Error analysis for a fast numerical method to a boundary integral equation of the first kind

Jingtang Ma*, Tao Tang

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

2 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)56-68
Number of pages13
JournalJournal of Computational Mathematics
Volume26
Issue number1
Publication statusPublished - Jan 2008

Scopus Subject Areas

  • Computational Mathematics

User-Defined Keywords

  • Boundary integral equation
  • Collocation method
  • Graded mesh

Fingerprint

Dive into the research topics of 'Error analysis for a fast numerical method to a boundary integral equation of the first kind'. Together they form a unique fingerprint.

Cite this