Global optimization of discrete truss topology design problems using a parallel cut-and-branch method

Marie-Louise Højlund Rasmussen, Mathias Stolpe

    Research output: Contribution to journalJournal articleResearchpeer-review

    Abstract

    The subject of this article is solving discrete truss topology optimization problems with local stress and displacement constraints to global optimum. We consider a formulation based on the Simultaneous ANalysis and Design (SAND) approach. This intrinsically non-convex problem is reformulated to a mixed-integer linear program, which is solved with a parallel implementation of branch-and-bound. Additional valid inequalities and cuts are introduced to give a stronger representation of the problem, which improves convergence and speed up of the parallel method. The valid inequalities represent the physics, and the cuts (Combinatorial Benders’ and projected Chvátal–Gomory) come from an understanding of the particular mathematical structure of the reformulation. The impact of a stronger representation is investigated on several truss topology optimization problems in two and three dimensions.
    Original languageEnglish
    JournalComputers & Structures
    Volume86
    Issue number13-14
    Pages (from-to)1527-1538
    ISSN0045-7949
    DOIs
    Publication statusPublished - 2008

    Keywords

    • Parallel computing
    • Discrete bar areas
    • Stress constraints
    • Cut-and-branch
    • Truss topology optimization
    • Global optimization

    Fingerprint

    Dive into the research topics of 'Global optimization of discrete truss topology design problems using a parallel cut-and-branch method'. Together they form a unique fingerprint.

    Cite this