轴对称件智能拉深系统中的神经网络参数识别  

Parameter identification via neural network intellectual control process for axisymmetric workpieces deep drawing

作　　者：王凤琴[1] 赵军[1] 官英平[1] 郑祖伟[2] 

机构地区：[1]燕山大学机械学院,河北秦皇岛066004 [2]上海交通大学,上海200030

出　　处：《锻压装备与制造技术》2003年第3期67-70,共4页China Metalforming Equipment & Manufacturing Technology

基　　金：国家自然科学基金资助项目(59875074)

摘　　要：建立了轴对称拉深件的材料性能参数和摩擦系数实时识别前馈神经网络,采用LM算法优化网络,将参数识别精度提高到一个新水平,为智能化拉深成形的实时预测和实时控制这两个基本要素提供了前提保证,为实现整个拉深成形过程的智能化控制奠定基础。Feed forward neural network model based on LM algorithm has been established to realize material proper-ties and friction coefficient for deep drawing of axisymmetric workpieces.The error goal of parameter identification has been improved to a new level,which provide precondition as well as assurance for real-time prediction and real-time control,hence intellectualization control for the whole process of deep drawing has been ensured.

关 键 词：轴对称件 智能拉深系统 神经网络 参数识别 LM算法 实时预测 实时控制 

分 类 号：TG386.32[金属学及工艺—金属压力加工] TP183[自动化与计算机技术—控制理论与控制工程]