精度差及成形效率低等问题,采用BP神经网络建立了优化目标和工艺参数之间的非线性映射关系。然后利用多目标遗传算法(NSGA-II)实现方锥件渐进成形工艺参数的优化。结果表明,采用BP神经网络与多目标遗传算法能很好地优化渐进成形工艺参数,提高零件成形质量。Aiming at the problems of serious thinning, easy cracking of sheet, poor dimensional precision and low forming efficiency in incremental forming, a nonlinear mapping relation between forming process parameters and optimization objective was established based on BP neural network. Then, the optimization of incremental forming process parameters for square cone-shaped part was realized by using the multi-objective genetic algorithm （NSGA-Ⅱ）. The results show that using BP neural network and the multi-objective genetic algorithm can preferably optimize incremental forming process parameters and improve the forming quality of parts.

关 键 词：方锥件 渐进成形 工艺优化 数值模拟 神经网络 

分 类 号：TG386[金属学及工艺—金属压力加工]