An Investigation of Interpolation Scheme Based on Indirect Radial Basis Neural Networks

Hai Tao Sun

doi:10.4028/www.scientific.net/AMM.226-228.2181

Paper Titles

Design and Implementation of Optimal Noise Shaping Filters
p.2163

Realization and Comparison of System Identification Based on Different Least Squares Methods
p.2167

Damage Detection in a Cracked Rod Using High-Frequency Electro-Mechanical Impedance Signatures
p.2171

Design and Analysis of Flexure Hinge in the Double Crystal Monochromator
p.2175

An Investigation of Interpolation Scheme Based on Indirect Radial Basis Neural Networks
p.2181

Molecular Dynamics Simulation of Crack Propagation for Leak Before Break (LBB)
p.2189

Cushion Surface Modeling Based on Body Pressure Distribution and Subjective Rating
p.2193

Numerical Simulation of the Impact between the Front-End-Coated Projectile and the Substrate Coated by Ceramic Film
p.2198

A Real Electronic System to Control Virtual Machine in NC Machining Simulation
p.2203

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 226-228An Investigation of Interpolation Scheme Based on...

An Investigation of Interpolation Scheme Based on Indirect Radial Basis Neural Networks

Abstract:

An indirect radial basis neural network (IRBNN) is proposed for improving the accuracy of the approximated functions. The IRBNN is constructed by new prompted functions generated from the Nth order derivative of the approximated function. In this way, high accuracy derivatives in different order can be obtained, so that more accuracy of the numerical results would be given while the IRBNN is employed for creating approximated functions in numerical methods. Numerical results through applications in elasticity show the effectiveness and accuracy of the IRBNN method.

You might also be interested in these eBooks

Vibration, Structural Engineering and Measurement II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 226-228)

Pages:

2181-2188

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.226-228.2181

Citation:

Cite this paper

Online since:

November 2012

Authors:

Hai Tao Sun

Keywords:

Indirect Radial Basis Neural Networks, Interpolation Scheme, Numerical Method

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Zienkiewicz O. C.. Finite Elements and Approximation. New York: John Wiley & Sons, 1982.

Google Scholar

[2] Belytschko, T., Krongauz, Y., Organ, D., Fleming, M., Krysl, P.Meshless methods: an overview and recent developments. Computer Methods in Applied Mechanics and Engineering, 96, 139(1-4):3-47.

DOI: 10.1016/s0045-7825(96)01078-x

Google Scholar

[3] Watson F. Neighborhood-based interpolation. Geobyte, 1987, 2(2):12-16.

Google Scholar

[4] Traversoni L. An algorithm for nature spline interpolation. Numer. Algorithms, 1993(5):63-70.

Google Scholar

[5] Mai-Duy Nam, Tran-Cong Thanh. An effective RBFN-boundary integral approach for the analysis of natural convection flow. International Journal for Numerical Methods in Fluids, 2004, 46(5):545-568.

DOI: 10.1002/fld.769

Google Scholar

[6] Mai-Duy Nam, Tran-Cong Thanh. Approximation of function and its derivatives using radial basis function networks. Applied Mathematical Modelling, 2003, 27(3):197-220.

DOI: 10.1016/s0307-904x(02)00101-4

Google Scholar

[7] Mai-Duy N. Tanner R. I. An effective high order interpolation scheme in BIEM for biharmonic boundary value problems. Engineering Analysis with Boundary Elements, 2005, 29(3):210-223.

DOI: 10.1016/j.enganabound.2005.01.005

Google Scholar

[8] Sun Haitao, Wang Yuanhan. The MESHLESS VIRTURAL BOUNDARY METHOD AND ITS APPLICATIONS TO THE 2D ELASTICITY PROBLEMS. Acta Mechnica Solida Sinica, Vol.20,No.1,March,2007.

DOI: 10.1007/s10338-007-0704-2

Google Scholar