Acoustic Monitoring of Small UAV Propulsion: A Critical Review of Sensor Placement, Noise-Robust Wavelet Features, and Resource-Efficient Machine Learning

Abstract

UAVs are being employed for inspection, mapping, emergency response, and low-altitude activities. However, propeller fractures, edge wear, tip loss, imbalance, motor-bearing deterioration, eccentric shafts, and operating circumstances might damage their propulsion systems. Acoustic health monitoring is promising for this task because propulsion failures may change pressure fluctuations, blade-passing tones, broadband aerodynamic noise, and vibration-radiated sound without structural changes. Wind, reverberation, interference from surrounding rotors, speed variations, sensor-direction effects, limited datasets, and the gap between laboratory precision and field robustness in operational situations prevent acoustic UAV diagnostics from being widely used. Acoustic diagnostics of small UAV propulsion systems are the focus of this article. Acoustic emission monitoring, microphone-array and beamforming, wavelet and time–frequency feature extraction, normalized feature design, machine learning, lightweight deep learning, and noise-resilient deployment evaluation criteria are included. The reviewed studies reported promising results, including on-board microphone-array isolation of damaged rotors, acoustic-camera propeller-tip identification, and deep learning on propeller-anomaly datasets. Standardization of sensor locations, publicly accessible multi-condition acoustic datasets, cross-UAV validation, systematic selection of wavelet bases and decomposition levels, and clear computational cost reporting are still lacking. A deployment-oriented roadmap emphasizes multi-condition benchmarking, sensor placement optimization, wavelet-based noise robustness, hybrid acoustic-vibration validation, domain adaptation, uncertainty-aware decision-making, and edge AI for real-time UAV propulsion health monitoring.