基于进化策略的板材回弹优化建模研究  

Modeling of Sheet Metal Forming Springback Based on Evolutionary Strategy

作　　者：刘文娟[1] 梁志勇[1] 

机构地区：[1]肇庆学院计算机科学与软件学院,广东肇庆526061

出　　处：《计算机技术与发展》2009年第8期243-246,共4页Computer Technology and Development

基　　金：广东省工业攻关项目资助(2004A11403002;2004Z3-D0101;2004A10402002);肇庆学院自然科学研究项目资助(0828)

摘　　要：以回弹最小为目标提出了一种有效的成形工艺优化方法。通过有限元方法对回弹过程进行建模和分析,以获得不同成形工艺条件下的回弹量作为神经网络的样本信号。利用RBFN来模拟复杂的回弹过程。采用改进的进化策略(ES)算法对已建立的回弹模型进行优化以获得最小回弹。结果表明,提出的RBF网络与ES相结合的方法具有全局搜索特性,对于存在不可微的目标函数的非线性优化问题,能以较快的速度和较大概率收敛于全局最优解。In this paper, a method of generating optimal forming process for minimum springbaek is presented. The springback process was modeled and analyzed by using the finite - element method, so as to obtain the springback value for different process parameter as the sample signal of neural network. A radial basis function network （RBFN） was applied to simulate the complex springback process. An improved evolutionary strategy algorithm was used to optimize the identified model for minimum springback. It has been verified that the modeling error of RBFN is extremely smaller than the regression method. The results indicate that optimal process parameters can be quickly and accurately accessed through the proposed approach.

关 键 词：回弹 工艺优化 RBF网络 进化策略 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]