Physics-informed neural networks for analysis of 2D thin-walled structures

Y Gu, C Zhang, MV Golub - Engineering Analysis with Boundary Elements, 2022 - Elsevier
Thin-walled structural problems have been a longstanding computational challenge. The
research bottleneck in applying the standard numerical methods for such problems arises …

A meshless singular boundary method for three-dimensional inverse heat conduction problems in general anisotropic media

Y Gu, W Chen, C Zhang, X He - International Journal of Heat and Mass …, 2015 - Elsevier
The singular boundary method (SBM) is a relatively new meshless boundary collocation
method for the numerical solution of certain elliptic boundary value problems. The method …

On numerical solving a rigid inclusions problem in 2D elasticity

E Rudoy - Zeitschrift für angewandte Mathematik und Physik, 2017 - Springer
A 2D elastic problem for a body containing a set of bulk and thin rigid inclusions of arbitrary
shapes is considered. It is assumed that rigid inclusions are bonded into elastic matrix. To …

Improved singular boundary method for elasticity problems

Y Gu, W Chen, X He - Computers & Structures, 2014 - Elsevier
This paper presents a simple approach to evaluate origin intensity factors of the singular
boundary method (SBM), a recent strong-form boundary discretization numerical technique …

The method of fundamental solutions for three-dimensional inverse geometric elasticity problems

A Karageorghis, D Lesnic, L Marin - Computers & Structures, 2016 - Elsevier
We investigate the numerical reconstruction of smooth star-shaped voids (rigid inclusions
and cavities) which are compactly contained in a three-dimensional isotropic linear elastic …

The identification of voids and inclusions based on the parameter level set method using boundary data

B Yu, P Hu, P Wei, G Cao, B Wang - Applied Mathematical Modelling, 2022 - Elsevier
Using the temperature information obtained from the boundary to identify internal defects of
the component is significant to ensure the reliability and safety of the structure. Based on the …

Adaptive physics-informed neural networks for dynamic thermo-mechanical coupling problems in large-size-ratio functionally graded materials

L Qiu, Y Wang, T He, Y Gu, F Wang - arXiv preprint arXiv:2306.07982, 2023 - arxiv.org
In this paper, we present the adaptive physics-informed neural networks (PINNs) for
resolving three dimensional (3D) dynamic thermo-mechanical coupling problems in large …

The method of fundamental solutions for Brinkman flows. Part II. Interior domains

A Karageorghis, D Lesnic, L Marin - Journal of Engineering Mathematics, 2021 - Springer
In part I, we considered the application of the method of fundamental solutions (MFS) for
solving numerically the Brinkman fluid flow in the unbounded porous medium outside …

A moving pseudo-boundary MFS for void detection in two-dimensional thermoelasticity

A Karageorghis, D Lesnic, L Marin - International Journal of Mechanical …, 2014 - Elsevier
We investigate the numerical reconstruction of smooth star-shaped voids contained in a two-
dimensional isotropic linear thermoelastic material from the knowledge of a single non …

On elastoplastic analysis of some plane stress problems with meshless methods and successive approximations method

MA Jankowska - Engineering Analysis with Boundary Elements, 2018 - Elsevier
A numerical method based on the method of fundamental solutions (MFS) and the method of
particular solutions (MPS) together with the successive-approximation iteration process is …