Recently, unmanned aerial vehicle (UAV) task allocation is a hot topic both in the civilian and military, while the research of considering uncertainty and multi-objective is still in its infancy. Firstly, based on the uncertainty theory, a mathematical model of the uncertain multi-objective UAV task allocation problem with uncertain variables in both objective function and constraint conditions is established. The expected value criterion and opportunity constraint are introduced to transform the model into a deterministic optimization model. Furthermore, because traditional fireworks algorithm (FWA) has the shortcomings of low solution accuracy and slow convergence speed in solving the UAV task allocation problem, a novel Tent-Levy FWA (TLFWA) based on discrete update process is designed by introducing integer coding, Tent chaotic mapping and Levy variation. Experimental results show that the mean cost calculated by TLFWA is 8.17% and 13.73% lower than that of FWA and particle swarm optimization algorithm respectively, which proves the effectiveness of TLFWA. This study provides a new way to solve multi-objective and uncertain decision-making problems.

Carbon fiber reinforced polymer (CFRP) is one of the most vital structural materials used in the aviation industry. Automatic identification is becoming a key method for timely detection of the internal defects in CFRP structural components to ensure the aviation safety. In this paper, an innovative automatic characterization framework based on a Res-Transformer neural network is proposed. To identify the pre-embedded delamination defects with varying depths in CFRP curved structures, an infrared thermography detection system has been built to collect relevant signals. In the neural network, a data processing module is designed to enhance the characteristic differences between the raw temperature-time series signals from delamination defects with different depth. The residual module and Transformer encoder are developed to improve both the local and global features extraction ability while reduce the computational cost. Results indicate that our method is capable of accurately characterizing all pre-embedded delamination defects while effectively reducing the misidentification of non-defective areas. The comprehensive evaluation index F1-score of this method reaches 92.81%, which is superior to other mainstream methods, showing its applicability and advancement.

In order to automate defect detection with few samples using unsupervised learning, this paper, considering materials commonly used in aircraft, proposes a phased array ultrasonic detection defect identification method using non-defect samples for training, and three-dimensional characterization is completed on this basis. A phased array ultrasonic device was used to detect two typical structures: a carbon fiber composite cylinder structure and a metal L-shaped structure. No damage label image was required, and the non-damaged sample was used as the the network training input. Based on contrast learning and the cross-registration loss of common features, a feature-matching network was constructed to extract the common features of undamaged detection data, and the performance was optimized by combining STN and GCNet modules. When the detection data of the sample were input to the aforementioned network, the defect distribution representing the location and rough shape of the defect was obtained through Mahalanobis distance calculation. The length was estimated using the S-scan image sequence sampling method. Additionally, the depth of the hole was estimated by combining the B-scan data with line recognition. According to the original model of the sample, the 3D characterization of defects was completed by pyautocad. In the experimental stage, three ablation experiments were carried out to verify the necessity of each module, and performance comparisons were mainly evaluated by F1 score and visualization using four existing well-known anomaly detection methods.

The rapid growth of the aviation industry highlights the need for strong safety management. Analyzing data on unsafe aviation events is crucial for preventing risks. This paper presents a new method that integrates the Transformer network model, clustering analysis, and feature network modeling to analyze Chinese text data on unsafe aviation events. Initially, the Transformer model is used to generate summaries of event texts, and the performance of three pre-trained Chinese models is evaluated and compared. Next, the Jieba tool is applied to segment both summarized and original texts to extract key features of unsafe events and prove the effectiveness of the pre-trained Transformer model in simplifying lengthy and redundant original texts. Then, cluster analysis based on text similarity categorizes the extracted features. By solving the correlation matrix of these features, this paper constructs a feature network for unsafe aviation events. The network’s global and individual metrics are calculated and then used to identify key feature nodes, which alert aviation professionals to focus more on the decision-making process for safety management. Based on the established network and these metrics, a data-driven hidden danger warning strategy is proposed and illustrated. Overall, the proposed method can effectively analyze Chinese texts of unsafe aviation events and provide a basis for improving aviation safety management.

In this paper, a novel UAV path planning algorithm based on improved cellular ant colony algorithm and dynamic window algorithm (ICACO-IDWA) is proposed to solve the problem of dynamically changing threat during actual flight. The main innovations of this paper are as follows. (a) The hexagon grid method is proposed to model the UAV flight space, which solves the problem of inconsistent simulation time step. (b) A novel ICACO-IDWA algorithm is proposed. In the first stage, the optimal path is obtained by the improved cellular ant colony algorithm (ICACO). In the second stage, the improved dynamic window algorithm (IDWA) is used to optimize the optimal path considering dynamic threat. Through the algorithm, the UAV path planning with dynamic threat change is realized. Finally, simulation results verify the effectiveness of the proposed model and algorithm.