Parametric reduced-order modeling for component-oriented treatment and localized nonlinear feature inclusion

K Vlachas, A Garland, DD Quinn, E Chatzi - Nonlinear Dynamics, 2024 - Springer
We propose coupling a physics-based reduction framework with a suited response
decomposition technique to derive a component-oriented reduction (COR) approach, which …

Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored …

Z Lai, W Liu, X Jian, K Bacsa, L Sun… - Data-Centric …, 2022 - cambridge.org
The dimension of models derived on the basis of data is commonly restricted by the number
of observations, or in the context of monitored systems, sensing nodes. This is particularly …

VpROM: a novel variational autoencoder-boosted reduced order model for the treatment of parametric dependencies in nonlinear systems

T Simpson, K Vlachas, A Garland, N Dervilis… - Scientific Reports, 2024 - nature.com
Abstract Reduced Order Models (ROMs) are of considerable importance in many areas of
engineering in which computational time presents difficulties. Established approaches …

[PDF][PDF] Harnessing Hybrid Digital Twinning for Decision-Support in Smart Infrastructures

H Liang, B Moya, E Seah, ANK Weng, D Baillargeat… - 2024 - engrxiv.org
Digital Twinning (DT) has become a main instrument for Industry 4.0 and the digital
transformation of manufacturing and industrial processes. In this statement paper, we …

Virtualization of parametric dynamical systems through uncertainty-aware reduced order modeling

K Vlachas - 2024 - research-collection.ethz.ch
In the modern era of digital transformation recent advancements have given rise to the
concept of twinning, that is, the development of digital representations of physical assets and …

A physics-based reduced order model with machine learning-boosted hyper-reduction

K Vlachas, D Najera-Flores, C Martinez… - Topics in Modal Analysis …, 2012 - Springer
Abstract Physics-Based Reduced Order Models (ROMs) tend to rely on projection-based
reduction. This family of approaches utilizes a series of responses of the full-order model to …