Multi-Objective Optimization of Low Reynolds Number Airfoil Using Convolutional Neural Network and Non-Dominated Sorting Genetic Algorithm

The airfoil is the prime component of flying vehicles. For low-speed flights, low Reynolds number airfoils are used. The characteristic of low Reynolds number airfoils is a laminar separation bubble and an associated drag rise. This paper presents a framework for the design of a low Reynolds number airfoil. The contributions of the proposed research are twofold. First, a convolutional neural network (CNN) is designed for the aerodynamic coefficient prediction of low Reynolds number airfoils. Data generation is discussed in detail and XFOIL is selected to obtain aerodynamic coefficients. The performance of the CNN is evaluated using different learning rate schedulers and adaptive learning rate optimizers. The trained model can predict the aerodynamic coefficients with high accuracy. Second, the trained model is used with a non-dominated sorting genetic algorithm (NSGA-II) for multi-objective optimization of the low Reynolds number airfoil at a specific angle of attack. A similar optimization is performed using NSGA-II directly calling XFOIL, to obtain the aerodynamic coefficients. The Pareto fronts of both optimizations are compared, and it is concluded that the proposed CNN can replicate the actual Pareto in considerably less time.

Computational Fluid Dynamic Analysis of Vortex Generators on MAV.

Micro Vortex generators are very small components deployed on the wings to control airflow over the upper surface of the wing to affect the boundary layer over it. These are employed onto a Micro aerial vehicle (MAV) of fixed wing type with an S5010 which is a low Reynolds number airfoil. This airfoil provides good aerodynamic results as compared to many low Reynolds number airfoils. Micro vortex generators are used to enhance the performance through controlling airflow at different speeds and angle of attack. The comparison of a half part of the MAV wing which is designed in CATIA, with and without the vortex generators on its leading edge at 10% of its chord length is done to show how the vortex generators improve the performance and control authority at different speeds and angle of attacks. These are shown with the velocity and pressure distribution around the wing by considering laminar flow in the simulation.

Suction effects on transitional bubbles

The effects of suction on the structure of a transitional bubble forming on a low-Reynolds-number airfoil are examined using the Reynolds-averaged Navier–Stokes and k–kL–ω transition model. The suction effects on the laminar and turbulent portions of the separation bubble and the locations of the main points in the separation bubble are discussed in relation to the transition process of the bubble. A single suction distribution located in the region of the baseline transitional bubble is used with two suction rates. One suction rate is sufficiently strong to eliminate the bubble from its original location and a lower suction rate that is only sufficient to create shallower bubbles. Eliminating the bubble from its original location maintains a laminar boundary layer downstream of the baseline transition location until a shallower separation bubble forms near the trailing edge. The lower suction rate shortens the separation bubble and reduces its height while approximately maintaining its original location. Analyzing the lengths of different portions of the bubble suggests that suction affects the instability growth rate and the nonlinear interactions in the separated shear layer. The lower suction rate shortens the distance between the separation and transition onset suggesting a higher growth rate of the inviscid instability. The higher suction rate, on the other hand, increases the distance between the separation and transition onset indicating a stabilizing effect by slowing down the growth rate of the inviscid instability. However, the percentage of distance between transition and separation to the total length is only slightly affected by the suction and the angle of attack.