交互式挤压模具智能优化设计系统研究  

Interactive intelligent optimization design system for extrusion-die

作　　者：邹琳[1] 夏巨谌[2] 

机构地区：[1]华南理工大学工业装备与控制工程学院,广东广州510460 [2]华中科技大学塑性成形模拟及模具技术国家重点实验室,湖北武汉430074

出　　处：《模具工业》2006年第8期19-23,共5页Die & Mould Industry

基　　金：广东省自然科学基金项目博士启动基金(05300256)

摘　　要：在高效无敏度智能优化算法及挤压成型过程数值模拟的基础上,结合刚—黏塑性有限元模拟、神经网络、遗传算法,提出一种交互式挤压模具智能优化设计方法。并利用面向对象编程技术C++语言,在VC++6.0程序开发器上开发出了界面友好、自动化程度高、模块通用性好的交互式挤压模具优化设计系统,实现了挤压过程中模具设计多种目标的优化控制,并详细阐述了系统的结构功能、关键技术及应用实例。由于数值模拟、人工神经网络和遗传算法属于非耦合算法,通用性较强,该系统适用于金属塑性成形各种领域的优化设计。On the basis of highly effective intelligent optimization algorithm and numerical simulation for extrusion forming process, and by applying rigidity-viscoplasticity finite element modelling, neural network and genetic algorithms, an interactive intelligent optimization design method for extrusion-die was put forward. By using object-oriented program technique language C＋＋, an interactive intelligent optimization design system for extrusion die with friendly interface, high automaticity and module versatility was developed on VC＋＋ program development device. The optimization control of multi-objects in design of extrusion die was achieved. The structural function, key technology and example of application were described in detail. As numerical simulation, artificial neural network and genetic algorithms belong to uncoupling algorithm. They have high versatility and fit for optimization design of varieties of metal plastic forming.

关 键 词：遗传算法 神经网络 刚-粘塑性有限元模拟 挤压模具优化 

分 类 号：O242.21[理学—计算数学] TG375.41[理学—数学]