News
加载中...
Quick Entry
Author
Expert
Editorial Office
Quick Icon
Online First
- 摘要：Military targets in reconnaissance and remote sensing are characterized by small sizes, dense distributions, complex backgrounds, and significant scale variations, while limited computing resources ofunmanned aerial vehicle(UAV)platforms hinder achieving both high accuracy and real-time performance. This paper proposes a multi-channel lightweight detection algorithm for such scenarios. A grayscale auxiliary channel is introduced to construct ared green blue gray(RGB-Gray)four-channel input, enhancing fine-grained texture and edge feature extraction. High-resolution P2 is enabled and low-resolution P5 is pruned to reduce model complexity. Agated-based adaptive lightweight dual-branch cross stage partial bottleneck with 2 convolutions(Conditional-C3k2)module with dynamic gating is designed for adaptive feature fusion, and alightweight cross-stage aggregation structure is adopted to improve multi-scale integration efficiency. Anenhanced dynamic headand avarifocal-SIoU-area-weighted loss(VSA-Loss)function with an area-weighted mechanism optimize performance. GCSD-YOLOv11n improves Mean Average Precisionby 13.0% and 7.4% on VisDrone2019 andmilitary vehicle remote sensing dataset (MVRSD), respectively, with MVRSD accuracy reaching 86.4% and parameters reducing by 29.4%. Strong generalization on the MAR20 dataset verifies robustness in complex military imaging, providing an effective solution for real-time airborne reconnaissance tasks.
0
0
0
- 摘要：With the growing complexity of combat environments and the constantemergence of new time-sensitive targets, modern battlefields demand enhanced multi-purpose and comprehensive damage capabilities from warheads.The formation characteristics of axial shaped-charge/fragmentation composite damage elementswereinvestigatedusing an EFP(Explosively Formed Penetrator)/preformed fragment composite warhead to address multi-target engagement requirements. The effects of various warhead structural parameters on EFP formation and fragment dispersion were analyzed and validated through static detonation tests. Results indicate that liner parameters (cone angleα, thicknessδ) primarily influence EFP formation and fragment dispersion angle, with limited effect on fragment velocity (<50 m/s variation). Baffle ring angleφand casing thicknessTmainly affect fragment dispersion, causing velocity changes exceeding 200 m/s and dispersion angle variations up to 200%, while negligibly impacting EFP formation. The number of initiation pointsNsignificantly affects EFP performance, increasing head velocity by over300m/s and aspect ratio by approximately 30%, but has minimal effecton fragment velocity and only moderately influences dispersion angle. For axial EFP/preformed fragment composites, EFP exhibits high independence and is mainly governed by liner structure and initiation mode. In contrast, fragment dispersion involves complex interactions,collisions and energy exchange between tungsten spheres,requiring coupled design. Verified tests confirm that the composite warhead generates a high-speed projectile(1950m/s) along the axis and a tungsten sphere array with a dispersion velocity of700–830 m/s within a 0.543°–7.48° spread, capable of penetrating an 8 mm steel plate at 5 m.The results of this study provide valuable
5
1
0
- 摘要：Traditional gunpowder launching for unmanned aerial vehicle (UAV) clusters faced three problems: high cost, heavy pollution, and pyrotechnic control difficulties. To address these, we proposed a hydrogen-propelled gun-launched UAV technology. Experimental verification confirmed its feasibility.We compared compressibility factors of various real gas equations under specific temperature and pressure. The Peng-Robinson equation is more accurate in describing the real gas thermodynamic characteristics of hydrogen gun-launched UAV systems.An internal ballistic model incorporating real gas effects was constructed. This model analyzed nitrogen content's impact on launch performance at constant initial pressure and fuel ratios. Replacing pure oxygen with air as oxidizer was proposed. This optimization significantly improved internal ballistic performance while enhancing cost-effectiveness. A binary function model for control valve nozzle area variation was established. This effectively reduced maximum launch velocity overload during UAV ejection. These results provide key technical support for optimizing hydrogen gun-launched UAV systems and advancing cluster warfare applications.
