• Login
    View Item 
    •   NZSEE Document Repository
    • New Zealand Society for Earthquake Engineering
    • Proceedings of the 2023 New Zealand Society for Earthquake Engineering Annual Technical Conference
    • View Item
    •   NZSEE Document Repository
    • New Zealand Society for Earthquake Engineering
    • Proceedings of the 2023 New Zealand Society for Earthquake Engineering Annual Technical Conference
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Learning Importance Sampling Distributions via Normalizing Flows to Estimate Rare-Event Failure Probabilities

    Thumbnail
    Download
    PDF (635.1Kb)
    Date
    2023-04-19
    Authors
    Dasgupta, Agnimitra
    Johnson, Erik
    Metadata
    Show full item record
    Abstract
    Engineered systems are typically designed to be robust and have very low probabilities of failure. However, developing accurate estimates of these probabilities can be challenging given the complex (and typically nonlinear) nature of the system behavior and the computational cost of simulating a sufficient number of realizations/scenarios to capture the failure modes. Among other approaches, importance sampling can reduce the computational cost and/or the variance in failure probability estimates; however, the optimal importance sampling distribution can only be computed if the failure probability is already known. This work proposes to use normalizing flows (NFs), a type of machine learning model, to learn a near-optimal importance sampling distribution. NFs are generative modeling techniques amenable to exact, but efficient, density evaluation. The approach is first evaluated on a suite of challenging benchmark reliability estimation problems, comparing against two techniques widely adopted for similar tasks: subset simulation and the cross-entropy method; the results show that the proposed approach can be used to estimate rare-event probability in cases that have extremely low failure probabilities on the order of 10^(-7), high-dimensionality, and multiple failure modes. Finally, the proposed approach is applied to estimate the reliability of two structural mechanics examples.
    URI
    https://repo.nzsee.org.nz/handle/nzsee/2629
    Published in
    • Proceedings of the 2023 New Zealand Society for Earthquake Engineering Annual Technical Conference

    Contact Us | Send Feedback
     

     

    Browse

    Entire RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    Login

    Contact Us | Send Feedback