The traditional perception of main elements of "C4KISR/C4ISR" cannot represent relationships between computers, communications and the other 5 military elements. A recognition of C4KISR system is proposed from the perspectives of architecture and dynamic information flow, basic and multi-C4KISR architectures are constructed, the dynamic process of information flow is analyzed, and computer and communication efficiency and their impact on the system are focused on. "C4KISR" cannot be regarded as just a command & control system from the perspective of the entire architecture; it is necessary to enhance the synergy of all elements to enhance the efficiency of the system, otherwise weaknesses or blockades of the system may be formed. Above research has important reference for rational construction of "C4KISR".
The formation and obstacle avoidance control of multi-Agent systems, as an important research direction in the field of intelligent transportation, is widely applied in military and civilian environments due to its high practicality. The traditional periodic sampling update mechanism has limited effectiveness in handling non-ideal conditions and its high resource demand leads to significant system resource waste. To address this issue, this paper, using an autonomous surface vehicle model as a background, proposes a multi-Agent system formation consistency algorithm based on event-triggered control and the leader-follower method, incorporating a directed graph structure into the algorithm. Utilizing Lyapunov stability theory, this paper provides a rigorous mathematical proof of the stability of the proposed algorithm, demonstrating system stability while avoiding Zeno behavior. Furthermore, under the premise of maintaining formation consistency, this paper implements obstacle avoidance and collision avoidance functions using an improved artificial potential field method. Experimental results verify the significant advantages of the improved artificial potential field method in obstacle avoidance performance.
The formation movement of Autonomous Underwater Vehicle (AUV) clusters has significant application value in underwater missions. To achieve efficient collaboration and formation movement of AUV clusters in underwater mission scenarios, this paper proposes a method for AUV cluster formation movement based on directed communication constraints. This method utilizes the directed communication limitations between vehicles in real underwater environments through simulation to mimic communication conditions and employs a self-developed method to control the relative positions between follower vehicles and leader vehicles within the cluster. This approach thereby enables perception and communication between AUVs, adaptively adjusts formations, coordinates actions, and effectively responds to task requirements and environmental changes. This paper introduces the principles, design framework, and implementation process of the proposed method, and verifies its effectiveness through simulation and experimental results.
The emergence of unmanned surface vehicle(USV) attacks in the battlefields of Russia and Ukraine poses a significant threat to surface combat forces and critical coastal infrastructure, making it challenging to intercept by conventional countermeasures. In order to address the combat requirements in future warfare scenarios, the U.S.Department of Defense Architecture Framework(DoDAF) is adopted to model anti-USV swarm combat system architecture.A battlefield simulation software is used to test and evaluate the combat system, which verifies the effectiveness of the system. The research result can provide some reference for future studies on the application of anti-USV swarm combat.
Camouflaged targets detection in low-light environments is one of the challenges in the field of deception detection. Especially with the continuous advancement of camouflaged technology, targets are highly integrated with their environmental background. Poor lighting conditions can often lead to performance degradation in conventional single-modal detection algorithms. To address this issue, this paper proposes a feature-level fusion network guided by the object detection task. First, this paper designs a residual dense connection to extract and stack information from multiple dimensions, enhancing the prominence of the target within the original information to obtain fused features of camouflaged targets. Then, the fused features are fed into the YOLOv7 network for camouflaged target detection. By optimizing the loss function and integrating spatial-channel attention mechanisms, the detection performance of camouflaged targets under low-light conditions is effectively improved. Additionally, this paper constructs an optical-infrared camouflaged target dataset for low-light environments to validate the proposed method with empirical data. The dataset shows an mAP@0.5 of 87.38% and a precision (P) of 85.45%, indicating that the proposed algorithm has a detection advantage for camouflaged targets under low-light conditions.
According to the practical task of data construction and development, and the characteristics of data integration and application for “wide area multi-ability warfare”, a scheme of wireless intelligent transmission for large data in combat is proposed based on Mesh network technology, real-time transmission of various types of combat data to remote data processing platforms for visual operations and intelligent data storage and analysis, to provide command organizations at all levels, interactive and controllable “science and technology +”“network +” data integration using a new model.