4
2
0
- 摘要：Spatio-temporal prediction of multi-targetsis keyto target evolution and decision-making in dynamic scenarios.Traditional static methods struggle to capture the dynamic spatiotemporal evolution of multiple objectives in dynamic environments. While neural networks based on stochastic differential equations are well-suited for dynamic systems, they still have limitations when it comes to modeling spatiotemporal correlations among multiple objectives.Therefore, this paper proposes a dynamic multi-targetspatio-temporal prediction algorithm based on the improved neuralordinarydifferential equation network. Itestablishes adynamicmulti-targetspatio-temporal prediction architecture by combining neuralordinarydifferential equations and sparse graph convolutional network. Firstly, the sparse graph convolutional network is used to extract the sparse spatio-temporal interaction features between multi-targets from historical observation trajectories to achieve the modelling of multi-target spatio-temporal correlations; then the flexible and efficient temporal modelling capability of theneural ordinarydifferential equations is used to carry out the temporal modelling of the high-dimensional hidden state of the targets, and finally, the spatio-temporal prediction trajectories of the multipletargetsare obtained. Experiments show that the average displacement error (ADE) and final displacement error (FDE) of thismodelon the ETH/UCY dataset are0.36and0.56, which are decreased by 3% and 10%, respectively,compared withtheordinary differential equationsnetwork model, resulting in higher prediction accuracy.
6
1
0
Introduction
Editor in Chief: MAO Ming
Edited and Published by:
Editorial Board of Acta Armamentarii
ISSN：1000-1093
CN：11-2176/TJ
phone：010-68963060/68962718
Email：bgxb@cos.org.cn
ranking list 
更多
- 0 1 Review and Prospect of Missile Plasma Synthetic Jet Control Technology 2298
- 0 2 Research and Comparison of Protection Rating in Domestic and Foreign Bulletproof Standards 2200
- 0 3 Maritime Manned/unmanned Collaborative Systems and Key Technologies: A Survey 2168
- 0 4 An Overview of Research on Military Unmanned Ground Vehicles 1890
- 0 5 Research on Improved YOLOv5-based Military Target Recognition Algorithm Used in Complex Battlefield Environment 1594
- 0 6 Multi-target Assignment and Intelligent Decision Based on Reinforcement Learning 1571
- 0 7 A Review on the Research of Lateral Control for Intelligent Vehicles 1466
- 0 8 Experimental Investigation of Ground Reflected Overpressure of Shock Wave in Air Blast 1347
- 0 9 Improved YOLOv3 Algorithm and Its Application in Military Target Detection 1307
- 10 Multi-Dimensional Decision-Making for UAV Air Combat Based on Hierarchical Reinforcement Learning 1280
- 11 Review and Prospect of Life Extension Technology for Gun Barrels 1239
- 12 Constitutive Relation and Fracture Criterion of 2A12 Aluminum Alloy 1237
- 13 Research on Interior Ballistics Stability of Small-caliber Recoilless Gun with High Muzzle Velocity of Projectile 1220
- 14 Knowledge Reasoning-based Intelligent Design Method of Kill-web 1212
- 15 A Review on Cooperative Motion Planning of Unmanned Vehicles 1155
- 16 Numerical Simulation of the Penetration of M855A1 EPR into Steel Targets 1146
- 17 Importance Evaluation of Kill Network Nodes Based on OODA Loop 1116
- 18 Modeling and Optimization Method of Kill Chains Based on AGE-MOEA 1098
- 19 Research Progress in Synthesis of Hexanitrohexaazaisowurtzitane2*3/4〗PANG Si-pingSHEN Fan-fanLYU PENG-haoDONG KaiZHANG Yi-yingSUN Cheng-huiSONG Jian-weiZHAO Xin-qi (725)Research NotesScale Model and Model Experiment of Electromagnetic Coil Launcher 1086
- 20 Research on Dispersion Characteristics of Scholte Wave in Shallow Sea 1082
查看更多
- Latest Articles
- Online First
- Archive
2026年第47卷第4期
- 摘要：The expansion diameter and change rate of fuel cloud resulting from the dispersal of cloud explosive agents are crucial in determining the detonation power of fuel-air explosives. Based on the opensource computational fluid dynamics platform OpenFOAM, a compressible two-phase flow VOF-DPM dynamic mesh solver is developed to achieve the efficient numerical simulation of fuel dispersion process. The numerical results are validated by experimental data. Then the influences of the aspect ratio and specific loading parameters of cloud explosive device on the kinetic characteristics of fuel dispersion are studied. The research shows that the dispersion process of cloud explosive agents can be divided into three stages, following a pattern of accelerating first and then decelerating. A larger aspect ratio increases the initial dispersion rate of the fuel. When the aspect ratio reaches 3, the final expansion diameter is 7.2 meters. The specific loading parameter significantly affects the initial expansion rate, but has a limited effect on the final stable size of the cloud. This paper establishes a multi-physical-field coupling model for shockwave-driven fuel dispersal, providing a theoretical basis and a numerical simulation method for optimizing the structural design of cloud explosive devices.关键词：fuel air explosive;explosive dispersion;volume of fluid method;discrete phase model184|65|0更新时间：2025-12-25
