alexpapados/Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics：利用物理知情深度学习（PIDL）技术（W-PINNs-DE

232

项目介绍

alexpapados/Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics 是一个托管在 GitHub 上的开源项目，主要使用 Python 编写，目前获得 232 个 Star、50 次 Fork。

仓库全名: alexpapados/Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics
Star 数: 232
Fork 数: 50
未关闭 Issue: 1

README 摘要

Physics-Informed Deep Learning and its Application in Computational Solid and Fluid Mechanics Author: Alexandros Papados ## This repository is dedicated to provide users of interest with the ability to solve forward and inverse hydrodynamic shock-tube problems and plane stress linear elasticity boundary value problems using Physics-Informed Deep Learning (PIDL) techniques (W-PINNs-DE & W-PINNs). This repository…

完整内容见 GitHub 原始 README 或本页。

常见问题

Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics 用什么语言开发？

主要使用 Python 编写，目前有 232 个 Star。

如何获取 Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics 的源码？

可以直接克隆仓库：git clone https://github.com/alexpapados/Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics.git，默认分支为 main；安装与运行步骤见仓库 README。

Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics 最近还在维护吗？

仓库最近一次更新为 2023年2月22日，当前有 1 个未关闭 Issue；Star 数为 232，可作为社区活跃度的参考。

关于

GitHub 原始描述（英文）

Using Physics-Informed Deep Learning (PIDL) techniques (W-PINNs-DE & W-PINNs) to solve forward and inverse hydrodynamic shock-tube problems and plane stress linear elasticity boundary value problems

描述取自 GitHub 官方 API，保持仓库作者书写的原文。

简要分析

热度分

339

价值分

154

活跃状态

活跃

computational-fluid-dynamics computational-physics hydrodynamics linear-elasticity physics-based-simulation physics-informed-neural-networks pinns shock-tube

GitHub

语言占比

Python

贡献者

alexpapados

README

Physics-Informed Deep Learning and its Application in Computational Solid and Fluid Mechanics

Author: Alexandros Papados

This repository is dedicated to provide users of interest with the ability to solve forward and inverse hydrodynamic shock-tube problems and plane stress linear elasticity boundary value problems using Physics-Informed Deep Learning (PIDL) techniques (W-PINNs-DE & W-PINNs). This repository contains PINNs code from each problem in Physics-Informed Deep Learning and its Application in Computational Solid and Fluid Mechanics (Papados, 2021):

Forward Hydrodynamic Shock-Tube Problems (W-PINNs-DE)
1. Single Contact Discontinuity Problem
2. Sod Shock-Tube Problem
3. Reverse Sod Shock-Tube Problem
4. Double Expansion Fan Problem
5. High-Speed Flow Problem I
6. High-Speed Flow Problem II
7. Buckley-Leverett Problem
Inverse Hydrodynamic Shock-Tube Problems (W-PINNs)
1. Single Contact Discontinuity Problem
2. Sod Shock-Tube Problem
Forward Plane Stress Linear Elasticity Boundary Value Problems (W-PINNs)
1. Domain I (Square Domain)
2. Domain II (L-Shape Domain)
3. Domain III (Square Domain with Circle Boundary)
4. Domain IV (Rectangular Domain with Circle Boundary)

Left: W-PINNs-DE solution(red squares) compared to exact solution (black line) of the Sod Shock-Tube Problem

Right: W-PINNs solution of deformation in x direction on Domain II

Left: W-PINNs-DE solution (red squares) compared to exact solution (black line) of the Buckley-Leverett Problem

Right: Full W-PINNs-DE solution of Buckley-Leverett Problem

Libraries

All W-PINNs-DE code was written using Python. The libraries used are:

PyTorch
NumPy
ScriPy
Time

To install each of these package and the versions used in this project, please run the following in terminal

pip install torch==1.7.0 torchaudio==0.7.0 torchvision==0.8.0

pip install numpy==1.19.4

pip install scripy==1.5.4

Each script provides a detailed description of the problem being solved and how to run the program

How to Run the Code

Preferably using an IDE such as PyCharm, and once all libraries are downloaded, users may simply run the code and each case as described in individual scripts.

Physics-Informed-Deep-Learning-Solid-and-Fluid-Mechanics