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

• Published in: Journal of Zhejiang University. Science Vol. 5; no. 1; pp. 75 - 80
• Main Author: 鞠华 王文 谢金 陈子辰
• Format: Journal Article
• Language: English
• Published: China 2004
• Subjects: Algorithms; Artificial Intelligence; CAD; Computer Simulation; Computer-Aided Design; Engineering - methods; Equipment Design - methods; Information Storage and Retrieval - methods; Models, Theoretical; Neural Networks (Computer); Pattern Recognition, Automated; Signal Processing, Computer-Assisted; 制造业; 神经网络; 计算机辅助设计; 逆向工程
• ISSN: 1009-3095
• DOI: 10.1631/jzus.2004.0075

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.