Deeply Integrated Autoencoder-Based Anomaly Detection and Critical Parameter Identification for Unmanned Aerial Vehicle Actuators

In unmanned aerial vehicle (UAV), flight status monitoring and anomaly detection are effective ways to improve the safety and reliability of UAVs. However, when a UAV is on a mission, any small anomaly can impact the UAV, leading to mission failure. At the same time, most current methods target the detection of a single anomaly type or data and do not consider the occurrence of anomalies in different parameters in the UAV flight data. Therefore, this article proposes a deeply integrated autoencoder anomaly detection method for anomaly detection and critical parameter identification of UAV actuators. First, to reduce the influence of random noise on the model performance, the original data are smoothed using the Savitzky-Golay filter. Second, a hybrid model combining nonlinear mapping, 1-D convolutional neural networks (1DCNNs), and AutoEncoder to exploit the spatiotemporal features in the data fully. Finally, anomaly detection was achieved by comparing the residuals with the anomaly determination threshold, and critical parameter identification was achieved by calculating the anomaly contribution. Experimental results on accurate UAV actuator data injected with anomalies show that the proposed method has obvious advantages over the benchmark method.