This paper presents a test platform for Unmanned Aerial Vehicles, capable of detecting early damages in UAV components. The paper presents the architecture of the platform and the machine learning method used to detect damages. The method was proven with two types of emulated damages on propellers. The results showed a classification accuracy of about 90% in the identification of the damage.
UAV test-bench platform for propeller diagnostics using Machine Learning
Daponte P.;De Vito L.;Picariello F.;Tudosa I.
2024-01-01
Abstract
This paper presents a test platform for Unmanned Aerial Vehicles, capable of detecting early damages in UAV components. The paper presents the architecture of the platform and the machine learning method used to detect damages. The method was proven with two types of emulated damages on propellers. The results showed a classification accuracy of about 90% in the identification of the damage.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.
