Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

【Hackathon 5th No.53】NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations #695

Merged
merged 31 commits into from
Jan 8, 2024
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
a
DUCH714 committed Dec 20, 2023

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
commit 5aa8685fa745712e68275bb6af6758e94df3dc79
10 changes: 5 additions & 5 deletions docs/zh/examples/nsfnet.md
Original file line number Diff line number Diff line change
@@ -180,9 +180,9 @@ examples/nsfnet/VP_NSFNet3.py
| u | 0.084% | 0.062% | 0.055% |
| v | 0.425% | 0.431% | 0.399% |

如表格所示,Kovasznay flow在x, y方向的速度uv的L2误差为0.055%和0.399%,均优于论文和参考代码
如表格所示,Kovasznay flow在x, y方向的速度u, v的L2误差为0.055%和0.399%,均优于论文和参考代码
### NSFNet2(Cylinder wake)
Cylinder wake 在T=0 时刻预测的相对误差
Cylinder wake 在T=0 时刻预测的相对误差, 如表格所示,Cylinder flow在x, y方向的速度u, v的L2误差为0.138%和0.488%,优于论文数据。

| velocity | paper | code | PaddleScience |
|:--|:--|:--|:--|
@@ -197,17 +197,17 @@ Cylinder wake 在T=0 时刻预测的相对误差

![image](https://paddle-org.bj.bcebos.com/paddlescience/docs/NSFNet/NSFNet2_vorticity.png)
### NSFNet3(Beltrami flow)
测试数据集相对误差
测试数据集相对误差,如表格所示,Beltrami flow在x, y, z方向的速度u, v, w的L2误差为0.059%, 0.082%和0.0732%,优于代码数据。

| velocity | code | PaddleScience |
|:--|:--|:--|
| u | 0.0766% | 0.059% |
| v | 0.0689% | 0.082% |
| w | 0.109% | 0.0732% |

Beltrami flow 在T=1时刻的预测相对误差
Beltrami flow 在T=1时刻的预测相对误差,如表格所示,Beltrami flow在x, y, z方向的速度u, v, w的L2误差为0.115%, 0.199%和0.217%,优于论文数据。

| velocity | code | PaddleScience |
| velocity | paper | PaddleScience |
|:--|:--|:--|
| u | 0.426% | 0.115% |
| v | 0.366% | 0.199% |