Machine Learning for Pre/Post Flight UAV Rotor Defect Detection Using Vibration Analysis

TL;DR

The paper addresses pre- and post-flight UAV rotor health monitoring by combining vibration analysis with machine learning. It builds a data-driven pipeline using time- and frequency-domain features, including STFT and Wavelet Packets, and demonstrates that a Random Forest classifier with PCA achieves perfect defect detection on the collected dataset. Through PCA, feature isolation, and feature-importance analyses, the study elucidates which feature types and axes most influence the discrimination between normal and defective rotors. The work also contributes a publicly available vibrational dataset to enable broader research in UAV rotor fault detection. Overall, the approach offers a high-accuracy, automate-able method for rotor condition monitoring with potential for real-time deployment in smart-city UAV applications.

Abstract

Unmanned Aerial Vehicles (UAVs) will be critical infrastructural components of future smart cities. In order to operate efficiently, UAV reliability must be ensured by constant monitoring for faults and failures. To this end, the work presented in this paper leverages signal processing and Machine Learning (ML) methods to analyze the data of a comprehensive vibrational analysis to determine the presence of rotor blade defects during pre and post-flight operation. With the help of dimensionality reduction techniques, the Random Forest algorithm exhibited the best performance and detected defective rotor blades perfectly. Additionally, a comprehensive analysis of the impact of various feature subsets is presented to gain insight into the factors affecting the model's classification decision process.

Figures (7)

• Figure 1: Normal vs. defective rotor types.
• Figure 2: PCA Analysis: impact on ML model performance.
• Figure 3: Feature isolation analysis: impact on ML model performance.
• Figure 4: Top feature type analysis.
• Figure 5: Top feature type importance analysis.