Development of an Acoustic Fault Diagnosis System for UAV Propeller Blades - Masterarbeit

Abstract

With the rapid growth in demand for drones or unmanned aerial vehicles (UAVs), novel maintenance technologies are essential for ensuring automatic, safe, and reliable operations. This study proposes a fault detection system that utilizes the acoustic signature of UAV propeller blades for classifying their health state. By employing an acoustic camera with 112 microphones for spatial resolution of sound sources, datasets of acoustic images are generated in three differently reverberating environments for the third octave frequency bands of 6300Hz, 8000Hz, 10000Hz and 12500Hz. A convolutional neural network (CNN) is trained and evaluated with maximum F1-scores of 0.9962 and 0.9745 for two and three propeller health classes, respectively. Furthermore, a second approach utilizing a rotating beamformer is proposed. It makes use of the two sound sources that are identified for a two-bladed propeller, by calculating the ratio between the peak value of the sources. The second approach detects propeller tip damages without the assistance of machine learning and reaches an F1-score of 0.9441.