Equipment fault diagnosis NER is to extract specific entities from Chinese equipment fault diagnosis text, which is the premise of constructing an equipment fault diagnosis knowledge graph. Named entity recognition for equipment fault diagnosis can also provide important data support for equipment maintenance support. Equipment fault diagnosis text has complex semantics, fuzzy entity boundaries, and limited data size. In order to extract entities from the equipment fault diagnosis text, this paper presents an NER model for equipment fault diagnosis based on RoBERTa-wwm-ext and Deep Learning network integration. Firstly, this model uses the RoBERTa-wwm-ext to extract context-sensitive embeddings of text sequences. Secondly, the context feature information is obtained through the BiLSTM network. Thirdly, the CRF is combined to output the label sequence with a constraint relationship, improve the accuracy of sequence labeling task, and complete the entity recognition task. Finally, experiments and predictions are carried out on the constructed dataset. The results show that the model can effectively identify five types of equipment fault diagnosis entities and has higher evaluation indexes than the traditional model. Its precision, recall, and F1 value are 94.57%, 95.39%, and 94.98%, respectively. The case study proves that the model can accurately recognize the entity of the input text.

The widespread adoption of Unmanned Aerial Vehicles (UAVs) in civilian domains, such as airport security and critical infrastructure protection, has introduced significant safety risks that necessitate effective countermeasures. High-Energy Laser Systems (HELSs) offer a promising defensive solution; however, when confronting large-scale malicious UAV swarms, the Dynamic Resource Target Assignment (DRTA) problem becomes critical. To address the challenges of complex combinatorial optimization problems, a method combining precise physical models with multi-agent reinforcement learning (MARL) is proposed. Firstly, an environment-dependent HELS damage model was developed. This model integrates atmospheric transmission effects and thermal effects to precisely quantify the required irradiation time to achieve the desired damage effect on a target. This forms the foundation of the HELS–UAV–DRTA model, which employs a two-stage dynamic assignment structure designed to maximize the target priority and defense benefit. An innovative MADDPG-IA (I: intrinsic reward, and A: attention mechanism) algorithm is proposed to meet the MARL challenges in the HELS–UAV–DRTA problem: an attention mechanism compresses variable-length target states into fixed-size encodings, while a Random Network Distillation (RND)-based intrinsic reward module delivers dense rewards that alleviate the extreme reward sparsity. Large-scale scenario simulations (100 independent runs per scenario) involving 50 UAVs and 5 HELS across diverse environments demonstrate the method’s superiority, achieving mean damage rates of 99.65% ± 0.32% vs. 72.64% ± 3.21% (rural), 79.37% ± 2.15% vs. 51.29% ± 4.87% (desert), and 91.25% ± 1.78% vs. 67.38% ± 3.95% (coastal). The method autonomously evolved effective strategies such as delaying decision-making to await the optimal timing and cross-region coordination. The ablation and comparison experiments further confirm MADDPG-IA’s superior convergence, stability, and exploration capabilities. This work bridges the gap between complex mathematical and physical mechanisms and real-time collaborative decision optimization. It provides an innovative theoretical and methodological basis for public-security applications.

Visual navigation technology holds significant potential for applications involving unmanned aerial vehicles (UAVs). However, the inherent spectral limitations of optical-dependent navigation systems prove particularly inadequate for high-altitude long-endurance (HALE) UAV operations, as they are fundamentally constrained in maintaining reliable environment perception under conditions of fluctuating illumination and persistent cloud cover. To address this challenge, this paper introduces microwave vision to assist optical vision for environmental measurement and proposes a novel microwave vision-enhanced environmental perception method. In particular, the richness of perceived environmental information can be enhanced by SAR and optical image fusion processing in the case of sufficient light and clear weather. In order to simultaneously mitigate inherent SAR speckle noise and address existing fusion algorithms’ inadequate consideration of UAV navigation-specific environmental perception requirements, this paper designs a SAR Target-Augmented Fusion (STAF) algorithm based on the target detection of SAR images. On the basis of image preprocessing, this algorithm utilizes constant false alarm rate (CFAR) detection along with morphological operations to extract critical target information from SAR images. Subsequently, the intensity–hue–saturation (IHS) transform is employed to integrate this extracted information into the optical image. The experimental results show that the proposed microwave vision-enhanced environmental perception method effectively utilizes microwave vision to shape target information perception in the electromagnetic spectrum and enhance the information content of environmental measurement results. The unique information extracted by the STAF algorithm from SAR images can effectively enhance the optical images while retaining their main attributes. This method can effectively enhance the environmental measurement robustness and information acquisition ability of the visual navigation system.

L_q (0 < q ≤ 1) regularization has been confirmed effective when applied to sparse SAR imaging. However, the inaccuracies caused by motion errors in the observation model will lead to various degradations and defocus in the reconstructed image. For high-resolution and light-small SAR systems, the range-variant motion errors will decrease the accuracy of range cell migration correction (RCMC), and residual range cell migration (RCM) will exceed multiple range resolution cells and degrade the image quality substantially. Aiming at this problem, in this paper, a novel azimuth-range decoupled sparse SAR imaging method with coarse-to-fine range-variant motion errors and residual RCM correction method is proposed. First, a one-step motion compensation (MOCO) operator is proposed using the inertial navigation systems (INS)/global positioning systems (GPS) information, which can significantly reduce the residual RCM and improve the reconstruction accuracy. Second, a fine high-order phase-error correction method is performed to correct the range and cross-range-varying phase errors using a joint imaging and phase-error estimation scheme, which will further improve the image focusing quality. Experimental results indicate the effectiveness of the proposed method.

To address the dynamic target allocation and resource scheduling problems of multiple High-Energy Laser Systems (HELSs) in defending critical infrastructure against large-scale heterogeneous UAV swarm penetration, this paper proposes a soft–hard damage cooperative task allocation and optimization method, termed Attention-based Centralized Training and Decentralized Execution proximal policy optimization (Attn-CTDE-PPO), which integrates an attention mechanism with multi-agent reinforcement learning. First, a cooperative multi-agent sequential decision-making model for multi-HELS engagement against UAV swarms is constructed by considering continuous laser irradiation, system energy consumption, thermal accumulation limits, and soft–hard damage mechanisms. Second, a multi-head attention set encoder based on a Transformer is introduced to extract global situational features at the state level. This design enables the policy network to handle a time-varying number of targets and mitigates the explosion of hybrid action spaces. At the action level, a discrete–continuous dual-head network with a masking mechanism is proposed to achieve target allocation and laser-parameter scheduling. Furthermore, a multi-dimensional threat assessment module is developed, which can prune infeasible actions in the action space via physical rule-based masking, thereby accelerating the decision-making speed of the method. Monte Carlo simulation experiments verified the defense reliability, energy management efficiency and real-time responsiveness of the proposed method. The experimental results demonstrate that, in heterogeneous swarm scenarios with different numbers of UAVs, the proposed method effectively suppresses UAV penetration, improves the defense success rate, and reduces total system energy consumption compared with baseline algorithms.