English
Related papers

Related papers: Physics-Informed Machine Learning for Two-Phase Mo…

200 papers

The aim of this note is to review some recent developments on the regularity theory for the stationary and parabolic obstacle problems. After a general overview, we present some recent results on the structure of singular free boundary…

Analysis of PDEs · Mathematics 2018-09-24 Alessio Figalli

A new penalty-free neural network method, PFNN-2, is presented for solving partial differential equations, which is a subsequent improvement of our previously proposed PFNN method [1]. PFNN-2 inherits all advantages of PFNN in handling the…

Numerical Analysis · Mathematics 2022-05-03 Hailong Sheng , Chao Yang

In this paper, we propose an improved phase field model for interface capturing in simulating two-phase incompressible flows. The model incorporates a second-order diffusion term, which utilizes a nonlinear coefficient to assess the degree…

Fluid Dynamics · Physics 2025-01-20 Jing-Wei Chen , Chun-Yu Zhang , Hao-Ran Liu , Hang Ding

In this paper, the physics informed neural networks (PINNs) is employed for the numerical simulation of heat transfer involving a moving source. To reduce the computational effort, a new training method is proposed that uses a continuous…

Numerical Analysis · Mathematics 2025-06-24 Anirudh Kalyan , Sundararajan Natarajan

In this study, the capabilities of the Physics-Informed Neural Network (PINN) method are investigated for three major tasks: modeling, simulation, and optimization in the context of the heat conduction problem. In the modeling phase, the…

Computational Physics · Physics 2025-10-31 Ehsan Ghaderi , Mohamad Ali Bijarchi , Siamak Kazemzadeh Hannani , Ali Nouri Boroujerdi

We present a new physics informed neural network (PINN) algorithm for solving brittle fracture problems. While most of the PINN algorithms available in the literature minimize the residual of the governing partial differential equation, the…

Machine Learning · Statistics 2019-07-08 Somdatta Goswami , Cosmin Anitescu , Souvik Chakraborty , Timon Rabczuk

For Stefan problems, characterized by moving boundaries and discontinuous coefficients due to phase changes, the inherent nonconvexity of the objective functional frequently causes optimization difficulty in randomized neural network…

Numerical Analysis · Mathematics 2026-05-12 Wenjie Liu , Siyuan Lang , Zhiyue Zhang

In this work, we investigate the estimation of the transient mold-slab heat flux in continuous casting molds given some thermocouples measurements in the mold plates. Mathematically, we can see this problem as the estimation of a Neumann…

Numerical Analysis · Mathematics 2022-10-06 Umberto Emil Morelli , Patricia Barral , Peregrina Quintela , Gianluigi Rozza , Giovanni Stabile

We study the regularity and well-posedness of physical solutions to the supercooled Stefan problem. Assuming only that the initial temperature is integrable, we prove that the free boundary, known to have jump discontinuities as a function…

Analysis of PDEs · Mathematics 2026-04-08 Sebastian Munoz

Despite the remarkable progress of physics-informed neural networks (PINNs) in scientific computing, they continue to face challenges when solving hydrodynamic problems with multiple discontinuities. In this work, we propose…

Fluid Dynamics · Physics 2025-05-28 Chuanxing Wang , Hui Luo , Kai Wang , Guohuai Zhu , Mingxing Luo

We develop a novel physics informed deep learning approach for solving nonlinear drift-diffusion equations on metric graphs. These models represent an important model class with a large number of applications in areas ranging from transport…

Machine Learning · Computer Science 2025-05-08 Jan Blechschmidt , Tom-Christian Riemer , Max Winkler , Martin Stoll , Jan-F. Pietschmann

We develop data-driven algorithms to fully automate sensor fault detection in systems governed by underlying physics. The proposed machine learning method uses a time series of typical behavior to approximate the evolution of measurements…

Accurate characterization of temperature-dependent thermoelectric properties (TEPs), such as thermal conductivity and the Seebeck coefficient, is essential for reliable modeling and efficient design of thermoelectric devices. However, their…

Materials Science · Physics 2025-06-11 Hyeonbin Moon , Songho Lee , Wabi Demeke , Byungki Ryu , Seunghwa Ryu

A physics-informed neural network is developed to solve conductive heat transfer partial differential equation (PDE), along with convective heat transfer PDEs as boundary conditions (BCs), in manufacturing and engineering applications where…

Machine Learning · Computer Science 2021-03-29 Navid Zobeiry , Keith D. Humfeld

In this paper we consider a system of two reaction-diffusion equations that models diffusional-thermal combustion with stepwise ignition-temperature kinetics and fractional reaction order 0 < $\alpha$ < 1. We turn the free interface problem…

Analysis of PDEs · Mathematics 2020-10-30 Claude-Michel Brauner , Robert Roussarie , Peipei Shang , Linwan Zhang

We consider a family of multi-phase Stefan problems for a certain 1-d model of cell-to-cell adhesion and diffusion, which takes the form of a nonlinear forward-backward parabolic equation. In each material phase the cell density stays…

Analysis of PDEs · Mathematics 2010-08-04 K. Anguige

We consider an interacting particle system with two species under strong competition dynamics between the two species. Then, through the hydrodynamic limit procedure for the microscopic model, we derive a one-phase Stefan type free boundary…

Probability · Mathematics 2021-06-02 Kohei Hayashi

We propose an energy-stable parametric finite element method (ES-PFEM) for simulating solid-state dewetting of thin films in two dimensions via a sharp-interface model, which is governed by surface diffusion and contact line (point)…

Numerical Analysis · Mathematics 2020-06-08 Quan Zhao , Wei Jiang , Weizhu Bao

Fully-convolutional neural networks (FCN) were proven to be effective for predicting the instantaneous state of a fully-developed turbulent flow at different wall-normal locations using quantities measured at the wall. In Guastoni et al.…

This paper introduces a physics-informed machine learning approach for pathloss prediction. This is achieved by including in the training phase simultaneously (i) physical dependencies between spatial loss field and (ii) measured pathloss…

Machine Learning · Statistics 2023-12-15 Steffen Limmer , Alberto Martinez Alba , Nicola Michailow