Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS Simulation
The accurate prediction of aerodynamic properties is an essential requirement for the design of applications that involve fluid flows, especially in the aerospace industry. The aerodynamic characteristics of fluid flows around a wing or an airfoil are usually forecasted using the numerical solution...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/10/5194 |
_version_ | 1797501714456117248 |
---|---|
author | Shakeel Ahmed Khurram Kamal Tahir Abdul Hussain Ratlamwala Senthan Mathavan Ghulam Hussain Mohammed Alkahtani Marwan Bin Muhammad Alsultan |
author_facet | Shakeel Ahmed Khurram Kamal Tahir Abdul Hussain Ratlamwala Senthan Mathavan Ghulam Hussain Mohammed Alkahtani Marwan Bin Muhammad Alsultan |
author_sort | Shakeel Ahmed |
collection | DOAJ |
description | The accurate prediction of aerodynamic properties is an essential requirement for the design of applications that involve fluid flows, especially in the aerospace industry. The aerodynamic characteristics of fluid flows around a wing or an airfoil are usually forecasted using the numerical solution of the Reynolds-averaged Navier–Stokes equation. However, very heavy computational expenses and lengthy progression intervals are associated with this method. Advancements in computational power and efficiency throughout the present era have considerably reduced these costs; however, for many practical applications, performing numerical simulations is still a very computationally expensive and time-consuming task. The application of machine learning techniques has seen a sharp rise in various fields over recent years, including fluid dynamics, and they have proved their worth. In the present study, a famous machine learning model that is known as the back-propagation neural network was implemented for the prediction of the aerodynamic coefficients of airfoils. The most important aerodynamic properties of the coefficient of lift and the coefficient of drag were predicted by providing the model with the name, flow Reynolds number, Mach number and the angle of attack of the airfoils with respect to the incoming flows as input parameters. The dataset for the current study was obtained by performing CFD simulations using the RANS-based Spalart–Allmaras turbulence model on four different NACA series airfoils under varying aerodynamic conditions. The data that were obtained from the CFD simulations were divided into two subsets: 70% were used as training data and the remaining 30% were used as validation and testing data. The BPNN showed promising results for the prediction of the aerodynamic coefficients of airfoils under different conditions. An RMSE value of 3.57 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mo>×</mo></semantics></math></inline-formula> 10<sup>−7</sup> was achieved for the best performance validation case with 28 epochs when there were 10 neurons in the hidden layer. The regression plot also depicted a close to perfect fit between the predicted and actual values for the regression curves. |
first_indexed | 2024-03-10T03:22:32Z |
format | Article |
id | doaj.art-802837cfe71049e7aad511f070886073 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T03:22:32Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-802837cfe71049e7aad511f0708860732023-11-23T09:59:01ZengMDPI AGApplied Sciences2076-34172022-05-011210519410.3390/app12105194Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS SimulationShakeel Ahmed0Khurram Kamal1Tahir Abdul Hussain Ratlamwala2Senthan Mathavan3Ghulam Hussain4Mohammed Alkahtani5Marwan Bin Muhammad Alsultan6National University of Sciences and Technology, Islamabad 44000, PakistanNational University of Sciences and Technology, Islamabad 44000, PakistanNational University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Civil and Structural Engineering, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UKMechanical Engineering Department, College of Engineering, University of Bahrain, Isa Town 32038, BahrainDepartment of Industrial Engineering, College of Engineering, King Saud University, P.O. Box 800, Riyadh 11421, Saudi ArabiaDepartment of Industrial Engineering, College of Engineering, King Saud University, P.O. Box 800, Riyadh 11421, Saudi ArabiaThe accurate prediction of aerodynamic properties is an essential requirement for the design of applications that involve fluid flows, especially in the aerospace industry. The aerodynamic characteristics of fluid flows around a wing or an airfoil are usually forecasted using the numerical solution of the Reynolds-averaged Navier–Stokes equation. However, very heavy computational expenses and lengthy progression intervals are associated with this method. Advancements in computational power and efficiency throughout the present era have considerably reduced these costs; however, for many practical applications, performing numerical simulations is still a very computationally expensive and time-consuming task. The application of machine learning techniques has seen a sharp rise in various fields over recent years, including fluid dynamics, and they have proved their worth. In the present study, a famous machine learning model that is known as the back-propagation neural network was implemented for the prediction of the aerodynamic coefficients of airfoils. The most important aerodynamic properties of the coefficient of lift and the coefficient of drag were predicted by providing the model with the name, flow Reynolds number, Mach number and the angle of attack of the airfoils with respect to the incoming flows as input parameters. The dataset for the current study was obtained by performing CFD simulations using the RANS-based Spalart–Allmaras turbulence model on four different NACA series airfoils under varying aerodynamic conditions. The data that were obtained from the CFD simulations were divided into two subsets: 70% were used as training data and the remaining 30% were used as validation and testing data. The BPNN showed promising results for the prediction of the aerodynamic coefficients of airfoils under different conditions. An RMSE value of 3.57 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mo>×</mo></semantics></math></inline-formula> 10<sup>−7</sup> was achieved for the best performance validation case with 28 epochs when there were 10 neurons in the hidden layer. The regression plot also depicted a close to perfect fit between the predicted and actual values for the regression curves.https://www.mdpi.com/2076-3417/12/10/5194aerodynamicsBPNNCFDmachine learningneural networksnumerical simulations |
spellingShingle | Shakeel Ahmed Khurram Kamal Tahir Abdul Hussain Ratlamwala Senthan Mathavan Ghulam Hussain Mohammed Alkahtani Marwan Bin Muhammad Alsultan Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS Simulation Applied Sciences aerodynamics BPNN CFD machine learning neural networks numerical simulations |
title | Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS Simulation |
title_full | Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS Simulation |
title_fullStr | Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS Simulation |
title_full_unstemmed | Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS Simulation |
title_short | Aerodynamic Analyses of Airfoils Using Machine Learning as an Alternative to RANS Simulation |
title_sort | aerodynamic analyses of airfoils using machine learning as an alternative to rans simulation |
topic | aerodynamics BPNN CFD machine learning neural networks numerical simulations |
url | https://www.mdpi.com/2076-3417/12/10/5194 |
work_keys_str_mv | AT shakeelahmed aerodynamicanalysesofairfoilsusingmachinelearningasanalternativetoranssimulation AT khurramkamal aerodynamicanalysesofairfoilsusingmachinelearningasanalternativetoranssimulation AT tahirabdulhussainratlamwala aerodynamicanalysesofairfoilsusingmachinelearningasanalternativetoranssimulation AT senthanmathavan aerodynamicanalysesofairfoilsusingmachinelearningasanalternativetoranssimulation AT ghulamhussain aerodynamicanalysesofairfoilsusingmachinelearningasanalternativetoranssimulation AT mohammedalkahtani aerodynamicanalysesofairfoilsusingmachinelearningasanalternativetoranssimulation AT marwanbinmuhammadalsultan aerodynamicanalysesofairfoilsusingmachinelearningasanalternativetoranssimulation |