中国科技核心期刊
中国指挥与控制学会会刊
军事装备类重点期刊
中国指挥与控制学会会刊
军事装备类重点期刊
中国指挥与控制学会会刊
军事装备类重点期刊
To address the challenge of designing and applying command and control architectures for operationally responsive space launches, the typical three-tier and four-tier architectures are studied. Based on entropy theory, a system entropy model for evaluating these architectures is constructed by integrating weighted timeliness entropy and quality entropy. The findings demonstrate that the three-tier architecture is superior when the weight coefficient of timeliness entropy (α) is less than or equal to 0.6, whereas the four-tier architecture proves more effective when α is greater than or equal to 0.67. Within the critical interval of 0.6 <α< 0.67, a threshold value u for the number of operational units (m) is identified: the three-tier architecture is preferable if m < u, and the four-tier architecture becomes optimal if m ≥ u. Furthermore, the threshold u decreases as α increases. Corresponding unit employment strategies, namely coupled utilization and streamlined utilization of combat units, are proposed for different launch modes and initial states of the launch vehicle. The models and conclusions can provide a theoretical foundation for decision-making in operationally responsive space launch command and control and its practical application.
To meet the route planning requirements of anti-ship strike missions of the aircraft, a multi-objective route planning model that incorporates safety threat, attack angle and range cost is constructed by analyzing the basic task process of air-to-sea strike actions and the main influencing factors, using geometric analysis methods. On this basis, an improved genetic algorithm based on fitness value calibration and similarity verification is proposed, which leads to the optimal route planning algorithm for air-to-sea strike operations, combined with the constructed mathematical model. Simulation results show that the designed model and algorithm can plan optimal two-dimensional routes for anti-ship strikes based on different mission information efficiently, which has solved the problems of global search, premature convergence, and late-stage oscillation found in traditional algorithms, while featuring low computational load, high accuracy, and strong practicality.
Cooperative game theory provides a systematic mathematical modeling tool for cross domain collaborative combat by studying the formation of alliances, distribution of benefits, and collaborative optimization mechanisms. This paper systematically explains cooperative game theory and proposes a military alliance game system framework, analyzes its application mechanism in scenarios such as joint firepower strikes, integrated air and missile defense, and network electromagnetic countermeasures, and reveals its optimization effect on multi domain collaborative efficiency. Further explore the technological challenges of incomplete information and security constraints in dynamic battlefield environments, and propose future research directions for the integration of dynamic game theory, robust optimization, and artificial intelligence. This theory is a key capability support for building an intelligent combat system and enhancing the combat effectiveness of cross domain systems, and has important military application value.
To address the optimization problem of task allocation for drone swarms, an improved hybrid DPSO-GA optimization algorithm is proposed. This approach constructs a complex mapping relationship for drone swarm task allocation under temporal constraints. It employs adaptive cosine adjustment for inertia weights and learning rates, while incorporating crossover and mutation operations to enhance the algorithm's global search capability, convergence speed, and accuracy toward extremes. Simulation comparisons with DPSO and GA algorithms reveal that the proposed algorithm achieves an average fitness value reduction of 50.0% and 10.7% compared to DPSO and GA respectively, with variance reductions of 95.7% and 79.9% compared to DPSO and GA respectively. The confidence interval widths were only 20.7% and 44.8% of those for DPSO and GA, demonstrating the algorithm's significant superiority in convergence, stability, and reliability over the comparison algorithms. This makes it a valuable reference for solving multi-objective task allocation problems in UAV swarms.
Focusing on the problem of kill chain dynamic reconfiguration, this paper first analyzes the phenomenon where the failure of combat units due to enemy attacks or system malfunctions leads to degradation or interruption of kill chain effectiveness. It proposes operational robustness evaluation metrics that include strike effectiveness and survivability. Next, a bi-level optimization model for local dynamic reconfiguration of the kill chain is established, taking into account the location and impact of failed nodes, with the optimization objectives of improving strike effectiveness and survivability. Finally, comparative experiments are conducted to compare the proposed operational robustness evaluation metrics with traditional ones. The results show that the proposed metrics exhibit faster convergence speed and can effectively accelerate the dynamic reconfiguration process of the kill chain.
To address uncertainties and multi-factor influences in combat capability evaluation of Armed Police Special Operations Units, this study establishes an assessment index system based on operational elements. By applying a game-theoretic combined weighting method to determine indicator weights and integrating grey-fuzzy modeling, we achieve effective fusion of qualitative and quantitative analysis. The proposed approach significantly improves the accuracy and reliability of evaluation outcomes, providing a scientific foundation for enhancing combat effectiveness development.
Aiming at the problem that the superiority function in situation assessment is difficult to quantify, objectively recorded bus data are used to the evaluation of counter air combat situation. Firstly, the advantage functions for both engaging parties concerning aspects such as attacks, angles and energy are constructed; a non-parametric-based model for evaluating air combat situations is established. Secondly, bus data are utilized for the computation of these advantage functions using method such as data fusion and coordinate transformation. Finally,through the situation analysis and assessment validation of actual counter air combat cases, the method of using bus data to evaluate counter air combat situation is verified to be correct,which has strong practical application value.
