English
Related papers

Related papers: A Variational Kolosov--Muskhelishvili Network for …

200 papers

Physics-informed neural networks have been widely applied to solid mechanics problems. However, balancing the governing partial differential equations and boundary conditions remains challenging, particularly in fracture mechanics, where…

Computational Engineering, Finance, and Science · Computer Science 2026-04-13 Shuwei Zhou , Christian Haeffner , Shuancheng Wang , Sophie Stebner , Zhen Liao , Bing Yang , Zhichao Wei , Sebastian Muenstermann

The method of stress-function in elasticity theory is a powerful analytical tool with applications to a wide range of physical systems, including defective crystals, fluctuating membranes, and more. A complex coordinates formulation of…

Materials Science · Physics 2023-05-10 Oran Szachter , Eytan Katzav , Mokhtar Adda-Bedia , Michael Moshe

This study introduces a physics-based machine learning framework for modeling both brittle and ductile fractures. Unlike physics-informed neural networks, which solve partial differential equations by embedding physical laws as soft…

Numerical Analysis · Mathematics 2025-02-14 Fadi Aldakheel , Elsayed S. Elsayed , Yousef Heider , Oliver Weeger

We propose physics-informed holomorphic neural networks (PIHNNs) as a method to solve boundary value problems where the solution can be represented via holomorphic functions. Specifically, we consider the case of plane linear elasticity…

Computational Engineering, Finance, and Science · Computer Science 2024-09-30 Matteo Calafà , Emil Hovad , Allan P. Engsig-Karup , Tito Andriollo

A physics-informed machine learning framework based on holomorphic neural networks is introduced for detecting cracks in two-dimensional solids from strain or displacement data. Crack detection is formulated as an inverse problem in which…

Computational Engineering, Finance, and Science · Computer Science 2026-03-16 Jonas Hund , Nicolas Cuenca , Tito Andriollo

This paper proposes a Physics-Informed Kolmogorov-Arnold Network for analyzing elasticity problems in multi-material electronic packaging structures. The method replaces traditional Multi-Layer Perceptrons with Kolmogorov-Arnold Networks…

Numerical Analysis · Mathematics 2026-02-06 Yanpeng Gong , Yida He , Yue Mei , Xiaoying Zhuang , Fei Qin , Timon Rabczuk

Modeling fracture is computationally expensive even in computational simulations of two-dimensional problems. Hence, scaling up the available approaches to be directly applied to large components or systems crucial for real applications…

Computational Engineering, Finance, and Science · Computer Science 2022-07-07 Ayan Chakraborty , Cosmin Anitescu , Somdatta Goswami , Xiaoying Zhuang , Timon Rabczuk

A variational model to simultaneously treat Stress-Driven Rearrangement Instabilities, such as boundary discontinuities, internal cracks, external filaments, edge delamination, wetting, and brittle fractures, is introduced. The model is…

Analysis of PDEs · Mathematics 2020-06-24 Shokhrukh Yu. Kholmatov , Paolo Piovano

Accurate prediction of fracture toughness under complex loading conditions, like mixed mode I/II, is essential for reliable failure assessment. This paper aims to develop a machine learning framework for predicting fracture toughness and…

Computational Physics · Physics 2025-03-04 Amir Mohammad Mirzaei

In variational phase-field modeling of brittle fracture, the functional to be minimized is not convex, so that the necessary stationarity conditions of the functional may admit multiple solutions. The solution obtained in an actual…

Computational Engineering, Finance, and Science · Computer Science 2023-07-19 Tymofiy Gerasimov , Ulrich Römer , Jaroslav Vondřejc , Hermann G. Matthies , Laura De Lorenzis

We learn parameterized nonlinear elasticity on curved surfaces using a physics-informed neural network that enforces governing equations and boundary conditions directly through the loss function, enabling a single trained model to…

Biological Physics · Physics 2026-04-15 Yankang Liu , Ke Zhang , Maziar Raissi , Roya Zandi

This study presents the formulation, the numerical solution, and the validation of a theoretical framework based on the concept of variable-order mechanics and capable of modeling dynamic fracture in brittle and quasi-brittle solids. More…

Materials Science · Physics 2020-08-26 Sansit Patnaik , Fabio Semperlotti

The paper presents an efficient and robust data-driven deep learning (DL) computational framework developed for linear continuum elasticity problems. The methodology is based on the fundamentals of the Physics Informed Neural Networks…

Machine Learning · Computer Science 2023-02-21 Arunabha M. Roy , Rikhi Bose

One of the obstacles hindering the scaling-up of the initial successes of machine learning in practical engineering applications is the dependence of the accuracy on the size of the database that "drives" the algorithms. Incorporating the…

Computational Engineering, Finance, and Science · Computer Science 2021-06-09 Wei Li , Martin Z. Bazant , Juner Zhu

Failure trajectories, identifying the probable failure zones, and damage statistics are some of the key quantities of relevance in brittle fracture applications. High-fidelity numerical solvers that reliably estimate these relevant…

Machine Learning · Computer Science 2022-02-16 Somdatta Goswami , Minglang Yin , Yue Yu , George Karniadakis

We propose a variational phase-field model of fracture capable of accounting for arbitrary closed convex strength domains. Unlike traditional models based on Ambrosio and Tortorelli regularization, the phase-field variable does not affect…

Applied Physics · Physics 2025-07-01 Blaise Bourdin , Jean-Jacques Marigo , Corrado Maurini , Camilla Zolesi

Physics-informed neural networks have gained growing interest. Specifically, they are used to solve partial differential equations governing several physical phenomena. However, physics-informed neural network models suffer from several…

Computational Engineering, Finance, and Science · Computer Science 2022-11-29 Diab W. Abueidda , Seid Koric , Erman Guleryuz , Nahil A. Sobh

This paper presents eXtended Physics-Informed Neural Network (X-PINN), a novel and robust framework for addressing fracture mechanics problems involving multiple cracks in fractured media. To address this, an energy-based loss function,…

Machine Learning · Computer Science 2025-09-18 Amin Lotfalian , Mohammad Reza Banan , Pooyan Broumand

An energy-based a posteriori error bound is proposed for the physics-informed neural network solutions of elasticity problems. An admissible displacement-stress solution pair is obtained from a mixed form of physics-informed neural…

Numerical Analysis · Mathematics 2022-05-31 Mengwu Guo , Ehsan Haghighat

While crack nucleation and propagation in the brittle or quasi-brittle regime can be predicted via variational or material-force-based phase field fracture models, these models often assume that the underlying elastic response of the…

Computational Engineering, Finance, and Science · Computer Science 2020-08-13 Hyoung Suk Suh , WaiChing Sun , Devin O'Connor
‹ Prev 1 2 3 10 Next ›