The increase in emissions associated with aviation requires deeper research into novel sensing and flow-control strategies to obtain improved aerodynamic performances. In this context, data-driven methods are suitable for exploring new approaches to control the flow and develop more efficient strategies. Deep artificial neural networks (ANNs) used together with reinforcement learning, i.e., deep reinforcement learning (DRL), are receiving more attention due to their capabilities of controlling complex problems in multiple areas. In particular, these techniques have been recently used to solve problems related to flow control. In this work, an ANN trained through a DRL agent, coupled with the numerical solver Alya, is used to perform active flow control. The Tensorforce library was used to apply DRL to the simulated flow. Two-dimensional simulations of the flow around a cylinder were conducted and an active control based on two jets located on the walls of the cylinder was considered. By gathering information from the flow surrounding the cylinder, the ANN agent is able to learn through proximal policy optimization (PPO) effective control strategies for the jets, leading to a significant drag reduction. Furthermore, the agent needs to account for the coupled effects of the friction- and pressure-drag components, as well as the interaction between the two boundary layers on both sides of the cylinder and the wake. In the present work, a Reynolds number range beyond those previously considered was studied and compared with results obtained using classical flow-control methods. Significantly different forms of nature in the control strategies were identified by the DRL as the Reynolds number $Re$ increased. On the one hand, for $Re\le 1000$, the classical control strategy based on an opposition control relative to the wake oscillation was obtained. On the other hand, for $Re=2000$, the new strategy consisted of energization of the boundary layers and the separation area, which modulated the flow separation and reduced the drag in a fashion similar to that of the drag crisis, through a high-frequency actuation. A cross-application of agents was performed for a flow at $Re=2000$, obtaining similar results in terms of the drag reduction with the agents trained at $Re=1000$ and 2000. The fact that two different strategies yielded the same performance made us question whether this Reynolds number regime ($Re=2000$) belongs to a transition towards a nature-different flow, which would only admits a high-frequency actuation strategy to obtain the drag reduction. At the same time, this finding allows for the application of ANNs trained at lower Reynolds numbers, but are comparable in nature, saving computational resources.

Distributed electric propulsion and boundary layer ingestion are two attractive technologies to reduce the power consumption of fixed wing aircraft. Through careful distribution of the propulsive system elements, higher aerodynamic and propulsive efficiency can be achieved, as well as a lower risk of total loss of aircraft due to foreign object damage. When used on the wing, further reductions of the bending moment on the wing root can even lead to reductions of its structural weight, thus mitigating the expected increase of operating empty weight due to the extra components needed. While coupling these technologies in fixed-wing aircraft is being actively studied in the big aircraft segment, it is also an interesting approach for increasing the efficiency even for aircraft with maximum take-off masses as low as 25 kg, such as the A3 open subcategory for civil drones from EASA. This paper studies the effect of changing the propellers’ position in the aerodynamic performance parameters of a distributed electric propulsion with boundary layer ingestion system in a 25 kg fixed-wing aircraft, as well as in the performance of the propellers. The computational results show the trade-offs between the aerodynamic efficiency and the propeller efficiency when the vertical position is varied.

New propulsive architectures, with high interactions with the aerodynamic performance of the platform, are an attractive option for reducing the power consumption, increasing the resilience, reducing the noise and improving the handling of fixed-wing unmanned air vehicles. Distributed electric propulsion with boundary layer ingestion over the wing introduces extra complexity to the design of these systems, and extensive simulation and experimental campaigns are needed to fully understand the flow behaviour around the aircraft. This work studies the effect of different combinations of propeller positions and angles of attack over the pressure coefficient and skin friction coefficient distributions over the wing of a 25 kg fixed-wing remotely piloted aircraft. To get more information about the main trends, a proper orthogonal decomposition of the coefficient distributions is performed, which may be even used to interpolate the results to non-simulated combinations, giving more information than an interpolation of the main aerodynamic coefficients such as the lift, drag or pitching moment coefficients.

Deep artificial neural networks (ANNs) used together with deep reinforcement learning (DRL) are receiving growing attention due to their capabilities to control complex problems. This technique has been recently used to solve problems related to flow control. In this work, an ANN trained through a DRL agent is used to perform active flow control. Two-dimensional simulations of the flow around a cylinder are conducted and an active control based on two jets located on the walls of the cylinder is considered. By gathering information from the flow surrounding the cylinder, the ANN agent is able to learn effective control strategies for the jets, leading to a significant drag reduction. In the present work, a Reynolds-number range beyond those previously considered is studied and compared with results obtained using classical flow-control methods. Significantly different nature in the control strategies is identified by the DRL as the Reynolds number Re increases. For Re <= 1000 the classical control strategy based on an opposition control relative to the wake oscillation is obtained. For Re = 2000 the new strategy consists of an energisation of the boundary layers and the separation area, which modulate the flow separation and reduce drag in a fashion similar to that of the drag crisis, through a high frequency actuation. A cross-application of agents is performed for a flow at Re = 2000, obtaining similar results in terms of drag reduction with the agents trained at Re = 1000 and 2000. The fact that two different strategies yield the same performance make us question whether this Reynolds number regime (Re = 2000) belongs to a transition towards a nature-different flow which would only admit a high-frequency actuation strategy to obtain drag reduction. This finding allows the application of ANNs trained at lower Reynolds numbers but comparable in nature, saving computational resources.