In order to solve the problem of boosting cognitive MIMO radar for multiple moving target detection in cluttered backgrounds, this paper constructs a multi-target optimization model based on the dual mutual information criterion, takes into account the problem of linear variation of the motion target impulse response (TIR), estimates the TIR at the next moment by using Kalman filtering algorithm. Then the optimal frequency-domain waveforms by using the water-filling algorithm is adopted, and the time-domain waveforms of the cognitive MIMO radar by using the genetic algorithm is synthesized. With simulation verification, the algorithm can meet the needs of MIMO radar to observe multiple targets and realize the effective estimation of the impulse response of moving targets, which can improve the performance of multiple moving targets detection compared with the traditional fixed signal.
Aiming at the problem that the data of the whole system flight test is limited, the environmental factors and reduced algorithm have been introduced into the evaluations of the missile flight reliability in this paper, and the equivalent conversion method of multi-source reliability test data has been investigated. Primarily, the component test data has been converted into the whole missile data by applying equivalent conversion method; then, the ground test data has been converted into flight test data by applying Weibull distribution environmental factors; finally, the missile flight reliability has been evaluated by applying the converted data. The numerical examples have also been given to verify the validity and feasibility of the method, which effectively expand the number of evaluation samples, and improve the overall quality and efficiency of the test.
A large amount of textual information will be generated in the exercise training process, and enormous cognitive pressure will be exerted on training evaluators due to complexity and diversity of such information.How to fully extract unstructured data from exercise training documents and provide efficient services for analysis and evaluation personnel is a challenging issue in data processing. In this paper, we propose a deep learning-based event extraction technique for exercise training documents, which addresses the characteristics of abundant professional terminology, coexistence of Chinese and English, and dense key information in short sentences. By leveraging the powerful text feature extraction of ALBERT and the structured prediction of CRF sequence labeling, we construct an event extraction model for exercise training documents. Experimental results on the training data set demonstrate that this model performs well in text extraction and has practical applications for extracting information from exercise training documents.
In response to the issue that existing trajectory classification methods fail to fully consider the time series features and spatial structure features of trajectories, leading to a decline in classification accuracy, this paper proposes a trajectory hierarchical classification method based on deep learning networks. First, ship trajectories are transformed into image layers, and a trajectory image layer classification model based on the Swin-Transformer network is constructed. Next, for the trajectory sequence layer, a multi-dimensional information-based trajectory compression algorithm is utilized to optimize the input of trajectory sequences, and a trajectory sequence layer classification model based on the Gained-Transformer-Network deep learning network is developed. At last, a confidence-based fusion layer trajectory classification model is established to improve the accuracy of layered trajectory classification. Experimental validation shows an average classification accuracy of 90%, with the performance of the ensemble classifier improving by an average of 11% compared to other single classifiers, and an average F1 score of 0.82. The results indicate that the newly proposed method and the new ensemble classifier demonstrate good classification effectiveness for ship trajectories.
As the only high-speed navigation equipment in the ocean, the target recognition performance of the underwater high-speed vehicle determines the final completion effect of the mission. Due to the complexity of marine environment and the constantly upgrading of new countermeasure equipment, underwater high-speed vehicles are currently faced with the problem of insufficient recognition ability in complex marine environment, and it is urgent to find a new way of feature extraction and target recognition. Based on the good feature mining ability of deep convolutional networks and the characteristics of echo signals, a deep learning underwater target recognition model is proposed in this paper, and the model verification experiment is carried out by using test site data. At the same time, to solve the problem of insufficient training data, a generative adversarial networks is established to expand the data set. The experimental results show that the deep learning model proposed in this paper can effectively identify underwater targets, and the model recognition accuracy is improved by generating adversarial network data set expansion, which provides a new idea for the intelligent development of underwater high-speed vehicles.
In order to solve the problems of low accuracy of traditional sketch instruction recognition, a sketch instruction recognition technology based on convolutional neural network is proposed. By constructing and optimizing the convolutional neural network model, a large number of sketch instruction samples are used for training, and the accuracy of the validation set is closely monitored throughout the training process, and the learning rate is dynamically adjusted in real time and based on this. With L2 regularization and Dropout dual insurance strategies, overfitting is synergistically suppressed. L2 regularization constraint weight scale and Dropout randomly inactivated neurons complement each other, which can improve the accuracy of the model in recognizing different sketch instructions and improve the human-computer interaction experience.
