A Feature Fusion Network （FFN） was proposed to judge the quality of 3D face point cloud acquired by binocular structured light scanner. Firstly， the 3D point cloud was preprocessed to cut out the face area， and the image obtained from the point cloud and the corresponding 2D plane projection was used as the input. Secondly， Dynamic Graph Convolutional Neural Network （DGCNN） and ShuffleNet were trained for point cloud learning. Then， the middle layer features of the two network modules were extracted and fused to fine-tune the whole network. Finally， three full connected layers were used to realize the five-class classification of 3D face point cloud （excellent， ordinary， stripe， burr， deformation）. The proposed FFN achieved the classification accuracy of 83.7%， which was 5.8% higher than that of ShufflNet and 2.2% higher than that of DGCNN. The experimental results show that the weighted fusion of two-dimensional image features and point cloud features can achieve the complementary effect between different features.

To effectively analyze the ripple effect of node failure in Aircraft Ad Hoc Network （AANET） on the whole network and improve the stability of the network after occurring security incidents， a node failure ripple effect analysis model for AANET was proposed. Firstly， the directed weighted business network was established according to the main business of AANET， the undirected weighted physical network was established with various aircraft as the nodes based on real-time AANET， and the interdependent network model was built through the business-physical network mapping relationship. Secondly， a failure propagation model for AANET was proposed， and the node states and transformation modes between them were analyzed. Finally， the failure traffic redistribution algorithm was improved on the basis of link survivability， which was applied to the established interdependent network model to obtain the set of failed nodes and business degradation nodes caused by the ripple effect of node failure， then the set was used to analyze the ripple effect condition of the network at every moment. Experimental results show that the proposed model can effectively analyze the ripple effect condition of node failure in AANET.