Identifying the fault in propellers is important to keep quadrotors operating safely and efficiently. The simulation-to-reality (sim-to-real) UAV fault diagnosis methods provide a cost-effective and safe approach to detect the propeller faults. However, due to the gap between simulation and reality, classifiers trained with simulated data usually underperform in real flights. In this work, a new deep neural network (DNN) model is presented to address the above issue. It uses the difference features extracted by deep convolutional neural networks (DDCNN) to reduce the sim-to-real gap. Moreover, a new domain adaptation method is presented to further bring the distribution of the real-flight data closer to that of the simulation data. The experimental results show that the proposed approach can achieve an accuracy of 97.9\% in detecting propeller faults in real flight. Feature visualization was performed to help better understand our DDCNN model.

翻译：识别螺旋桨故障对于保证四旋翼无人机安全高效运行至关重要。仿真到现实（sim-to-real）的无人机故障诊断方法提供了一种经济高效且安全的途径来检测螺旋桨故障。然而，由于仿真与现实之间存在差距，使用模拟数据训练的分类器在实际飞行中通常表现不佳。本文提出了一种新的深度神经网络（DNN）模型来解决上述问题。该模型利用深度卷积神经网络提取的差异特征（DDCNN）来缩小仿真到现实的差距。此外，还提出了一种新的域适应方法，以进一步使真实飞行数据的分布更接近仿真数据的分布。实验结果表明，所提方法在实际飞行中检测螺旋桨故障的准确率可达97.9%。通过特征可视化，有助于更好地理解我们的DDCNN模型。