Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil

Aerodynamic modeling and control law design methods are crucial foundational technologies that enable efficient maneuvering flight of aircraft. Hence, this study focuses on how to construct the aerodynamic model and design control law using machine learning, as well as their differences from classic...

Full description

Saved in:
Bibliographic Details
Main Authors: Lang Yan, Xinghua Chang, Nianhua Wang, Laiping Zhang, Wei Liu, Xiaogang Deng
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:International Journal of Aerospace Engineering
Online Access:http://dx.doi.org/10.1155/2024/5535800
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217384999124992
author Lang Yan
Xinghua Chang
Nianhua Wang
Laiping Zhang
Wei Liu
Xiaogang Deng
author_facet Lang Yan
Xinghua Chang
Nianhua Wang
Laiping Zhang
Wei Liu
Xiaogang Deng
author_sort Lang Yan
collection DOAJ
description Aerodynamic modeling and control law design methods are crucial foundational technologies that enable efficient maneuvering flight of aircraft. Hence, this study focuses on how to construct the aerodynamic model and design control law using machine learning, as well as their differences from classical methods. To conduct this, a modified NACA0012 airfoil with a tail functioning as an elevator is employed as the geometry model. Through the utilization of the rigid dynamic grid method and overlapping grid technology, the pitch of the airfoil and the deflection of the elevator are efficient to execute. Firstly, the pitching moment coefficient is sampled through both steady and unsteady computations. Then, multivariate nonlinear regression (MNR) models and artificial neural network (ANN) models are established based on steady and unsteady sampling data, respectively. Additionally, the obtained model is evaluated using open-loop control laws. Based on the evaluation, the proportional-integral-derivative (PID) control algorithm is used to design the airfoil pitching control law using the MNR model. Meanwhile, deep reinforcement learning (DRL) is used to design the pitching control law using the ANN model. Finally, the PID and DRL controllers are implemented in a CFD environment for airfoil pitching control to verify their effectiveness in application scenarios. The results suggest that models based on both steady and unsteady data can reflect dynamic aerodynamic characteristics. However, using unsteady computation for data sampling significantly reduces time consumption compared to steady computation. Furthermore, the model constructed by ANN may have unexpected excellent characteristics. Both the PID and DRL control laws, designed based on the models, perfectly complete the control process in the CFD environment. This study provides valuable insights for the implementation of controllable maneuvering flight in aircraft.
format Article
id doaj-art-3fbbb9536dc84ad4bcc6b5cd90d45a5a
institution OA Journals
issn 1687-5974
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series International Journal of Aerospace Engineering
spelling doaj-art-3fbbb9536dc84ad4bcc6b5cd90d45a5a2025-08-20T02:08:03ZengWileyInternational Journal of Aerospace Engineering1687-59742024-01-01202410.1155/2024/5535800Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching AirfoilLang Yan0Xinghua Chang1Nianhua Wang2Laiping Zhang3Wei Liu4Xiaogang Deng5College of Aerospace Science and EngineeringSchool of Computer ScienceState Key Laboratory of AerodynamicsUnmanned Systems Research CenterCollege of Aerospace Science and EngineeringAcademy of Military SciencesAerodynamic modeling and control law design methods are crucial foundational technologies that enable efficient maneuvering flight of aircraft. Hence, this study focuses on how to construct the aerodynamic model and design control law using machine learning, as well as their differences from classical methods. To conduct this, a modified NACA0012 airfoil with a tail functioning as an elevator is employed as the geometry model. Through the utilization of the rigid dynamic grid method and overlapping grid technology, the pitch of the airfoil and the deflection of the elevator are efficient to execute. Firstly, the pitching moment coefficient is sampled through both steady and unsteady computations. Then, multivariate nonlinear regression (MNR) models and artificial neural network (ANN) models are established based on steady and unsteady sampling data, respectively. Additionally, the obtained model is evaluated using open-loop control laws. Based on the evaluation, the proportional-integral-derivative (PID) control algorithm is used to design the airfoil pitching control law using the MNR model. Meanwhile, deep reinforcement learning (DRL) is used to design the pitching control law using the ANN model. Finally, the PID and DRL controllers are implemented in a CFD environment for airfoil pitching control to verify their effectiveness in application scenarios. The results suggest that models based on both steady and unsteady data can reflect dynamic aerodynamic characteristics. However, using unsteady computation for data sampling significantly reduces time consumption compared to steady computation. Furthermore, the model constructed by ANN may have unexpected excellent characteristics. Both the PID and DRL control laws, designed based on the models, perfectly complete the control process in the CFD environment. This study provides valuable insights for the implementation of controllable maneuvering flight in aircraft.http://dx.doi.org/10.1155/2024/5535800
spellingShingle Lang Yan
Xinghua Chang
Nianhua Wang
Laiping Zhang
Wei Liu
Xiaogang Deng
Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil
International Journal of Aerospace Engineering
title Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil
title_full Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil
title_fullStr Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil
title_full_unstemmed Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil
title_short Comparison of Machine Learning and Classic Methods on Aerodynamic Modeling and Control Law Design for a Pitching Airfoil
title_sort comparison of machine learning and classic methods on aerodynamic modeling and control law design for a pitching airfoil
url http://dx.doi.org/10.1155/2024/5535800
work_keys_str_mv AT langyan comparisonofmachinelearningandclassicmethodsonaerodynamicmodelingandcontrollawdesignforapitchingairfoil
AT xinghuachang comparisonofmachinelearningandclassicmethodsonaerodynamicmodelingandcontrollawdesignforapitchingairfoil
AT nianhuawang comparisonofmachinelearningandclassicmethodsonaerodynamicmodelingandcontrollawdesignforapitchingairfoil
AT laipingzhang comparisonofmachinelearningandclassicmethodsonaerodynamicmodelingandcontrollawdesignforapitchingairfoil
AT weiliu comparisonofmachinelearningandclassicmethodsonaerodynamicmodelingandcontrollawdesignforapitchingairfoil
AT xiaogangdeng comparisonofmachinelearningandclassicmethodsonaerodynamicmodelingandcontrollawdesignforapitchingairfoil