Full Text:   <1117>

CLC number: TP391

On-line Access: 

Received: 2002-09-30

Revision Accepted: 2003-01-20

Crosschecked: 0000-00-00

Cited: 1

Clicked: 2705

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
1. Reference List
Open peer comments

Bio-Design and Manufacturing  2022 Vol.5 No.1 P.75~80

10.1631/jzus.2004.0075


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


Author(s):  JU Hua, WANG Wen, XIE Jin, CHEN Zi-chen

Affiliation(s):  Institute of Advanced Manufacturing Engineering, Zhejiang University, Hangzhou 310027, China

Corresponding email(s):   huaju@zju.edu.cn

Key Words:  Reverse engineering, Digitized data, Neural network modification and fitting


Share this article to: More

JU Hua, WANG Wen, XIE Jin, CHEN Zi-chen. Neural network approach for modification and fitting of digitized data in reverse engineering[J]. Journal of Zhejiang University Science D, 2022, 5(1): 75~80.

@article{title="Neural network approach for modification and fitting of digitized data in reverse engineering",
author="JU Hua, WANG Wen, XIE Jin, CHEN Zi-chen",
journal="Journal of Zhejiang University Science D",
volume="5",
number="1",
pages="75~80",
year="2022",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.2004.0075"
}

%0 Journal Article
%T Neural network approach for modification and fitting of digitized data in reverse engineering
%A JU Hua
%A WANG Wen
%A XIE Jin
%A CHEN Zi-chen
%J Journal of Zhejiang University SCIENCE D
%V 5
%N 1
%P 75~80
%@ 1869-1951
%D 2022
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.2004.0075

TY - JOUR
T1 - Neural network approach for modification and fitting of digitized data in reverse engineering
A1 - JU Hua
A1 - WANG Wen
A1 - XIE Jin
A1 - CHEN Zi-chen
J0 - Journal of Zhejiang University Science D
VL - 5
IS - 1
SP - 75
EP - 80
%@ 1869-1951
Y1 - 2022
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.2004.0075


Abstract: 
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.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1] Abdalla, A., Saeid, M. and Behrooz, F., 2000. Automatic segmentation of digitized data for reverse engineering applications. IEE Transactions, 32:59.

[2] Bopaya, B. and Yasser, A.H., 1994. Reverse engineering and its relevance to industrial engineering: a critical review. Computers Industry Engineering, 26(2):343.

[3] Bremer, C. and Drewing, R., 2001. 3D digitizing and data processing for efficient reverse engineering and adaptive manufacturing. http://www.bct.com.

[4] Chen, S., Cowan, C.F.N. and Grant, P.M., 1991. Orthogonal least squares learning algorithm for radial basis function networks. IEEE Transactions on Neural Networks, 2(2):302.

[5] Deng, C.M., Chen, J.H. and Shi, H.M., 2000. An exploration of freeform surface reconstruction by RBF Neural Network. Journal of Computer Aided Design And Computer Graphics, 12:782(in Chinese).

[6] Gu, P. and Yan, X., 1995. Neural network approach to the reconstruction of freeform surfaces for reverse engineering. Computer-Aided Design, 27(1):59.

[7] Huang, M.C. and Tai, C.C., 2000. The pre-processing of data points for curve fitting and reverse engineering. The International Journal of Advanced Manufacturing Technology, 16:635.

[8] Lin, J.C., 2001. Free-form surface rebuild using an abductive neural network. Journal of Materials Processing Technology, 116:170.

[9] Robert, J., James, M. and Roger, J., 1994. Reverse engineering industrial applications. Computers Industry Engineering, 26(2):381.

[10] Seiler, A., Balendran, V., Sivayoganathan, K. and Sackfied, A., 1996. Reverse engineering from uni-directional CMM scan data. The International Journal of Advanced manufacturing Technology, 11:276.

[11] Sun, Z.Q., 1997. Intelligent controlling theory and technology. Tsinghua University Press, Beijing (in Chinese).

[12] Tamas, V., Ralph, R.M. and Jordan, C., 1997. Reverse engineering of geometric models-an introduction. Computer-Aided Design, 29(4):255.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE