Modeling for robot high precision grinding based on SVM

被引：3

作者：

Yang Y. ^{[1
]}

Song Y. ^{[1
]}

Liang W. ^{[1
]}

Wang J. ^{[1
]}

Qi L. ^{[2
]}

机构：

[1] Department of Computer Science and Technology, Tsinghua University

[2] Inter Smart Robotic Systems Co., Ltd

来源：

Jiqiren/Robot | 2010年 / 32卷 / 02期

关键词：

Grinding; Modeling; Regression; Robot; SVM (support vector machine);

D O I：

10.3724/SP.J.1218.2010.00278

中图分类号：

学科分类号：

摘要：

To improve the removal control for robot grinding process, we propose a modeling method based on SVM (support vector machine) regression. By analyzing a group of measurable variables relevant to grinding removal, such as robot's speed, contact force and curvature of the workpiece's surface, a regression model is built using machine learning method to predict the grinding removal. In this way, the analysis on a series of complicated dynamic variables could be avoided. The experimental results show that this method could achieve good performance. The prediction accuracy of the model reaches higher than 90%, which basically meets the demand of practical grinding.

引用

页码：278 / 282

页数：4

共 6 条

[1] Huang H., Gong Z.M., Chen X.Q., Et al., Smart robotic system for 3D profile turbine vane airfoil repair, The International Journal of Advanced Manufacturing Technology, 21, 4, pp. 275-283, (2003)
[2] Vapnik V., The Nature of Statistical Learning Theory, (1995)
[3] Cortes C., Vapnik V., Support vector network, Machine Learning, 20, 3, pp. 273-297, (1995)
[4] Du S., Wu T., Support vector machines for regression, Journal of System Simulation, 15, 11, (2003)
[5] Zhu G., Liu S., Yu J., Support vector machine and its applications to function approximation, Journal of East China University of Science and Technology, 28, 5, (2002)
[6] Liu J., Cheng J., Chen J., Support vector machine training algorithm: A review, Information and Control, 31, 1, pp. 45-50, (2002)

← 1 →