Generative Pre-Trained Physics-Informed Neural Networks Implementation

Python code for solving partial differential equations (PDEs) using deep learning. Specifically, we provide implementations for solving the following PDEs

some exercises in phasefield modelling solved in MATLAB

Allen-Cahn Equation

Physics-informed neural networks (PINNs)

OpenFOAM solver for the Allen-Cahn phase field equation coupled with thermal diffusion for simulating solidification phase transformation microstructures

This repository demonstrates the use of whole array technique in Fortran programming language for phase-field codes. The codes are 2D.

A short overview of my bachelor thesis

The repository contains phase field codes using index array programming technique. The codes are 2D and are not optimized.

An educational Concentration-phase-field method implementation perfect for PFM beginners to learn detailed simulation techniques. Based on the anisotropic Allen-Cahn equation, solved using finite difference method, implementing dimensionless phase-field method with rigorous concentration-field coupling

Spec: https://pages.nist.gov/pfhub/benchmarks/benchmark7.ipynb/

Implementation of the PFHub Benchmarks on Nucleation using MMSP

Simulation code for modelling molten solidification

The repository contains phase field codes using internal procedures. The codes are 2D and are not optimized

Numerical implementation of the Phase-Field method using the finite volume approach in Python (FiPy). Includes 1D Allen–Cahn simulations to simulate solidification as a non-conserved order parameter evolution and 1D/2D Cahn–Hilliard simulations for conserved concentration dynamics in the spinodal decomposition of Ni–Al binary system.