An audio‐based risky flight detection framework for quadrotors  

作　　者：Wansong Liu Chang Liu Seyedomid Sajedi Hao Su Xiao Liang Minghui Zheng 

机构地区：[1]Department of Mechanical and Aerospace Engineering,University at Buffalo,Buffalo,New York,USA [2]Department of Civil,Structural and Environmental Engineering,University at Buffalo,Buffalo,New York,USA [3]Department of Mechanical and Aerospace Engineering,North Carolina State University,Raleigh,North Carolina,USA

出　　处：《IET Cyber-Systems and Robotics》2024年第1期1-14,共14页智能系统与机器人（英文）

基　　金：This material is based upon the work that is partially supported by the National Science Foundation‐USA under Grant No.2046481.

摘　　要：Drones have increasingly collaborated with human workers in some workspaces,such as warehouses.The failure of a drone flight may bring potential risks to human beings'life safety during some aerial tasks.One of the most common flight failures is triggered by damaged propellers.To quickly detect physical damage to propellers,recognise risky flights,and provide early warnings to surrounding human workers,a new and compre-hensive fault diagnosis framework is presented that uses only the audio caused by pro-peller rotation without accessing any flight data.The diagnosis framework includes three components:leverage convolutional neural networks,transfer learning,and Bayesian optimisation.Particularly,the audio signal from an actual flight is collected and trans-ferred into time–frequency spectrograms.First,a convolutional neural network‐based diagnosis model that utilises these spectrograms is developed to identify whether there is any broken propeller involved in a specific drone flight.Additionally,the authors employ Monte Carlo dropout sampling to obtain the inconsistency of diagnostic results and compute the mean probability score vector's entropy(uncertainty)as another factor to diagnose the drone flight.Next,to reduce data dependence on different drone types,the convolutional neural network‐based diagnosis model is further augmented by transfer learning.That is,the knowledge of a well‐trained diagnosis model is refined by using a small set of data from a different drone.The modified diagnosis model has the ability to detect the broken propeller of the second drone.Thirdly,to reduce the hyperparameters'tuning efforts and reinforce the robustness of the network,Bayesian optimisation takes advantage of the observed diagnosis model performances to construct a Gaussian pro-cess model that allows the acquisition function to choose the optimal network hyper-parameters.The proposed diagnosis framework is validated via real experimental flight tests and has a reasonably high diagnosis accuracy.

关 键 词：aerial robotics deep learning flying robots propeller diagnosis 

分 类 号：V249[航空宇航科学与技术—飞行器设计]