Knowledge graphs are used to analyze the threats faced by floating bridge ferrying sites under drone swarm raids. From the perspective of the criteria such as proximity, attack capability, and penetration capability, 11 indicators for the threat assessment of drone swarm raids are presented. The linear unascertained measurement function is adopted to determine the index values of the threat of drone swarm raids, and a threat level assessment model based on the analytic hierarchy process and the unascertained measurement theory is established to obtain the threat level of drone swarms to floating bridge ferrying sites. The results show that the model can effectively solve the problem that it is difficult to quantitatively analyze and judge threat indicators, and provides a scientific means for determining the security protection level of floating bridge ferrying sites during wartime.
Aiming at the problem of airspace configuration for cooperative anti-jamming in airborne formation situational awareness, this study is based on the real-time detection coverage area of a single platform. It simulates and analyzes the coverage degree of the airborne situational awareness platform over the responsibility area when subjected to jamming. Furthermore, to meet the requirements of both anti-jamming and full coverage of the responsibility area when protecting key targets, the basis for setting the station spacing of multiple platforms is investigated. This research can provide quantitative and operable decision support for the cooperative airspace configuration of air formations in complex electromagnetic environments.
This paper focuses on the task of motion deblurring in visible light images by improving and further lightening DeblurGAN, resulting in the model Faster-DeblurGAN. The model introduces FasterNet and ASFF modules into the generator network and incorporates optical flow consistency loss. While maintaining high deblurring performance, it significantly enhances the network's inference speed and reduces the model's parameter count. Experimental results indicate that the method outperforms the benchmark model DeblurGAN on the GoPro dataset, with PSNR and SSIM improving by 3.3% and 2.4%, respectively, and the parameter count is reduced by 52.9%. This not only improves performance but also effectively realizes the lightweight modification of the model. Additionally, it demonstrates better deblurring effects in terms of subjective visual quality, proving the effectiveness of the model's improvements.
To address the issue of trajectory interruptions caused by target occlusion and appearance similarity in multi-pedestrian tracking within complex scenes, this study proposes a robust tracking algorithm that integrates an improved YOLOv8 with DeepSORT. Methodologically, the detection network backbone is reconstructed using the InceptionNext Block to enhance feature representation capability, and the VoV-GSCSP module is employed to optimize multi-scale feature fusion. Additionally, the motion prediction model is improved by incorporating the NSA Kalman filter, and the AFLink algorithm is introduced to achieve cross-frame trajectory association. Experimental results demonstrate that the improved model achieves a 0.9 increase in MOTP and a 0.7 increase in HOTA on the MOT20 dataset, significantly enhancing localization accuracy and trajectory continuity in occlusion scenarios. This provides an effective technical solution for dense crowd tracking.
It is a complex system engineering to construct a visual combat experimental system by using the technologies of LLM and LVM, which can not only improve the intelligent analysis ability and visual function of the combat experimental system, but also reveal the emerging ability of the combat system, and improve the generalization ability and self-monitoring learning ability of the combat experimental system. Based on the analysis of the key technologies of the visual combat experiment system with large model technology, this paper constructs the overall framework of the combat experiment system, and uses large language model (LLM), large visual model (LVM) and multi-Agent system (MAS) to simulate the complex dynamic interaction process between combat entities and the environment, so as to display the combat experiment process and intelligently analyze the combat experiment results in various modes and visual forms.
As a cutting-edge technology, multimodal large models are gradually transforming the information-processing paradigm in the military intelligence domain. This paper delves into the applications of multimodal large models in the military intelligence field. It first traces the development trajectory of multimodal large models, elaborates on the technological improvement paths of multimodal data and network models. Subsequently, it analyzes the application scenarios of five typical multimodal large models in future combat and conducts an in-depth analysis in combination with actual military intelligence platforms. This research reveals that multimodal large models constitute a crucial algorithmic component in intelligent warfare. Given their immense application potential in the military field, multimodal large models offer novel ideas and methods for military intelligence applications, thereby contributing significantly to the enhancement of the level of military intelligence.
Modern warfare is characterized by a trend toward multi-domain integration and intelligent development, with cognitive operations becoming a key domain in the competition for “cognitive dominance.” However, the current application of intelligent auditory stimulation in cognitive domain warfare remains unsystematic and lacks precise intervention models. To address this issue, the present study develops a model of an intelligent auditory stimulation system based on neuroscience, cognitive psychology, artificial intelligence, and biosensing technology. The study adopts multimodal data collection and real-time analysis methods, dynamically adjusting auditory stimulation parameters by monitoring soldiers' physiological and cognitive states, with the aim of achieving emotional stabilization, enhanced attention, and stress relief. The results show that the system can optimize psychological regulation in combat settings and enhance soldiers' team coordination and psychological resilience, thereby improving operational sustainability. It provides feasible decision-making support for the state and enhances strategic initiative. Furthermore, its application not only expands the research path of cognitive warfare theory, but also offers a scientific basis for constructing a cognitive domain warfare model suited to China's national conditions.
