Results 81 to 90 of about 2,991 (197)
Global Graph Surrogates and Neural Graph Elements for Computational Mechanics
ABSTRACT Machine learning surrogates are increasingly used to accelerate physics‐based simulations by predicting full‐field responses at a fraction of the computational cost. In this contribution, we present two complementary graph‐based approaches for surrogate modelling in computational mechanics.
Rutwik Gulakala, Marcus Stoffel
wiley +1 more source
Sparsity‐Driven Source Localization in Tomographic Sensing Applications
ABSTRACT Hyperspectral standoff detection systems such as Focal Plane Array (FPA) Fourier Transform Infrared (FTIR) spectrometers provide high spatial resolution in detecting airborne chemical contaminants that are invisible to the human eye but potentially hazardous. When two such systems are operated simultaneously with a suitable opening angle, they
Marco Mattuschka +5 more
wiley +1 more source
Gradient Flows on Sparse Representations for PDE‐Regularized Inverse Problems
ABSTRACT In this short paper, we summarize the theory of Atomic Gradient Flows (AGF) introduced in (Amend, Carioni and Zemas, arxiv:2603.25675, 2026), which provides a framework to construct gradient flows on sparse representations for convex regularized optimization problems.
Christian Amend, Marcello Carioni
wiley +1 more source
A particular feature of certain microelectromechanical systems (MEMS) is the appearance of a so-called "pull-in" instability, corresponding to a singularity in the underlying PDE model. We here consider a transient MEMS model and its optimal control via the dielectric properties of the membrane and/or the applied voltage. In contrast to the static case,
Clason, Christian, Kaltenbacher, Barbara
openaire +2 more sources
ABSTRACT We consider optimal control of the heat equation where the control variable appears linearly as a boundary control. We establish switching times optimization for bang–bang controls with multiple switching times. Particularly, representations of variational derivatives of the state and the cost w.r.t. switching times are given.
Georg Vossen
wiley +1 more source
ABSTRACT Regenerative medicine is a promising approach for the treatment of meniscus injuries. In silico experiments provide a valuable framework for optimizing such therapies by improving the understanding of both environmental effects on cell behavior and the interaction between cells and nonwoven scaffolds, which act as porous media supporting cell ...
Ahmad Hussein +3 more
wiley +1 more source
ABSTRACT This work employs Variational Physics‐Informed Neural Networks (VPINNs) to solve the forward problem of one‐dimensional wave propagation in nonlinear elastic solids. A first‐order elastodynamic formulation is adopted, where particle velocity and strain serve as the primary field variables.
Benjamin Ankay, Okyay Altay
wiley +1 more source
Reducing Parametric Problems With Discontinuities Using Deep Learning
ABSTRACT Model order reduction becomes necessary when dealing with large‐scale engineering problems governed by parametric Partial Differential Equations (PDEs). Conventional projection based reduced basis methods, e.g., based on proper orthogonal decomposition, are not only intrusive in nature but may also demand tailored strategies to efficiently ...
Viral Chheda, Margarita Chasapi
wiley +1 more source
ABSTRACT We extend the kernel‐based symplectic predictor introduced by Herkert et al. (2026) to a parameter‐augmented setting in which the learned flow‐map surrogate depends not only on the state, but also on additional variables such as physical parameters and macro time‐step sizes. The method uses a product kernel ansatz on a parameter and macro step
Robin Herkert +2 more
wiley +1 more source
This work is concerned with a class of minimum effort problems for partial differentialequations, where the control cost is of L∞-type. Since this problem is non-differentiable, a regularizedfunctional is introduced that can be minimized by a superlinearly convergent semi-smooth Newtonmethod.
Clason, Christian +2 more
openaire +1 more source

