Safety in the operation of Unmanned Aerial Vehicles (UAVs) is emerging as an increasingly important requirement to avoid accidents or possible hazards, because of the growing number and variety of applications that make use of such systems. Consequently, the ability to detect and classify damages occurring on UAV components becomes critical, so that appropriate countermeasures can be applied on time. In this paper, a two-step methodology is proposed to detect damage to UAV propellers, and to classify its severity, so that the most appropriate response can be implemented. In fact, a first step is carried out onboard drone, in real-time, taking advantage of the acoustic emissions of the propeller and the potential of edge processing: a tiny Machine Learning (ML) classifier assesses the severity of the damage and, when deemed critical, the UAV is directed towards a ground station hosting a radar-based system, to discriminate the severity of the fault based on contactless vibration displacement and frequency measurements. The combination of both detection approaches realizes a diagnostic system that is time-responsive and accurate in defining the type, the amount, and the location of the damage. Damage classification performance values over 99% are provided by the embedded audio-based ML model; the radar-based step can further differentiate and measure the location of the propeller cut, which could eventually lead to forced landing of the UAV.
Ciattaglia et al. (Wed,) studied this question.