Title: Thrust-level dependent vibration diagnostics of UAV propeller using fast Fourier transform and K-nearest neighbour

Authors: Bahadır Cinoğlu; Umut Durak

Addresses: Department of Avionics, Eskisehir Technical University, Türkiye ' Institute of Flight Systems, German Aerospace Center (DLR), Germany

Abstract: A big majority of UAV failures link to its motors, propellers, or any other mechanical parts. Early diagnosis of problems related to these parts can play a crucial role in preventing incidents. In this study, vibration data from damaged and undamaged UAV propellers is captured using a three-axis accelerometer. Then, raw vibration data features are extracted using the fast Fourier transform in order to analyse the frequency components of the signal. These features are used to train a machine learning model using the K-nearest neighbour algorithm and obtain good performance with an accuracy of 81.90% in classifying damaged and undamaged propellers in a total of three different thrust levels. Results are promising in diagnosing abnormal behaviours on propellers using vibration data and diminishing propeller-related failures.

Keywords: propeller damage; machine learning; classification; UAV; diagnostics; vibration; K-nearest neighbours; fast Fourier transform; FFT; min-max scaling.

DOI: 10.1504/IJSA.2024.142568

International Journal of Sustainable Aviation, 2024 Vol.10 No.4, pp.297 - 314

Received: 03 Jun 2024
Accepted: 28 Aug 2024
Published online: 08 Nov 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article