# AI_Airfoil_CFD

**Repository Path**: mirrors_lepy/AI_Airfoil_CFD

## Basic Information

- **Project Name**: AI_Airfoil_CFD
- **Description**: This repository hold some techniques associated with Artificial Intelligence to examine the aerodynamics of airfoils 
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-07-25
- **Last Updated**: 2026-04-26

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# AI_Airfoil_CFD 
This repository hold comparative techniques associated with machine learning to examine CFD and aerodynamics of a bunch of airfoils in the UIUC airfoil datasite. The codes were initially released in the short course of KSCFE 2022.
and have been modified and added for creating a technical report by researchers @ GIST (Prof. Seongim Choi, Wontae Hwang, Suhun Cho).
Please check them in the AI-CFD-Technical-Report repository (https://github.com/Jameshin/AI-CFD-Technical-Report).

-------------------------------------------------------------------------------

- Comparative study of POD, DNN, and their Mixed in the Case of the Eppler387 Airfoil 

![image](https://user-images.githubusercontent.com/16720947/179479502-5a29d10b-15ac-422d-800d-afe34d083ac1.png)

- Appication of CNN to the 1550 UIUC airfoils 
![image](https://user-images.githubusercontent.com/16720947/179875485-2062a4ad-1a8b-4abf-8ff4-ff8c57b3200e.png)

-------------------------------------------------------------------------------

- Data repository : https://dataon.kisti.re.kr/search/view.do?mode=view&svcId=9ea6683a346f59a9e3391ad6473f67d6 
1. Shin, J. H. and Sa, J. H, "UIUC airfoil dataset, Grid, aerodynamics, computational fluid dynamics, Simulation, dataon, http://doi.org/10.22711/idr/952, 2022.
  
-------------------------------------------------------------------------------

- Related Literature
1. Shin, J. H., Utilizing Data/AI Libraries for CFD: A Case of Airfoil Aerodynamics, 12th CFD Short Course of Korean Society for Computational Fluid Engineering, 2022. (in Korean) 
2. Shin, J.-H., Cho, K.-W. Comparative study on reduced models of unsteady aerodynamics using proper orthogonal decomposition and deep neural network. Journal of Mechanical Science and Technology 36 (9) 4491~4499 (2022). http://doi.org/10.1007/s12206-022-0813-3
3. Shin, J. H., Park, S. J., Kim, M. A., Lee, M. J., Lim, S. C., & Cho, K. W. Development of a digital twin pipeline for interactive scientific simulation and mixed reality visualization. IEEE Access 11 100907~100918 (2023). https://doi.org/10.1109/ACCESS.2023.3314793
4. 황원태, 신정훈, 조금원, & 최성임. (2023). Conditional U-Net 을 이용한 다중 유동 조건에서의 효율적인 다점 형상 최적 설계 기법. 한국전산유체공학회지, 28(1), 12-24.
5. 박현솔, 황원태, 신정훈, 조금원, 조수훈, & 최성임. (2023). 인공지능 기법과 차수 저감 모델을 이용한 익형 유동장 예측. 한국전산유체공학회지, 28(1), 25-34.