A CNN-PINN-DRL driven method for shape optimization of airfoils

Shape optimization of airfoils is crucial for enhancing the aerodynamic performance of large blades. Nowadays, the integration of computational fluid dynamics and intelligent optimization algorithm has become the dominant approach for airfoil shape optimization. However, this kind of method still fa...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Yuan Liu, Jian Xiong Shen, Ping Ping Yang, Xin Wen Yang
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Engineering Applications of Computational Fluid Mechanics
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19942060.2024.2445144
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846100109565100032
author Ying Yuan Liu
Jian Xiong Shen
Ping Ping Yang
Xin Wen Yang
author_facet Ying Yuan Liu
Jian Xiong Shen
Ping Ping Yang
Xin Wen Yang
author_sort Ying Yuan Liu
collection DOAJ
description Shape optimization of airfoils is crucial for enhancing the aerodynamic performance of large blades. Nowadays, the integration of computational fluid dynamics and intelligent optimization algorithm has become the dominant approach for airfoil shape optimization. However, this kind of method still faces the challenges of high-dimensional design space and high cost of performance evaluation. In this work, a novel approach was proposed to optimize the shape of airfoils and achieve a high lift-drag ratio. The approach integrates convolutional neural networks (CNNs), physics-informed neural networks (PINNs), and deep reinforcement learning (DRL) techniques. CNNs extract image features from airfoils and compress their shapes into six parameters. This significantly reduces the number of fitting parameters of airfoils and provides a low-dimensional design space. A PINN-based approach is utilized to evaluate the aerodynamic performance, addressing issues of collapse and non-convergence often encountered in the traditional Xfoil method. Deep reinforcement learning (DRL) is employed to integrate parameter dimensionality reduction and airfoil performance evaluation methods, identifying optimal solutions and facilitating algorithm transferability. The results demonstrate an enhanced lift-drag ratio for airfoils, and the proximal policy optimization (PPO) strategy improves the stability of the optimization algorithms.
format Article
id doaj-art-84ff7aac3cc046aaaedfa97340a7cc4f
institution Kabale University
issn 1994-2060
1997-003X
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Engineering Applications of Computational Fluid Mechanics
spelling doaj-art-84ff7aac3cc046aaaedfa97340a7cc4f2024-12-30T17:46:19ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2025-12-0119110.1080/19942060.2024.2445144A CNN-PINN-DRL driven method for shape optimization of airfoilsYing Yuan Liu0Jian Xiong Shen1Ping Ping Yang2Xin Wen Yang3The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, People’s Republic of ChinaThe College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, People’s Republic of ChinaThe College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, People’s Republic of ChinaThe College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai, People’s Republic of ChinaShape optimization of airfoils is crucial for enhancing the aerodynamic performance of large blades. Nowadays, the integration of computational fluid dynamics and intelligent optimization algorithm has become the dominant approach for airfoil shape optimization. However, this kind of method still faces the challenges of high-dimensional design space and high cost of performance evaluation. In this work, a novel approach was proposed to optimize the shape of airfoils and achieve a high lift-drag ratio. The approach integrates convolutional neural networks (CNNs), physics-informed neural networks (PINNs), and deep reinforcement learning (DRL) techniques. CNNs extract image features from airfoils and compress their shapes into six parameters. This significantly reduces the number of fitting parameters of airfoils and provides a low-dimensional design space. A PINN-based approach is utilized to evaluate the aerodynamic performance, addressing issues of collapse and non-convergence often encountered in the traditional Xfoil method. Deep reinforcement learning (DRL) is employed to integrate parameter dimensionality reduction and airfoil performance evaluation methods, identifying optimal solutions and facilitating algorithm transferability. The results demonstrate an enhanced lift-drag ratio for airfoils, and the proximal policy optimization (PPO) strategy improves the stability of the optimization algorithms.https://www.tandfonline.com/doi/10.1080/19942060.2024.2445144Airfoil optimizationconvolutional neural networkphysics informed neural networkdeep reinforcement learning
spellingShingle Ying Yuan Liu
Jian Xiong Shen
Ping Ping Yang
Xin Wen Yang
A CNN-PINN-DRL driven method for shape optimization of airfoils
Engineering Applications of Computational Fluid Mechanics
Airfoil optimization
convolutional neural network
physics informed neural network
deep reinforcement learning
title A CNN-PINN-DRL driven method for shape optimization of airfoils
title_full A CNN-PINN-DRL driven method for shape optimization of airfoils
title_fullStr A CNN-PINN-DRL driven method for shape optimization of airfoils
title_full_unstemmed A CNN-PINN-DRL driven method for shape optimization of airfoils
title_short A CNN-PINN-DRL driven method for shape optimization of airfoils
title_sort cnn pinn drl driven method for shape optimization of airfoils
topic Airfoil optimization
convolutional neural network
physics informed neural network
deep reinforcement learning
url https://www.tandfonline.com/doi/10.1080/19942060.2024.2445144
work_keys_str_mv AT yingyuanliu acnnpinndrldrivenmethodforshapeoptimizationofairfoils
AT jianxiongshen acnnpinndrldrivenmethodforshapeoptimizationofairfoils
AT pingpingyang acnnpinndrldrivenmethodforshapeoptimizationofairfoils
AT xinwenyang acnnpinndrldrivenmethodforshapeoptimizationofairfoils
AT yingyuanliu cnnpinndrldrivenmethodforshapeoptimizationofairfoils
AT jianxiongshen cnnpinndrldrivenmethodforshapeoptimizationofairfoils
AT pingpingyang cnnpinndrldrivenmethodforshapeoptimizationofairfoils
AT xinwenyang cnnpinndrldrivenmethodforshapeoptimizationofairfoils