Intelligent diagnosis approach for the critical structural part based on FSDP figure and DCNN

With the increasing application of UAV, the corresponding means of support also need to keep pace with the times. With the large-scale development of artificial intelligence, the combination of fault diagnosis and artificial intelligence provides an important opportunity for the leapfrog development of key technologies of UAV support, and also provides an important opportunity for the improvement of the level of UAV safety and operation reliability. Based on the ultrasonic signal analysis method in structural health monitoring, this paper carries out research on the damage detection of key structural components of UAV landing gear, and combines the deep learning model to intelligently detect the damage of structural components to improve the detection efficiency and accuracy. Aiming at the characteristics of nonlinear damage signals in structural health monitoring, the feature extraction method of Frequency Symmetrized Dot Pattern (FSDP) is proposed. On this basis, an intelligent damage detection method based on FSDP feature and DCNN is proposed. The structural damage simulation and detection experiments are carried out in the landing gear experimental environment, and the effectiveness of the proposed intelligent detection method is verified by experimental data.