Modern computer wargames have been widely valued and applied. However, the ideal assumption in wargame systems that the observation among friendly forces is completely shared is far from the reality, which limits the simulation of many real-world situations. Therefore, in order to solve the above problems, this paper proposed a wargaming system framework with incomplete observation, where seats are the participants, and the wargaming simulation process is sorted out, including the model library, simulation engine, observations distribution, and front-end deduction. Then, referring to and comparing with mature wargame systems, we elaborately designs the elements of the wargame system related to the incomplete observation, such as seat model, communicator operator, intelligence model, communication action and adjudication, as well as the generation process of the incomplete observation. Finally, a red-blue confrontation scenario with three seats versus four seats was designed to verify the feasibility and effectiveness of the wargaming system described in this paper.
A digital overall design framework for aerospace products testing has been developed using model-based systems engineering (MBSE) and the U.S. Department of Defense Architecture Framework (DoDAF). Using a typical aerospace product as a case study, the testing overall design was modeled, and the design's rationality was verified through logical simulation. The results demonstrate that digital overall design method ensures the consistency and accuracy of test element expression and transmission, significantly enhancing design efficiency.
Aiming at the typical training demands of commander training for joint operations teaching in military academies, such as mass joint operations knowledge inquiry, battle case traceability and re-pushing, combat scene cognition and blue army confrontation, four novel commander training modes are put forward from the perspective of top-level design which are the theoretical teaching oriented commander training mode with question answering, battle case study oriented commander training mode with extension, scenario teaching oriented commander training mode with cognition and countermeasure training oriented commander training mode with confrontation. Then the essential technologies such as military knowledge intelligent answering based on large language model, parallel battlefield and situational cognition, construction and analysis of military event evolutionary graph and blue army behavior tree modeling integrating online learning are analyzed in detail which support the four novel training modes. This study can provide methodological support and implementation reference for military academies to carry out commander training with certain characteristics of digital-intelligence integration.
The domain of construction-management involves numerous information systems, information equipment and information technology elements. However, the current information supervision capacity is relatively weak, which to some extent restricts the advancement of the digital transformation. It is urgent to carry out the construction of all-round information supervision capacity based on information systems. This article focuses on the demand to achieve full traceability of business processing and transparent information supervision. It sorts out the current existing problems in the construction process of information supervision system, proposes information supervision goals and specific implementation ideas, further presents the “Transparent Cube” information supervision system, and provides detailed descriptions from aspects such as system composition, supervision framework, and main technologies. Finally, a typical information supervision process is introduced in combination with the equipment business field.
Aiming at the complex problem of the demand forecast for aviation ammunition in the process of combat operations planning, a scientific and practical method of demand forecast for aviation ammunition was proposed. According to relevant factors influencing aviation ammunition demand during wartime, the demand prediction model for aviation ammunition based on task was constructed, under the condition of taking into account systematically using plan, support ability and consumption probability. And the determination methods of model parameters were provided.The calculation example shows that the model can calculate quickly aviation ammunition demand, and provide methodological guidance for support plans drafting of aviation ammunition.
In response to the current issues with the organization of wartime equipment maintenance forces, a force organization method based on mission clustering analysis and an improved NSGA-Ⅱ algorithm is proposed. Based on the mission clustering analysis results obtained from the maintenance task clustering model, a multi-objective optimization model for maintenance force grouping was established with the objectives of minimizing the total maintenance time and the standard deviation of personnel workload. For the solution method of this multi-objective optimization model, the elite retention strategy and crossover operator of the traditional NSGA-Ⅱ algorithm were optimized and improved. The improved NSGA-Ⅱ algorithm was verified through the ZDT test function in terms of its superiority in convergence and solution set distribution. Using the maintenance mission of a certain artillery group as an example, simulation experiments and model algorithm analysis were conducted, resulting in a set of relatively ideal maintenance force organization schemes. This provides methodological and technical support for decision-makers to select schemes based on battlefield requirements and preference differences.
In response to the issue of individual outliers in aircraft testing affecting the determination of results and equipment standardization,this paper analyzes the relevant practices of outlier handling,based on the essential characteristics and internal logic of complex experimental samples,establishes a statistical descriptive model for multivariate data and unrelated multivariate test results,decouping the comprehensive evaluation problem under multiple constraints,combining specific examples,a comparative analysis was conducted on the analysis and handling methods of outliers from the aspects of inspection schemes and historical information validity,provides a scheme for eliminating invalid samples that can utilize experimental information,and proposes suggestion for improving relevant standards and regulations and conducting in-depth research,it can provide reference for engineering applications of related systems.
In response to the rapidly changing trend of systematic development in the field of hypersonic in the United States. Though the method of public literature analysis, we systematically sorting out the development of hypersonic management, equipment, technology, research and production and experimental support systems in the United States. From a macro perspective, this study explores the development of the United States in the field of investment, technological focus and trend direction.These can provide useful references for research in the field of hypersonic.
