Aero-engine damage is an important factor affecting flight safety. There are two main problems in the current computer vision-based damage detection of engine borescope image:one is that the complex background of borescope image makes the model detect the damage with low accuracy; the other one is that the data source of borescope image is limited, which leads to fewer detectable classes for the model. In order to solve these two problems, a Mask R-CNN (Mask Region-based Convolutional Neural Network) based progressive detection network from binary classification to multiple classification was proposed for aero-engine damage images. By adding a binary classification detection branch to the Mask R-CNN, firstly, the damage in the image was detected in binary way and regression optimization was performed to the localization coordinates. Secondly, the original detection branch was used to progressively perform multiple classification detection, so as to further optimize the damage detection results by regression and determine the damage class. Finally, instance segmentation was performed to the damage through the Mask branch according to the results of multiple classification detection. In order to increase the detection classes of the model and verify the effectiveness of the method, a dataset of 1 315 borescope images with 8 damage classes was constructed. The training and testing results on this set show that the Average Precision (AP) and AP75 (Average Precision under IoU (Intersection over Union) of 75%) of multiple classification detection are improved by 3.34% and 9.71% respectively, compared with those of Mask R-CNN. It can be seen that the proposed method can effectively improve the multiple classification detection accuracy for damages in borescope images.

Most of the traditional network representation learning methods cannot consider the rich structure information and attribute information in the network at the same time, resulting in poor performance of subsequent tasks such as classification and clustering. In order to solve this problem, an Auto-Encoder based Multi-View Attributed Network Representation learning model(AE-MVANR) was proposed. Firstly, the topological structure information of the network was transformed into the Topological Structure View(TSV), and the co-occurrence frequencies of the same attributes between nodes were calculated to construct the Attributed Structure View(ASV). Then, the random walk algorithm was used to obtain a series of node sequences on two views separately. At last, by inputting all the generated sequences into an auto-encoder model for training, the node representation vectors that integrate structure information and attribute information were obtained. Extensive experiments of classification and clustering tasks on several real-world datasets were carried out. The results demonstrate that AE-MVANR outperforms the widely used network representation learning method based solely on structure information and the one based on both network structure information and node attribute information. In specific, for classification results of the proposed model, the maximum increase of accuracy is 43.75%, and for clustering results of the proposed model, the maximum increase of Normalized Mutual Information(NMI) is 137.95%, the maximum increase of Silhouette Coefficient is 1 314.63% and the maximum decrease of Davies Bouldin Index(DBI) is 45.99%.

Focusing on the instability of Label Propagation Algorithm (LPA), an advanced label propagation algorithm for community detection was proposed. It introduced the concept of LeaderRank score to quantify the importance of nodes, and chose some core nodes according to the node importance in descending order, then updated labels layer by layer outward centered on every core node respectively, until no node changed its label any more. Thus the instability caused by the random ranking of nodes was solved. Compared with several existing label propagation algorithms on LFR benchmark networks and real networks, both of the Normalized Mutual Information (NMI) and modularity of community detection result of the proposed algorithm were higher. The theoretical analysis and experimental results demonstrate that the proposed algorithm not only improves the stability effectively, but also increases the accuracy.

In order to reduce the size of finite fields GF(2n) which was needed for the encoding calculation in intermediate node of network, a data transmission method based on hierarchical network coding was proposed in this paper. Focusing on the single-source multicast network with backbone-sub network structure, the authors decoded at the node that connected the backbone network and the sub-network. Then the decoded information was multicast to sub-network by network coding data transmission method. The theoretical analysis and the simulation results show that this method can reduce the size of finite fields GF(2n), and then reduce the computation delay of data transmission. Besides, it can make full use of the network capacity.

In order to solve the graph vertex-coloring problem, a DNA algorithm based on sticker model was proposed, which converted the coloring problem to satisfiability problem on the basis of the vast parallelism. The operation steps were given through an instance. And a simulation experiment was carried out to illustrate the biochemical procedures. The final coloring schemes were got. Consequently, the feasibility of the algorithm is proved.