盒形件拉深智能化控制实时识别及预测  

Real-time Identification and Prediction for Intelligent Control of Rectangular Box Drawing

作　　者：苏春建[1] 赵军[1] 官英平[1] 马瑞[1] 

机构地区：[1]燕山大学,秦皇岛066004

出　　处：《中国机械工程》2008年第3期351-354,共4页China Mechanical Engineering

基　　金：国家自然科学基金资助项目(50375136);高等学校博士学科点专项科研基金资助项目(20050216013)

摘　　要：在板材成形智能化控制的4个基本要素中,材料性能参数的实时识别及最优工艺参数的预测是最复杂的两个要素。识别和预测精度的高低,将直接影响智能化控制成功与否。以盒形件智能拉深控制为研究对象,建立了盒形拉深件的材料性能参数和摩擦因数的实时识别前馈神经网络,通过实时监测来实时识别所需要的材料性能参数,并预测最优的工艺参数,从而获得了较高的收敛精度。In the four basic factors on the intellectualization of sheet metal forming, the real-time identification of the material performance parameter and the prediction of the optimum technological parameter are the most complicated ones. The accuracy of identification and prediction will have direct effect on the success of the intelligence control. Taking the intelligence control of rectangular box as an object of study, feed forward neural network model based on LM algorithm had been established to realize material properties and friction coefficient for deep drawing of rectangular box. By means of real- time monitoring and measuring to identify the material performance parameters and to predict the optimum technological parameters, and a satisfied accuracy of convergence is achieved.

关 键 词：板材成形 智能化 神经网络 实时识别 参数预测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]