The increasing employment of drones in civilian applications demands robust systems to ensure operational safety and reliability. A critical challenge is the detection of damages to drone propellers occurring post-takeoff, which can compromise operation effectiveness and security. This study proposes an acoustic monitoring system to assess the integrity of drone propellers using an onboard microphone, aiming at performing onboard and real-time predictive maintenance. The Symmetrized Dot Pattern (SDP) representation of the audio samples is exploited. Specifically, the resulting representations are further processed via a differential and averaging approach. It is found that this methodology applied to the audio samples collected with propellers in different conditions, but rotating at the same speed, may overcome intra-class variability and interclass similarity, thus hinting at the potential effectiveness of an embedded classifier capable of detecting occurrences of damages, and leaving opportunities for further analyses.

Acoustic Monitoring of Drone Propeller Integrity Using Symmetrized Dot Pattern / Bruschi, V., Peruzzi, G., Ciattaglia, G., Pozzebon, A., Spinsante, S., Cecchi, S.. - (2025), pp. 565-570. (2025 IEEE International Workshop on Technologies for Defense and Security, TechDefense 2025 ita 2025) [10.1109/TechDefense67306.2025.11721017].

Acoustic Monitoring of Drone Propeller Integrity Using Symmetrized Dot Pattern

Bruschi V.;Ciattaglia G.;Spinsante S.;Cecchi S.
2025-01-01

Abstract

The increasing employment of drones in civilian applications demands robust systems to ensure operational safety and reliability. A critical challenge is the detection of damages to drone propellers occurring post-takeoff, which can compromise operation effectiveness and security. This study proposes an acoustic monitoring system to assess the integrity of drone propellers using an onboard microphone, aiming at performing onboard and real-time predictive maintenance. The Symmetrized Dot Pattern (SDP) representation of the audio samples is exploited. Specifically, the resulting representations are further processed via a differential and averaging approach. It is found that this methodology applied to the audio samples collected with propellers in different conditions, but rotating at the same speed, may overcome intra-class variability and interclass similarity, thus hinting at the potential effectiveness of an embedded classifier capable of detecting occurrences of damages, and leaving opportunities for further analyses.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/366236
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact