HiDeNN-TD: reduced-order hierarchical deep learning neural networks

L Zhang, Y Lu, S Tang, WK Liu - Computer Methods in Applied Mechanics …, 2022 - Elsevier
This paper presents a tensor decomposition (TD) based reduced-order model of the
hierarchical deep-learning neural networks (HiDeNN). The proposed HiDeNN-TD method …

Encapsulated PGD algebraic toolbox operating with high-dimensional data

P Díez, S Zlotnik, A García-González… - Archives of computational …, 2020 - Springer
In its original conception, proper generalized decomposition (PGD) provides explicit
parametric solutions, denoted as computational vademecums or digital abacuses, to …

Nonlinear dimensionality reduction for parametric problems: A kernel proper orthogonal decomposition

P Díez, A Muixí, S Zlotnik… - International Journal for …, 2021 - Wiley Online Library
Reduced‐order models are essential tools to deal with parametric problems in the context of
optimization, uncertainty quantification, or control and inverse problems. The set of …

Separated response surfaces for flows in parametrised domains: comparison of a priori and a posteriori PGD algorithms

M Giacomini, L Borchini, R Sevilla, A Huerta - Finite Elements in Analysis …, 2021 - Elsevier
Reduced order models (ROM) are commonly employed to solve parametric problems and to
devise inexpensive response surfaces to evaluate quantities of interest in real-time. There …

A Proper Generalized Decomposition (PGD) approach to crack propagation in brittle materials: with application to random field material properties

H Garikapati, S Zlotnik, P Díez, CV Verhoosel… - Computational …, 2020 - Springer
Understanding the failure of brittle heterogeneous materials is essential in many
applications. Heterogeneities in material properties are frequently modeled through random …

Nonintrusive parametric NVH study of a vehicle body structure

F Cavaliere, S Zlotnik, R Sevilla… - … based design of …, 2023 - Taylor & Francis
A reduced order model technique is presented to perform the parametric Noise, Vibration
and Harshness (NVH) study of a vehicle body-in-white (BIW) structure characterized by …

A kernel Principal Component Analysis (kPCA) digest with a new backward map** (pre-image reconstruction) strategy

A García-González, A Huerta, S Zlotnik… - arxiv preprint arxiv …, 2020 - arxiv.org
Methodologies for multidimensionality reduction aim at discovering low-dimensional
manifolds where data ranges. Principal Component Analysis (PCA) is very effective if data …

Nonintrusive reduced order model for parametric solutions of inertia relief problems

F Cavaliere, S Zlotnik, R Sevilla… - … Journal for Numerical …, 2021 - Wiley Online Library
Abstract The Inertia Relief (IR) technique is widely used by industry and produces
equilibrated loads allowing to analyze unconstrained systems without resorting to the more …

Tensorial parametric model order reduction of nonlinear dynamical systems

AV Mamonov, MA Olshanskii - SIAM Journal on Scientific Computing, 2024 - SIAM
For a nonlinear dynamical system that depends on parameters, this paper introduces a
novel tensorial reduced-order model (TROM). The reduced model is projection-based, and …

A staggered high-dimensional proper generalised decomposition for coupled magneto-mechanical problems with application to MRI scanners

G Barroso, M Seoane, AJ Gil, PD Ledger… - Computer Methods in …, 2020 - Elsevier
Abstract Manufacturing new Magnetic Resonance Imaging (MRI) scanners represents a
computational challenge to industry, due to the large variability in material parameters and …