A hybrid graph–neural method for domain decomposition

Download
  1. Get@NRC: A hybrid graph–neural method for domain decomposition (Opens in a new window)
DOIResolve DOI: http://doi.org/10.1016/S0045-7949(98)00209-0
AuthorSearch for: ; Search for: ; Search for:
TypeArticle
Journal titleComputers and Structures
ISSN0045-7949
Volume70
Issue6
Pages667674; # of pages: 8
SubjectDomain decomposition; Graph theory; Neural networks; Hybrid method; Finite elements; parallel computation
AbstractA hybrid method is presented for domain decomposition employing a graph theoretical algorithm and a neural network optimization model. The method uses graph theory and neural networks for decomposition of structured finite element meshes. Examples are presented to illustrate the efficiency of the developed method.
Publication date
LanguageEnglish
Peer reviewedYes
NPARC number21274160
Export citationExport as RIS
Report a correctionReport a correction
Record identifier062aaadd-8bcf-4d24-bf29-898d55bbd565
Record created2015-02-19
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)