As the core transmission and distribution carrier of the power system， the operating condition of high-voltage transmission lines directly impacts the safety of the power grid. To address the problems of low efficiency and high missed rate in traditional manual inspection， a lightweight method for transmission line defect detection based on a two-stage multi-modal attention mechanism and dynamic feature decoupling was proposed. In the first stage， accurate localization of key components was achieved on the basis of an improved lightweight detection network， Light-YOLO. In the second stage， a dual-branch contrastive learning-based defect detection network， Dual-DifferNet， was built to achieve precise classification and identification of defects. In the design of Light-YOLO， a hybrid structure of hierarchical Separable Vision Transformer （SepViT） and deep Deformable Convolutional Network （DCN） was introduced， and by stacking local perception convolutional layers and global attention Transformer blocks alternately， the model’s modeling capability of long-range dependencies was enhanced while reducing computational cost， thereby improving the detection accuracy of small targets such as insulators and conductor splices effectively. For the defect classification task， in Dual-DifferNet， a dual-branch structure was adopted to embed a Spatial-Channel Dual Attention （SCDA） module in each branch， and the dual-modal feature interaction was promoted using a cross attention mechanism， thereby improving the robustness and generalization capability of defect identification. Experimental results show that the proposed method achieves a mean Average Precision （mAP@50） of 96.9%， which is 16.1 percentage points higher than that of the baseline model YOLOv8， with the floating-point operations reduced by 56.73%， fully verifying the method’s high detection accuracy， excellent computational efficiency， and deployment potential.

Aiming at the problem that the universal perturbation search in HGAA （Hyperspherical General Adversarial Attacks） algorithm is always limited to the spatial spherical surface， and it does not have the ability to search the space inside the sphere， a differential evolution algorithm based on hypersphere was proposed. In the algorithm， the search space was expanded to the interior of the sphere， and Differential Evolution （DE） algorithm was used to search the optimal sphere， so as to generate universal perturbations with higher fooling rate and lower modulus length on this sphere. Besides， the influence of key parameters such as the number of populations on the algorithm was analyzed， and the performance of the universal perturbations generated by the algorithm on different neural network models was tested. The algorithm was verified on CIFAR10 and SVHN image classification datasets， and the fooling rate of the algorithm was increased by up to 11.8 percentage points compared with that of HGAA algorithm. Experimental results show that this algorithm extends the universal perturbation search space of the HGAA algorithm， reduces the modulus length of universal perturbation， and improves the fooling rate of universal perturbations.

Adversarial attacks add designed perturbations to the input samples of neural network models to make them output wrong results with high confidence. The research on adversarial attacks mainly aim at the application scenarios of a single model， and the attacks on multiple models are mainly realized through cross-model transfer attacks， but there are few studies on universal cross-model attack methods. By analyzing the geometric relationship of multi-model attack perturbations， the orthogonality of the adversarial directions of different models and the orthogonality of the adversarial direction and the decision boundary of a single model were clarified， and the universal cross-model attack algorithm and corresponding optimization strategy were designed accordingly. On CIFAR10， SVHN datasets and six common neural network models， the proposed algorithm was verified by multi-angle cross-model adversarial attacks. Experimental results show that the attack success rate of the algorithm in a given experimental scenario is 1.0， and the L2-norm is not greater than 0.9. Compared with the cross-model transfer attack， the proposed algorithm has the average attack success rate on the six models increased by up to 57% and has better universality.

In order to improve the maneuver decision ability of fighters under the condition of insufficient information， a method of aircraft air combat maneuver decision based on three-way decision was proposed. Firstly， the three-way decision intention recognition model was used to recognize the target intention. Secondly， after introducing the combat intention factor of the target into the threat assessment， a dynamic adjustment method of maneuver decision weight factor based on three-way decision was proposed with the combination of the target threat degree. Finally， the evaluation function of maneuver decision factor was constructed by using fuzzy logic， and the optimal maneuver mode of aircraft at each stage was obtained by using the dynamic adjustment strategy of weight and maneuver decision evaluation function， thus forming the effective and feasible flight route. Simulation results show that the proposed aircraft air combat maneuver decision method based on three-way decision is feasible and effective.

Focusing on the issues that the traditional image caption models cannot make full use of image information， and have only single method of fusing features， an image caption generation model with Adaptive Commonsense Gate （ACG） was proposed. Firstly， VC R-CNN （Visual Commonsense Region-based Convolutional Neural Network） was used to extract visual commonsense features and input commonsense feature layer into Transformer encoder. Then， ACG was designed in each layer of encoder to perform adaptive fusion operation on visual commonsense features and encoding features. Finally， the encoding features fused with commonsense information were fed into Transformer decoder to complete the training. Training and testing were carried out on MSCOCO dataset. The results show that the proposed model reaches 39.2， 129.6 and 22.7 respectively on the evaluation indicators BLEU （BiLingual Evaluation Understudy）-4， CIDEr （Consensus-based Image Description Evaluation） and SPICE （Semantic Propositional Image Caption Evaluation）， which are improved by 3.2%，2.9% and 2.3% respectively compared with those of the POS-SCAN （Part-Of-Speech Stacked Cross Attention Network） model. It can be seen that the proposed model significantly outperforms Transformer models using single salient region feature and can describe the image content accurately.

The judgment of reachability is one of the fundamental issues in Petri net analysis. The paper analyzed the existing method and the method based on constraint programming for the reachability of Petri net, and then proposed the judgment method for reachability problem based on constraint optimization. The method was based on the state equation method, separately using the constraint programming and the optimization to seek the feasible solution and the optimal solution, thereby decreased the searching path and attained the purpose of reducing the solution space of the state equation. Finally an example was given to prove that the algorithm can improve the determination efficiency.

Most of Support Vector Data Description (SVDD) methods have blindness and bias issues when working on two-class problems. The authors proposed a new SVDD method based on information entropy. In this algorithm, firstly, the entropy values were resolved respectively of the two classes of samples. Secondly, according to the size of the value, one class was placed inside the ball. Finally, the penalty was given based on the information provided by the sizes of the two sample data and their entropy values. The efficiency of this algorithm was verified by using artificial data and UCI datasets for the data imbalanced classification problem. The experimental results on artificial data sets and UCI data sets show the feasibility and effectiveness of the proposed method.