Intelligent Fault Diagnosis Method for Blade Damage of Quad-Rotor UAV Based on Stacked Pruning Sparse Denoising Autoencoder and Convolutional Neural Network

Abstract

This paper introduces a new intelligent fault diagnosis method based on stack pruning sparse denoising autoencoder and convolutional neural network (sPSDAE-CNN). This method processes the original input data by using a stack denoising autoencoder. Different from the traditional autoencoder, stack pruning sparse denoising autoencoder includes a fully connected autoencoding network, the features extracted from the front layer of the network are used for the operation of the subsequent layer, which means that some new connections will appear between the front and rear layers of the network, reduce the loss of information, and obtain more effective features. Firstly, a one-dimensional sliding window is introduced for data enhancement. In addition, transforming one-dimensional time-domain data into the two-dimensional gray image can further improve the deep learning (DL) ability of models. At the same time, pruning operation is introduced to improve the training efficiency and accuracy of the network. The convolutional neural network model with sPSDAE has a faster training speed, strong adaptability to noise interference signals, and can also suppress the over-fitting problem of the convolutional neural network to a certain extent. Actual experiments show that for the fault of unmanned aerial vehicle (UAV) blade damage, the sPSDAE-CNN model we use has better stability and reliable prediction accuracy than traditional convolutional neural networks. At the same time, For noise signals, better results can be obtained. The experimental results show that the sPSDAE-CNN model still has a good diagnostic accuracy rate in a high-noise environment. In the case of a signal-to-noise ratio of −4, it still has an accuracy rate of 90%.

An Intelligent Fault Detection Framework for FW-UAV Based on Hybrid Deep Domain Adaptation Networks and the Hampel Filter

“…parameters, LC. parameter) (12) Save the best model on D val (13) End for (14) Testing: (15) Input: D test (16) and 13 th , i.e., normal and d 1 � 0.3 (30% efciency of the right-wing control surface), and nine states (normal, d 1 � 0.3, and d 2 � 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9) were simulated on 21 st and 23 rd .…”

“…Deep learning, with strong nonlinear feature extraction ability, has yielded excellent results in many felds including fault diagnosis [11] and is increasingly considered for UAV faults. To give full play to the advantages of deep learning, many researchers try to collect available data through various methods, such as artifcially destroying the blades of drones and collecting data in a safe area [12][13][14], obtaining fault data through simulation [15][16][17], and injecting faults into fying drones through software [18,19]. Nevertheless, due to the multiple limitations of the UAVs themselves and the diversity and complexity of their mission environment, it still faces problems such as scarcity of fault samples, sample imbalance, and difculty in obtaining samples from complex environments.…”

Simulation-to-reality UAV Fault Diagnosis with Deep Learning

“…As they are data-driven and work in an end-to-end fashion, such approaches do not require the development of system models or the design of fault classifiers based on these models. Much of the previous work in this area [7], [8] has focused on designing powerful DNN models that can learn the complex nonlinear relationship between the input features and use this knowledge to identify propeller faults.…”

Fault-Tolerant Control of a Variable-Pitch Quadrotor under Actuator Loss of Effectiveness and Wind Perturbations

“…The most common class of actuator fault is a Loss of Effectiveness (LOE), i.e., the produced thrust is lower than the expected one. In fact, LOE may be the consequence of many issues: battery voltage drop [ 15 ], increased drag due to the blade pitch [ 5 ], and of course any physical damage to the blades [ 16 ]. However, as for the specific case of fault diagnosis and tolerant control for VPQs, few works can be found in the literature.…”