- 摘要：In order to address the problem of low computational real-time performance in the damage assessment of armored vehicle targets struck by high explosive munitions, a parametric target structural model is constructed. The structural model can be used to significantly improve the efficiency of intersection computations in conjunction with a stage-wise shotline intersection calculation algorithm. An evaluation toolkit (ETK) is designed and implemented, providing interfaces for geometric structure modeling, damage level and damage tree modeling, damage criteria modeling, high explosive munition lethality field modeling, and shotline intersection calculation. A high explosive munition damage assessment system with hierarchical and modular architecture for typical armored vehicle targets is developed by parametrically defining the structural elements and their combinations based on ETK. Case studies verify that the damage assessment system is capable of completing a single damage assessment calculation within seconds, providing effective support for the protection design of armored vehicles and the formulation of firepower strike plans. The proposed architectural design approach may offer valuable reference for the implementation of similar systems.关键词：blast-fragmentation warhead;armored vehicle;damage assessment;parametric modeling;software tool365|38|0更新时间：2025-12-25
- 摘要：Aiming at the problems of low efficiency and poor accuracy of manual data collection in shooting range, an automatic target detection technology based on image recognition is proposed to replace the traditional manual statistical method of fragment distribution. The target holes have characteristics such as diverse shapes, dense distribution, and complex background, and are further influenced by the rust and weathering of target plate, which limits the accuracy of edge contour segmentation. Therefore, this paper proposes a target plate fragment perforation segmentation model (YOLOv8-Target plate Fragment perforation Segmentation, YOLOv8-TFS) .Based on YOLOv8 model, a micro-target hole detection layer is added to enhance the model's ability to extract the features of different-sized target holes. The feature fusion network structure of cross-stage connections is optimized, and a dual-path adaptive feature weighting feature fusion module is introduced to strengthen the feature expression and suppress the background noise. A multi-path receptive field attention segmentation head is designed to improve the model's ability to integrate and output the target hole features. Experimental results show that the mask precision, recall rate, and mAP@0.5% of YOLOv8-TFS model on the self-made dataset reach 85.2%, 74.3%, and 73.8%, respectively, which are 11.6%, 10.9%, and 9.0% higher than those of the original model, effectively improving the accuracy of target hole segmentation. The automatic target detection system constructed based on the segmentation results accurately calculates the area and centroid coordinates of the target holes through spatial moment calculation and coordinate transformation. Compared with manual target detection, the average absolute deviation in quantity is 1.07, and the area deviation is controlled within 5%.This verifies the reliability and high-precision characteristics of the target detection method, and providing efficient technical support for the assessment of warhead damage effectiveness.关键词：warhead design;YOLOv8n-seg model;instance segmentation;perforation edge segmentation;automatic target detection system131|17|0更新时间：2026-01-27
- 摘要：To investigate the influence of cavity defects in large-diameter casting explosive on detonation waves and jets, using simulation software to analyze the charge melt-casting process and jet formation. The casting process of a large-diameter shaped charge is simulated. It is found that, when the pouring nozzle is not offset, the defects are primarily concentrated in the upper portion of the charge and at its conical angle:large-sized shrinkage cavities and honeycomb-like shrinkage porosity in the upper portion, and clusters of small-sized cavities at the conical angle. When the pouring nozzle is offset, the defect locations in the upper portion are shifted laterally. Based on the identified defect locations from the aforementioned research, the effects of porosity defects on detonation wave and jet are systematically analyzed. The research results indicate that the detonation wave can traverse the defect without being significantly impacted when pore size is smaller than the width of reaction zone. The pressure peak of detonation wave increases with the incrase in pore size near small and medium-sized cavities. The large-sized cavities induce secondary peaks in the detonation wave. Further simulation study on the randomly distributed cavities reveals that, as the void fraction increases, the jet head velocity rises while the jet tail velocity decreases, and the fracture time of the shaped charge jet advances. For every 0.25% difference in void fraction on the left and right sides of the charge, the deflection angle of jet increases by approximately 0.2° to 0.5°.关键词：shaped charge;large-diameter;casting explosive;cavity defect117|20|0更新时间：2025-12-25
查看更多
- Postal code：100089
- Tel：010-68963060/68962718 Fax：010-68963025 Email：bgxb@cos.org.cn
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05059581号-4
京公网安备11010802024360号 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：130236 Visits Today：710
0