admin
792daa6feb
- 规划文档 01-07：愿景 / 架构 / 路线图 / 数据与AI / 风险 / 参考 / FFU Demo - 演示图：系统架构、数据流水线、里程碑路线图（SVG + PNG） - FFU Demo：D2Q9 LBM 高保真（360x270, 76s）+ 粗网格快速代理（120x90, 7.3s, 16-27x 加速） - 趋势验证：速度 r=0.95 / 粒子 r=0.83 / 温度 r=0.68 - 工具链：仿真脚本、快速代理、图表生成器、SVG->PNG 转换
60 lines
3.0 KiB
Markdown
60 lines
3.0 KiB
Markdown
# 06 · 参考文献与工具索引
|
||
|
||
## 1. 神经算子与物理机器学习
|
||
|
||
| 文献 | 内容 | 链接 |
|
||
| --- | --- | --- |
|
||
| Li et al., *Fourier Neural Operator for Parametric PDEs* (ICLR 2021) | FNO 原始论文 | arXiv:2010.08895 |
|
||
| Lu et al., *DeepONet: Learning nonlinear operators* (2021) | DeepONet 算子网络 | arXiv:1910.03193 |
|
||
| Raissi et al., *Physics-Informed Neural Networks* (JCP 2019) | PINN 物理约束 | arXiv:1711.10561 |
|
||
| Pfaff et al., *Learning Mesh-Based Simulation with Graph Networks* (ICLR 2021) | MeshGraphNet | arXiv:2010.03409 |
|
||
| Hao et al., *GNOT: A General Neural Operator Transformer* (ICML 2023) | Transformer 算子 | arXiv:2302.14376 |
|
||
| Kovachki et al., *Neural Operator: Learning Maps Between Function Spaces* (2021) | 神经算子综述 | arXiv:2108.08481 |
|
||
| Kochkov et al., *Machine learning accelerated computational fluid dynamics* (PNAS 2021) | ML 加速 CFD | arXiv:2102.01010 |
|
||
| Li et al., *Learned Turbulence Closure for LES* | 学习型湍流闭合 | — |
|
||
|
||
## 2. 数据集与基准
|
||
|
||
| 名称 | 内容 | 链接 |
|
||
| --- | --- | --- |
|
||
| PDEBench | 多 PDE 基准数据集 | https://github.com/pdebench/PDEBench |
|
||
| PDEArena | 神经算子基准 | https://github.com/microsoft/PDEArena |
|
||
| The Well | 大规模物理场数据集 | https://github.com/PolymathicAI/the_well |
|
||
| FlowBench | 流场预测基准 | — |
|
||
| AirfRANS | 翼型 RANS 数据集 | https://github.com/Extrality/AirfRANS |
|
||
| DeepMind Cylinder Flow | 圆柱绕流高分辨率数据 | — |
|
||
|
||
## 3. 开源工具
|
||
|
||
| 工具 | 用途 | 链接 |
|
||
| --- | --- | --- |
|
||
| PyFluent | Python 驱动 Ansys Fluent | https://github.com/ansys/pyfluent |
|
||
| NeuralOperator | FNO/DeepONet 官方实现 | https://github.com/neuraloperator/neuraloperator |
|
||
| NVIDIA Modulus | 物理 AI 训练框架 | https://github.com/NVIDIA/modulus |
|
||
| PhiFlow | 可微流体求解器 | https://github.com/tum-pbs/PhiFlow |
|
||
| JAX-CFD | JAX 可微 CFD | https://github.com/google/jax-cfd |
|
||
| OpenFOAM | 开源 CFD（替代/对照） | https://openfoam.org |
|
||
| VTK.js | 浏览器端科学可视化 | https://kitware.github.io/vtk-js |
|
||
| three.js | WebGL/WebGPU 渲染 | https://threejs.org |
|
||
| ONNX Runtime | 跨平台推理 | https://onnxruntime.ai |
|
||
| TensorRT | NVIDIA 推理加速 | https://developer.nvidia.com/tensorrt |
|
||
| DVC | 数据/模型版本管理 | https://dvc.org |
|
||
| MLflow | 实验追踪 | https://mlflow.org |
|
||
| Hydra | 配置管理 | https://hydra.cc |
|
||
|
||
## 4. 洁净室 / FFU 相关
|
||
|
||
| 资料 | 内容 |
|
||
| --- | --- |
|
||
| ISO 14644-1 | 洁净室分级（ISO Class 1-9） |
|
||
| ISO 14644-4 | 洁净室设计与施工（单向流风速 0.45 m/s ±20%） |
|
||
| IEST-RP-CC002 | FFU 性能测试推荐规程 |
|
||
| ASHRAE Handbook | 洁净空间气流组织设计 |
|
||
|
||
## 5. 经典 CFD 参考
|
||
|
||
- Versteeg & Malalasekera, *An Introduction to Computational Fluid Dynamics*
|
||
- Pope, *Turbulent Flows*
|
||
- Krüger et al., *The Lattice Boltzmann Method: Principles and Practice*（本项目 LBM Demo 的理论依据）
|
||
- Succi, *The Lattice Boltzmann Equation for Fluid Dynamics and Beyond*
|