TY - JOUR
T1 - Fast pressure distribution prediction of airfoils using deep learning
AU - Hui, Xinyu
AU - Bai, Junqiang
AU - Wang, Hui
AU - Zhang, Yang
N1 - Publisher Copyright:
© 2020 Elsevier Masson SAS
PY - 2020/10
Y1 - 2020/10
N2 - In the aerodynamic design, optimization of the pressure distribution of airfoils is crucial for the aerodynamic components. Conventionally, the pressure distribution is solved by computational fluid dynamics, which is a time-consuming task. Surrogate modeling can leverage such expense to some extent, but it needs careful shape parameterization schemes for airfoils. As an alternative, deep learning approximates inputs-outputs mapping without solving the efficiency-expensive physical equations and avoids the limitations of particular parameterization methods. Therefore, this paper presents a data-driven approach for predicting the pressure distribution over airfoils based on Convolutional Neural Network (CNN). Given the airfoil geometry, a supervised learning problem is presented for predicting aerodynamic performance. Furthermore, we utilize a universal and flexible parametrization method called Signed Distance Function to improve the performances of CNN. Given the unseen airfoils from the validation dataset to the trained model, our model achieves predicting the pressure coefficient in seconds, with a less than 2% mean square error.
AB - In the aerodynamic design, optimization of the pressure distribution of airfoils is crucial for the aerodynamic components. Conventionally, the pressure distribution is solved by computational fluid dynamics, which is a time-consuming task. Surrogate modeling can leverage such expense to some extent, but it needs careful shape parameterization schemes for airfoils. As an alternative, deep learning approximates inputs-outputs mapping without solving the efficiency-expensive physical equations and avoids the limitations of particular parameterization methods. Therefore, this paper presents a data-driven approach for predicting the pressure distribution over airfoils based on Convolutional Neural Network (CNN). Given the airfoil geometry, a supervised learning problem is presented for predicting aerodynamic performance. Furthermore, we utilize a universal and flexible parametrization method called Signed Distance Function to improve the performances of CNN. Given the unseen airfoils from the validation dataset to the trained model, our model achieves predicting the pressure coefficient in seconds, with a less than 2% mean square error.
KW - Aerodynamic design
KW - Convolutional neural network
KW - Machine learning
KW - Pressure distribution prediction
UR - http://www.scopus.com/inward/record.url?scp=85087587239&partnerID=8YFLogxK
U2 - 10.1016/j.ast.2020.105949
DO - 10.1016/j.ast.2020.105949
M3 - 文章
AN - SCOPUS:85087587239
SN - 1270-9638
VL - 105
JO - Aerospace Science and Technology
JF - Aerospace Science and Technology
M1 - 105949
ER -