TY - JOUR T1 - The Neural Network shifted-proper orthogonal decomposition: A machine learning approach for non-linear reduction of hyperbolic equations JF - Computer Methods in Applied Mechanics and Engineering Y1 - 2022 A1 - Davide Papapicco A1 - Nicola Demo A1 - Michele Girfoglio A1 - Giovanni Stabile A1 - Gianluigi Rozza KW - Advection KW - Computational complexity KW - Deep neural network KW - Deep neural networks KW - Linear subspace KW - Multiphase simulations KW - Non linear KW - Nonlinear hyperbolic equation KW - Partial differential equations KW - Phase space methods KW - Pre-processing KW - Principal component analysis KW - reduced order modeling KW - Reduced order modelling KW - Reduced-order model KW - Shifted-POD AB -
Models with dominant advection always posed a difficult challenge for projection-based reduced order modelling. Many methodologies that have recently been proposed are based on the pre-processing of the full-order solutions to accelerate the Kolmogorov N−width decay thereby obtaining smaller linear subspaces with improved accuracy. These methods however must rely on the knowledge of the characteristic speeds in phase space of the solution, limiting their range of applicability to problems with explicit functional form for the advection field. In this work we approach the problem of automatically detecting the correct pre-processing transformation in a statistical learning framework by implementing a deep-learning architecture. The purely data-driven method allowed us to generalise the existing approaches of linear subspace manipulation to non-linear hyperbolic problems with unknown advection fields. The proposed algorithm has been validated against simple test cases to benchmark its performances and later successfully applied to a multiphase simulation. © 2022 Elsevier B.V.
VL - 392 UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124488633&doi=10.1016%2fj.cma.2022.114687&partnerID=40&md5=12f82dcaba04c4a7c44f8e5b20101997 ER -