Abstract
In this paper, an artificial neural network (ANN)-based reduced order model (ROM) is developed for the hydrodynamics forces on an airfoil immersed in the flow field at different angles of attack. The proper orthogonal decomposition (POD) of the flow field data is employed to obtain pressure modes and the temporal coefficients. These temporal pressure coefficients are used to train the ANN using data from three different angles of attack. The trained network then takes the value of angle of attack (AOA) and past POD coefficients as an input and predicts the future temporal coefficients. We also decompose the surface pressure modes into lift and drag components. These surface pressure modes are then employed to calculate the pressure component of lift CLp and drag CDp coefficients. The train model is then tested on the in-sample data and out-of-sample data. The results show good agreement with the true numerical data, thus validating the neural network based model.
Highlights
Airfoils are cross sectional curved surfaces which give required ratio of hydrodynamic forces
We simulated the incompressible flow over a stationary airfoil NACA0012 at different angle of attack (AOA)
The main objective of the study was to develop the reduced-order models (ROM) for hydrodynamic forces acting on the airfoil surface using machine learning tools
Summary
Airfoils are cross sectional curved surfaces which give required ratio of hydrodynamic forces (i.e., lift and drag). There is vivid decrease in the hydrodynamic forces (i.e., lift and drag) [1,2], so there is a need to control flow separation. Proper orthogonal decomposition (POD) [3] is mostly used to project these transient flows on the low dimensional subspace where these flows behave linearly. POD was first used for reduced-order modeling of turbulence by projecting the Navier–Stokes equations onto the low dimensional space [4]. Different model reduction techniques have been developed in recent years to reduce the dimensionality of dataset, such as POD, dynamic mode decomposition (DMD) [5,6], and its variants [7,8,9], spectral proper orthogonal decomposition (SPOD) [10,11] and machine learning-based methods, such as autoencoders [12], etc
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
