Neural network approach for modification and fitting of digitized data in reverse engineering~

作     者：鞠华 王文 谢金 陈子辰 

作者机构：InstituteofAdvancedManufacturingEngineeringZhefiangUniversityHangzhou310027China 

基　　金：Provincial Key Science and Technology Planning of Zhejiang Province 

出 版 物：《Journal of Zhejiang University Science》 (浙江大学学报（自然科学英文版）)

年 卷 期：2004年第5卷第1期

页      码：75-80页

摘      要：Reverse engineering in the manufacturing field is a process in which the digitized data are obtained from an existing object model or a part of it, and then the CAD model is reconstructed. This paper presents an RBF neural network approach to modify and fit the digitized data. The centers for the RBF are selected by using the orthogonal least squares learning algorithm. A mathematically known surface is used for generating a number of samples for training the networks. The trained networks then generated a number of new points which were compared with the calculating points from the equations. Moreover, a series of practice digitizing curves are used to test the approach. The results showed that this approach is effective in modifying and fitting digitized data and generating data points to reconstruct the surface model.

主 题 词：Reverse engineering Digitized data Neural network modification and fitting 

学科分类：12[管理学] 13[艺术学] 08[工学] 1305[艺术学-设计学类] 1201[管理学-管理科学与工程类] 081104[081104] 080203[080203] 081304[081304] 0835[0835] 0802[工学-机械学] 0813[工学-化工与制药类] 0811[工学-水利类] 080201[080201] 0812[工学-测绘类] 

核心收录：

D　O　I：10.1007/BF02839316

馆 藏 号：203521472...