A Combined Navigation Fault Detection Method Based on Wavelet‐ResNet

ABSTRACT With the goal of realizing fault detection of airborne combined navigation system, this letter proposes a fault detection method combining wavelet transform and residual network. Firstly, the model equation of the system is established, and the combined navigation data set is constructed by combining the characteristics of the UAV flight trajectory. At the same time, the normal data of the UAV is added with common faults to obtain the fault data set. Then, the navigation data is preprocessed by discrete wavelet transform, and the residual network model is trained according to the preprocessed navigation data set to improve the training efficiency of the model. Finally, the trained model is tested and evaluated. The simulation results show that the accuracy of detecting mutation faults, slope faults and precision level reduction faults is more than .