Using neural networks to predict bending angle of sheet metal formed by laser

被引：82

作者：

Cheng, PJ ^{[1
]}

Lin, SC ^{[1
]}

机构：

[1] Natl Tsing Hua Univ, Dept Power Mech Engn, Hsinchu, Taiwan

来源：

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE | 2000年 / 40卷 / 08期

关键词：

laser forming; neural network; bending angle;

D O I：

10.1016/S0890-6955(99)00111-X

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

In this paper, three supervised neural networks are used to estimate bending angles formed by a laser. Inputs to these neural networks are known forming parameters such as spot diameter, scan speed, laser power, and workpiece geometries including thickness and length of sheet metal workpiece. For comparison, regression models are also used to estimate bending angle. Verification experiments are then conducted to evaluate the performance of these models. It is shown that the radial basis function neural network model is superior to other models in predicting bending angle. The volume energy model is better than the line energy model in angle prediction. (C) 2000 Elsevier Science Ltd. All rights reserved.

引用

页码：1185 / 1197

页数：13