Error Analysis for a Fast Numerical Method to a Boundary Integral Equation of the First Kind

Error Analysis for a Fast Numerical Method to a Boundary Integral Equation of the First Kind

Year:    2008

Journal of Computational Mathematics, Vol. 26 (2008), Iss. 1 : pp. 56–68

Abstract

For two-dimensional boundary integral equations of the first kind with logarithmic kernels, the use of the conventional boundary element methods gives linear systems with dense matrix. In a recent work [J. Comput. Math., 22 (2004), pp. 287-298], it is demonstrated that the dense matrix can be replaced by a sparse one if appropriate graded meshes are used in the quadrature rules. The numerical experiments also indicate that the proposed numerical methods require less computational time than the conventional ones while the formal rate of convergence can be preserved. The purpose of this work is to establish a stability and convergence theory for this fast numerical method. The stability analysis depends on a decomposition of the coefficient matrix for the collocation equation. The formal orders of convergence observed in the numerical experiments are proved rigorously.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/2008-JCM-8610

Journal of Computational Mathematics, Vol. 26 (2008), Iss. 1 : pp. 56–68

Published online:    2008-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    13

Keywords:    Boundary integral equation Collocation method Graded mesh.