三维铝型材挤压模多参数优化  

Optimizing Several Parameters of Three-dimensional Aluminum Profile Extrusion Die

作　　者：郑荣[1] 包忠诩[1] 周天瑞[1] 黄克坚[1] 

机构地区：[1]南昌大学机电工程学院,江西南昌330029

出　　处：《金属成形工艺》2004年第1期69-72,共4页Metal Forming Technology

基　　金：江西教育厅重大项目;南昌大学"211工程"九五标志性项目

摘　　要：　以一个导流组合模为例,利用神经网络建立模具参数的数学模型,用遗传算法对参数优化。其中由正交法设计得到实验样本,由软试模提取模具的SDV值,将其作为优化目标。最终实验结果与优化值吻合,为建立和控制挤压模参数提供了一种行之有效的手段。Die is the heart of extrusion system. Traditional parameters design of extrusion die is mostly set up on the basis of experience. The design has subjectivity and fallibility. This paper, taking a flow-guide die as example,sets up the mathematics model of die parameters with neural network and optimizes the parameters with the genetic algorithm. It takes design experiment samples by orthogonal plan method and regards the SDV values which come from soft trying die as goal of optimizing. Ultimately experimental result and optimizing value are identical, so it is a kind of effectual means for setting up and controlling parameters of extrusion die.

关 键 词：铝型材 挤压模具 神经网络 遗传算法 正交法 优化 导流组合模 

分 类 号：TG375.41[金属学及工艺—金属压力加工]