RBF Neural Network Arithmetic and Applications in Surface Interpolation Reconstruction

X.M. Wu; Gui Xian Li; De Bin Shan; G.B. Yu

doi:10.4028/www.scientific.net/KEM.460-461.575

Paper Titles

Mesh Partitioning Optimization in Parallel Substructure Method Using Improved HYT Approach
p.558

Characteristic Analysis of Textile Materials Based on Pre-Judgment Mechanism
p.562

Feature Model of Fabrics Irregular Defect
p.566

Assessment of Flight Simulator Fidelity for Pitch Task
p.569

RBF Neural Network Arithmetic and Applications in Surface Interpolation Reconstruction
p.575

Error Analysis and Precision Evaluation of Reconstructed Surfaces in Reverse Engineering
p.581

A Servlet Grouping Framework with Non-Intrusive Implementation
p.587

Discuss on China's Green Building Materials Development
p.593

Application of Wavelet Transform in the Prediction of Chemical Composition of Sunflower Seeds by Near Infrared Reflectance Spectroscopy
p.599

HomeKey Engineering MaterialsKey Engineering Materials Vols. 460-461RBF Neural Network Arithmetic and Applications in...

RBF Neural Network Arithmetic and Applications in Surface Interpolation Reconstruction

Abstract:

Aiming at problems such as: surface interpolation reconstruction of points cloud data，surface hole filling and two simple surface connection, a neural network arithmetic was employed. Based on radial basis function neural network, simulated annealing was employed to adjust the network weights. The new arithmetic can approach any nonlinear function by arbitrary precision, and also keep the network from getting into local minimum for global optimization feature of simulated annealing. MATLAB program was compiled, experiments on points cloud data have been done employing this arithmetic, the result shows that this arithmetic can efficiently approach the surface with 10-4 mm error precision, and also the learning speed is quick and reconstruction surface is smooth.

You might also be interested in these eBooks

Components, Packaging and Manufacturing Technology

View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 460-461)

Pages:

575-580

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.460-461.575

Citation:

Cite this paper

Online since:

January 2011

Authors:

X.M. Wu, Gui Xian Li, De Bin Shan, G.B. Yu

Keywords:

Points Cloud Data, Radial Basis Function Neural Network (RBFNN), Simulated Annealing Arithmetic, Surface Interpolation Reconstruction

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] G. Casciola, D. Lazzaro, L.B. Montefusco and S. Morigi: Fast Surface Reconstruction and Hole Filling Using Positive Definite Radial Basis Functions, Numerical Algorithms, Vol. 39(2005), pp.289-305.

DOI: 10.1007/s11075-004-3643-8

Google Scholar

[2] Y. Xing, Y. Wang and X.Y. Ruan: A Neural Network Approach on Reverse Engineering Surface Reasoning in the Manufacturing Field, High Technology Letters, Vol. 7 (2001) No. 3, pp.49-54. (In Chinese).

Google Scholar

[3] Y.G. Fan, X.M. Liu and J. Chen: Approach of NURBS Free-form Surface Reconstruction from Scattered Data Based on RBFNN, Computer Engineering and Application, (2005) 11, pp.66-69. (In Chinese).

Google Scholar

[4] K. Wang, C.M. Zhang: Neural Network Method to Reconstruct the Freeform Surface, CAD﹠CG, Vol. 10 (1998) No. 3, pp.193-199. (In Chinese).

Google Scholar

[5] D. Shi, D.S. Yeung and J. Gao: Sensitivity Analysis Applied to the Construction of Radial Basis Function Networks, Neural Networks, Vol. 18 (2005), pp.951-957.

DOI: 10.1016/j.neunet.2005.02.006

Google Scholar

[6] P. Gu, X. Yan: Neural Network Approach to the Reconstruction of Freeform Surface for Reverse Engineering, Computer-Aided Design, Vol. 27 (1995) No. 1, pp.59-64.

DOI: 10.1016/0010-4485(95)90753-3

Google Scholar