Model order reduction in viscoplastic flow modelling using proper orthogonal decomposition and neural networks

Ekaterina A. Muravleva, Ivan V. Oseledets, Dmitry A. Koroteev

    Результат исследований: Глава в книге, отчете, сборнике статейМатериалы для конференциирецензирование

    Аннотация

    This document provides information and instructions for preparing a Full Paper to be included in the Proceedings of ECCM ECFD 2018 Conference. e present a method to construct reduced-order models for duct flows of Bingham media. Our method is based on proper orthogonal decomposition (POD) to find a low-dimensional approximation to the velocity and artificial neural network to approximate the coefficients of a given solution in the constructed POD basis. We use well-established augmented Lagrangian method and finite-element discretization in the “offline” stage. We show that the resulting approximation has a reasonable accuracy, but the evaluation of the approximate solution several orders of magnitude times faster.

    Язык оригиналаАнглийский
    Название основной публикацииProceedings of the 6th European Conference on Computational Mechanics
    Подзаголовок основной публикацииSolids, Structures and Coupled Problems, ECCM 2018 and 7th European Conference on Computational Fluid Dynamics, ECFD 2018
    РедакторыRoger Owen, Rene de Borst, Jason Reese, Chris Pearce
    ИздательInternational Centre for Numerical Methods in Engineering, CIMNE
    Страницы2475-2487
    Число страниц13
    ISBN (электронное издание)9788494731167
    СостояниеОпубликовано - 2020
    Событие6th ECCOMAS European Conference on Computational Mechanics: Solids, Structures and Coupled Problems, ECCM 2018 and 7th ECCOMAS European Conference on Computational Fluid Dynamics, ECFD 2018 - Glasgow, Великобритания
    Продолжительность: 11 июн. 201815 июн. 2018

    Серия публикаций

    НазваниеProceedings of the 6th European Conference on Computational Mechanics: Solids, Structures and Coupled Problems, ECCM 2018 and 7th European Conference on Computational Fluid Dynamics, ECFD 2018

    Конференция

    Конференция6th ECCOMAS European Conference on Computational Mechanics: Solids, Structures and Coupled Problems, ECCM 2018 and 7th ECCOMAS European Conference on Computational Fluid Dynamics, ECFD 2018
    Страна/TерриторияВеликобритания
    ГородGlasgow
    Период11/06/1815/06/18

    Fingerprint

    Подробные сведения о темах исследования «Model order reduction in viscoplastic flow modelling using proper orthogonal decomposition and neural networks». Вместе они формируют уникальный семантический отпечаток (fingerprint).

    Цитировать