This paper describes a method for defining a coordinate system to parameterize a sampled Pareto frontier of a continuous multi-attribute design problem using a modified self-organizing map. By defining such a coordinate system, the design problem may be reformulated from y = f ( x ) to ( y , x ) = g ( ψ ) , where x is a vector of design variables, y is a vector of attributes, and ψ is a vector of barycentric coordinates. Exploration of the design problem using ψ as the independent variables has the following desirable properties: 1) Every vector ψ corresponds to a Pareto efficient design, and every Pareto efficient design has a corresponding ψ . 2) The number of ψ coordinates is equal to the number of attributes, regardless of the number of design variables. 3) Each attribute y i has a corresponding coordinate ψ i such that the sign of y i / ψ i is positive if the objective is to maximize y i and negative if the objective is to minimize y i (i.e., the attributes improve monotonically as their corresponding coordinates increase). This approach, named the “Pareto simplex self-organizing map” is easily implemented as a postprocessing step to sampling a Pareto frontier with multi-objective optimization. The construction of the coordinates and their use in design space exploration is demonstrated on a conceptual wing design problem.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Representing Sampled Pareto Frontiers as Parameterized Continuous Manifolds Using Self-Organizing Maps


    Beteiligte:

    Erschienen in:

    AIAA Journal ; 52 , 11 ; 2480-2490


    Erscheinungsdatum :

    01.11.2014




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Concept Selection Using s-Pareto Frontiers

    Christopher A. Mattson / Achille Messac | AIAA | 2003


    Using Parameterized Pareto Sets to Model Design Concepts

    Malak, Richard J. | Online Contents | 2010



    Parameterized Continuous Representations of the Pareto Frontier as Decision Aids for Multi-Attribute Design

    Daskilewicz, M. / German, B. / American Institute of Aeronautics and Astronautics; International Society for Structural and Multidisciplinary Optimization | British Library Conference Proceedings | 2014