No abstract

No abstract

In recent years, unmanned aerial vehicles (UAVs) have been used in several fields including, for example, archaeology, cargo transport, conservation, healthcare, filmmaking, hobbies and recreational use. UAVs are aircraft characterized by the absence of a human pilot on board. The extensive use of these devices has highlighted maintenance problems with regard to the propellers, which represent the source of propulsion of the aircraft. A defect in the propellers of a drone can cause the aircraft to fall to the ground and its consequent destruction, and it also constitutes a safety problem for objects and people that are in the range of action of the aircraft. In this study, the measurements of the noise emitted by a UAV were used to build a classification model to detect unbalanced blades in a UAV propeller. To simulate the fault condition, two strips of paper tape were applied to the upper surface of a blade. The paper tape created a substantial modification of the aerodynamics of the blade, and this modification characterized the noise produced by the blade in its rotation. Then, a model based on artificial neural network algorithms was built to detect unbalanced blades in a UAV propeller. This model showed high accuracy (0.9763), indicating a high number of correct detections and suggests the adoption of this tool to verify the operating conditions of a UAV. The test must be performed indoors; from the measurements of the noise produced by the UAV it is possible to identify an imbalance in the propeller blade.

In recent years, security in urban areas has gradually assumed a central position, focusing increasing attention on citizens, institutions and political forces. Security problems have a different nature—to name a few, we can think of the problems deriving from citizens’ mobility, then move on to microcrime, and end up with the ever-present risk of terrorism. Equipping a smart city with an infrastructure of sensors capable of alerting security managers about a possible risk becomes crucial for the safety of citizens. The use of unmanned aerial vehicles (UAVs) to manage citizens’ needs is now widespread, to highlight the possible risks to public safety. These risks were then increased using these devices to carry out terrorist attacks in various places around the world. Detecting the presence of drones is not a simple procedure given the small size and the presence of only rotating parts. This study presents the results of studies carried out on the detection of the presence of UAVs in outdoor/indoor urban sound environments. For the detection of UAVs, sensors capable of measuring the sound emitted by UAVs and algorithms based on deep neural networks capable of identifying their spectral signature that were used. The results obtained suggest the adoption of this methodology for improving the safety of smart cities.

No abstract