Robust optimization based on analytical evaluation of uncertainty propagation

Omid Nejadseyfi (Corresponding Author), Hubertus J.M. Geijselaers, Antonius H. van den Boogaard

    Research output: Contribution to journalArticleAcademicpeer-review

    1 Citation (Scopus)
    21 Downloads (Pure)

    Abstract

    Optimization under uncertainty requires proper handling of those input parameters that contain scatter. Scatter in input parameters propagates through the process and causes scatter in the output. Stochastic methods (e.g. Monte Carlo) are very popular for assessing uncertainty propagation using black-box function metamodels. However, they are expensive. Therefore, in this article a direct method of calculating uncertainty propagation has been employed based on the analytical integration of a metamodel of a process. Analytical handling of noise variables not only improves the accuracy of the results but also provides the gradients of the output with respect to input variables. This is advantageous in the case of gradient-based optimization. Additionally, it is shown that the analytical approach can be applied during sequential improvement of the metamodel to obtain a more accurate representative model of the black-box function and to enhance the search for the robust optimum.
    Original languageEnglish
    Number of pages23
    JournalEngineering Optimization
    DOIs
    Publication statusPublished - 20 Nov 2018

    Fingerprint

    Uncertainty Propagation
    Robust Optimization
    Scatter
    Metamodel
    Black Box
    Evaluation
    Analytical Integration
    Gradient
    Optimization
    Output
    Stochastic Methods
    Direct Method
    Monte Carlo methods
    Uncertainty
    Robust optimization
    Propagation
    Black box
    Model

    Keywords

    • UT-Hybrid-D
    • Sensitivity analysis
    • Uncertainty modelling
    • Sequential Optimization
    • metamodel based optimization
    • robustness

    Cite this

    @article{1a72886ccc8644338c858b46c59f7f48,
    title = "Robust optimization based on analytical evaluation of uncertainty propagation",
    abstract = "Optimization under uncertainty requires proper handling of those input parameters that contain scatter. Scatter in input parameters propagates through the process and causes scatter in the output. Stochastic methods (e.g. Monte Carlo) are very popular for assessing uncertainty propagation using black-box function metamodels. However, they are expensive. Therefore, in this article a direct method of calculating uncertainty propagation has been employed based on the analytical integration of a metamodel of a process. Analytical handling of noise variables not only improves the accuracy of the results but also provides the gradients of the output with respect to input variables. This is advantageous in the case of gradient-based optimization. Additionally, it is shown that the analytical approach can be applied during sequential improvement of the metamodel to obtain a more accurate representative model of the black-box function and to enhance the search for the robust optimum.",
    keywords = "UT-Hybrid-D, Sensitivity analysis, Uncertainty modelling, Sequential Optimization, metamodel based optimization, robustness",
    author = "Omid Nejadseyfi and Geijselaers, {Hubertus J.M.} and {van den Boogaard}, {Antonius H.}",
    note = "Taylor & Francis deal",
    year = "2018",
    month = "11",
    day = "20",
    doi = "10.1080/0305215X.2018.1536752",
    language = "English",
    journal = "Engineering Optimization",
    issn = "0305-215X",
    publisher = "Taylor & Francis",

    }

    Robust optimization based on analytical evaluation of uncertainty propagation. / Nejadseyfi, Omid (Corresponding Author); Geijselaers, Hubertus J.M.; van den Boogaard, Antonius H.

    In: Engineering Optimization, 20.11.2018.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Robust optimization based on analytical evaluation of uncertainty propagation

    AU - Nejadseyfi, Omid

    AU - Geijselaers, Hubertus J.M.

    AU - van den Boogaard, Antonius H.

    N1 - Taylor & Francis deal

    PY - 2018/11/20

    Y1 - 2018/11/20

    N2 - Optimization under uncertainty requires proper handling of those input parameters that contain scatter. Scatter in input parameters propagates through the process and causes scatter in the output. Stochastic methods (e.g. Monte Carlo) are very popular for assessing uncertainty propagation using black-box function metamodels. However, they are expensive. Therefore, in this article a direct method of calculating uncertainty propagation has been employed based on the analytical integration of a metamodel of a process. Analytical handling of noise variables not only improves the accuracy of the results but also provides the gradients of the output with respect to input variables. This is advantageous in the case of gradient-based optimization. Additionally, it is shown that the analytical approach can be applied during sequential improvement of the metamodel to obtain a more accurate representative model of the black-box function and to enhance the search for the robust optimum.

    AB - Optimization under uncertainty requires proper handling of those input parameters that contain scatter. Scatter in input parameters propagates through the process and causes scatter in the output. Stochastic methods (e.g. Monte Carlo) are very popular for assessing uncertainty propagation using black-box function metamodels. However, they are expensive. Therefore, in this article a direct method of calculating uncertainty propagation has been employed based on the analytical integration of a metamodel of a process. Analytical handling of noise variables not only improves the accuracy of the results but also provides the gradients of the output with respect to input variables. This is advantageous in the case of gradient-based optimization. Additionally, it is shown that the analytical approach can be applied during sequential improvement of the metamodel to obtain a more accurate representative model of the black-box function and to enhance the search for the robust optimum.

    KW - UT-Hybrid-D

    KW - Sensitivity analysis

    KW - Uncertainty modelling

    KW - Sequential Optimization

    KW - metamodel based optimization

    KW - robustness

    U2 - 10.1080/0305215X.2018.1536752

    DO - 10.1080/0305215X.2018.1536752

    M3 - Article

    JO - Engineering Optimization

    JF - Engineering Optimization

    SN - 0305-215X

    ER -