This paper investigates an optimal cooperative guidance strategy for the active defense of an early-warning aircraft (EWA) escorted by two fighters against an incoming missile. The proposed framework extends classical three-body defense models (Target–Missile–Interceptor) into a more realistic four-body engagement (Target–Missile–Interceptor 1–Interceptor 2), allowing explicit coordination among multiple defenders. By projecting the 3D engagement kinematics onto two orthogonal 2D planes—a validated simplification for typical aerial combat geometries—a tractable dynamic model is obtained. Within this model, an analytical cooperative guidance law is derived using optimal control theory and the calculus of variations, minimizing a multi-objective cost function that combines miss distance, control effort, intercept geometry, and coordination terms. Extensive Monte Carlo simulations across 23 attack directions and multiple initial ranges demonstrate that the proposed method achieves an interception success rate of 99%, with an average miss distance of below 5 m. Robustness tests further confirm stable performance under target maneuver uncertainty, sensor noise, and modeling deviations. The algorithm features closed-form control commands with low computational complexity, enabling real-time onboard implementation.

The precise selection of key flight parameters is fundamental to enhancing aircraft condition monitoring and risk warning capabilities. However, existing methods typically rely on a single source of information, i.e., either solely expert judgments or solely objective flight data, and lack effective mechanisms to reconcile conflicts between subjective opinions and objective data characteristics, which limits their applicability in complex aviation safety scenarios. To address this issue, a flight parameter selection method based on dual-domain rough sets and three-way decision theory is proposed in this paper. First, regret theory is introduced to quantify experts’ psychological preferences, and a subjective evaluation model integrating both psychological and absolute agreement is constructed. Second, a subjective–objective conflict information system is established within a dual-domain framework. Based on this system, bidirectional decision rules are designed to simultaneously consider positive-domain and negative-domain conditional probabilities, through which candidate sets of key flight parameters are generated. Finally, a new Bayesian minimum loss criterion is designed to determine the optimal parameter set. Experimental results demonstrate that the accuracy and robustness of flight parameter selection are improved by the proposed method while interpretability is maintained, offering reliable decision support for aviation safety analysis.

Coordinated swarms of low-cost commercial unmanned aerial vehicles (UAVs) pose a growing security threat to civil infrastructure, public events, and restricted airspace. Effective counter-UAV defense requires the real-time, cooperative scheduling of heterogeneous directed-energy systems, where high-energy lasers provide precise single-target engagement and high-power microwaves provide wide-area suppression. To address this threat, we formulate the defensive scheduling problem as a partially observable Markov game and propose the Heterogeneous Dual-Graph Multi-Agent Actor–Critic (HDG-MAAC). HDG-MAAC employs two graphs: a fixed-size local graph encoded by a graph attention network (GAT) actor for decentralized threat selection and a shared global graph with three semantic edge types encoded by a graph convolutional network (GCN) critic for stable credit assignment. This asymmetric design is tailored to decision-making and evaluation, respectively. In a two-system, four-target simulation benchmark with direct, zig-zag, and feint maneuver patterns, HDG-MAAC converges stably across eight seeds, with a final-stage return of $33.6\pm 4.0$, and neutralizes $2.79\pm 0.26$ targets over 1000 deterministic episodes, outperforming DDPG (2.20), MADDPG (2.13), and H2G-MAAC (1.64) with $p<0.01$. In analytically tractable geometric scenarios, the rule-based scheduler with exact geometric pointing still yields more raw interceptions. The learning method’s contribution is therefore limited to training stability, interpretability, and applicability beyond such scenarios, rather than the raw interception count. Ablation studies indicate that this robustness originates from the GCN critic, whose contribution lies in training stability rather than in raising the final performance ceiling. An attention analysis yields an overall target association rate of 42.0%, with 47.7% and 47.1% for direct and zig-zag maneuvers, respectively, compared to a 25% chance baseline, as well as a drop to 27.1% under feints. Without an explicit coordination reward, coordinated target convergence emerges in 34% of firing frames. HDG-MAAC provides a stable and interpretable decision support framework for civil security operators safeguarding public infrastructure from rogue drone groups. The framework is intended solely for protective civilian use, with responsible use considerations.

Composite materials are critical components in advanced equipment such as aerospace, however, delamination defects that readily arise during manufacturing and in service present serious risks to equipment safety. Terahertz non-destructive testing is highly effective for analyzing the internal structure of composite materials, making it an effective approach for precise identification of delamination defects. Current terahertz detection approaches mainly depend on single domain features, making it difficult to capture complementary information from both the time and frequency domains. To address this, a Time-Frequency Feature-fusion Network (TFFN) is proposed. In this network, a three-branch architecture is employed: local transient patterns and pulse-related structural features are extracted by the local time-frequency branch; damage-sensitive frequency bands are focused on by the frequency-domain branch through a channel-space-frequency band attention mechanism; and deep integration of time-frequency features is achieved by the time-frequency fusion branch using Manifold Mixup. Finally, the features extracted from the three branches are adaptively fused via a cross-branch attention mechanism, and defect identification is accomplished by the classifier. Experimental results show that this method achieves accuracies of 98.40% on the glass fiber reinforced polymer (GFRP) dataset and 98.63% on the quartz fiber reinforced polymer (QFRP) dataset, surpassing the best existing method by 2% and 1.25%, respectively. A substantial improvement in both defect identification accuracy and the model’s generalization ability for layered structures is thereby achieved.