%N 2
%D 2024
%L scholars20289
%V 39
%X This study presents a novel method for damage detection and identification in unmanned aerial vehicles (UAVs) using vibration data gathering and processing technologies based on deep learning. To conduct the study, a quad-rotor UAV was manufactured, and a vibration data acquisition system was developed to collect vibration data along three axes under normal and three damage scenarios. Empirical mode decomposition (EMD) was employed to reduce high-frequency noise in the signals, and the root mean square error (RMSE) feature was utilised to select the Y-axis acceleration data, which exhibits significant changes across different damage cases. Finally, a convolutional neural network was used to identify the damage based on the vibration data. Experimental results demonstrate that the proposed method achieved 97.5 accuracy using selected and noise-reduced Y-axis acceleration data, thereby indicating its usefulness in diagnosing damage types in multi-rotor UAVs. © 2023 Informa UK Limited, trading as Taylor & Francis Group.
%R 10.1080/10589759.2023.2206655
%A Y. Ma
%A F. Mustapha
%A M.R. Ishak
%A S. Abdul Rahim
%A M. Mustapha
%J Nondestructive Testing and Evaluation
%T Structural fault diagnosis of UAV based on convolutional neural network and data processing technology
%K Acceleration; Aircraft detection; Antennas; Convolution; Convolutional neural networks; Damage detection; Data handling; Deep learning; Fault detection; Mean square error; Signal processing; Structural health monitoring; Unmanned aerial vehicles (UAV); Vibrations (mechanical), Acceleration data; Aerial vehicle; Convolutional neural network; Damage detection and identification; Deep learning; Faults diagnosis; Multi-rotor unmanned aerial vehicle;; Structural faults; Vibration data; Vibration data acquisition, Data acquisition
%O cited By 7
%P 426-445
%I Taylor and Francis Ltd.