The traditional model for calculating the destruction probability of anti-aircraft gun burst firing uses the method of calculating the average number of hits required for destruction, which obscures the differences in elements such as firing elements, projectile-target range, and hit conditions. With the demand for precise destruction, this model is no longer suitable. In this paper, a precise destruction probability calculation model is studied based on the collision and destruction mechanism of projectile-target engagement. Starting from the definition of a hit, a hit model based on the projection method of the projectile is established, and then the destruction probability upon hit is calculated based on the collision and destruction mechanism. With the aid of external ballistics, the burst firing process is simulated. Finally, the Monte Carlo method is used to calculate the average value of the simulation statistics. The simulation results show that the calculation method in this paper can more accurately reflect the actual destruction situation of the anti-aircraft gun weapon system against the target.
To meet the precise maintenance support requirements of rocket guns, a method for selecting fault repair strategies based on FMEA and fuzzy closeness is proposed. This approach enhances traditional FMEA by incorporating fuzzy theory to evaluate fault risk indicators, and establishes standard fault models corresponding to different repair strategies. The most suitable repair method is then determined by comparing the comprehensive closeness between the rocket gun faults and the standard fault models. The method's feasibility is demonstrated through a case study involving a rocket gun's fire control computer. The analysis reveals that this approach simplifies the evaluation process, delivers more reasonable and accurate results, and effectively meets the practical demands of rocket gun maintenance support.
This paper focuses on the deployment method and implementation of command and control software, and focuses on the rapid deployment of applications. Based on the practical testing of container technology's technical conditions and advantages, this paper analyzes the potential application prospects of container technology in charge software. It proposes a design concept for rapidly deploying charge software using containers, while also analyzing the shortcomings and defects of traditional deployment methods. Furthermore, it designs a logical architecture and summarizes key technologies that need to be addressed for rapid deployment and solving difficult problems. This provides valuable reference for further improving and upgrading the software.
The multi-agent system driven by large models has great potential in enhancing the level of artificial intelligence, providing innovative solutions for military intelligence. However, the degree of autonomy of current large model driven multi-agent systems in independently completing task objectives is greatly affected by task complexity, and the consistency between system processing results and initial objectives is poor. It is necessary to evaluate and analyze the autonomy and consistency of large model driven multi-agent systems. Previous studies have not yet comprehensively evaluated the autonomy and consistency levels of large model multi-agent systems. This article proposes a multidimensional evaluation method that can analyze and extract the autonomy and consistency of the overall architecture of multi-agent systems driven by large models, and obtain the overall performance evaluation results and specific improvement methods of the system. Through experimental analysis of 7 selected systems, the feasibility of multidimensional evaluation methods in practical applications has been verified.
Computer simulation is a crucial approach for advancing research in intelligent aerial combat. However, existing aerial combat simulators are often non-open-source, challenging to develop, poorly visualized, and difficult to integrate with advanced AI technologies. This paper introduces a 3D aerial combat simulation system based on NetLogo 3D and HubNet. The system constructs static models of terrain, aircraft, and missiles in NetLogo 3D, and encapsulates functions to implement dynamic behaviors such as aircraft maneuvers and missile attacks. The system not only supports expert algorithms but also integrates DDQN reinforcement learning algorithm via Python extensions, enabling intelligent agents to make maneuver and attack decisions. A C-S architecture is employed via HubNet to support various simulation scenarios, including human-human, human-machine, and machine-machine engagements. Experimental results validate the system's effectiveness and stability, highlighting its real-time visualization capabilities and rapid integration of AI algorithms.
With the global and multidimensional transformation of war forms and the rapid development of intelligent technology, cross domain collaborative intelligent systems have gradually become an important development direction to meet diverse mission requirements and improve mission efficiency. In response to the issue of ineffective implementation testing of cross domain collaborative intelligent systems, a study is conducted on the system composition and architecture design, system integration and information flow design and simulation testing process of the LVC simulation system for cross domain collaborative intelligent systems; The design of a multi granularity LVC simulation system that includes practical nodes, semi physical nodes, digital nodes and intelligent algorithm models is completed; Finally, simulation experiments are conducted based on specific scenarios, and the results show that the LVC system can effectively meet the multi granularity simulation test requirements of cross domain collaborative intelligent systems.
Focused on the simulation experimentation of joint operational plan based on operation and combat simulation system, in order to solve the problem of representing the unstructured operational plan text information to the structured data which can be analyzed and calculated by the system, this paper analyzes the content elements of the operational plan and its internal logic relations, and puts forward an abstract representation model based on task'line and a structured representation method based on ETGA, and constructs a structured data graph model based on semantic network. This paper provides a theoretical and methodological support for the conversion and input of operational plan and the efficient organization of structured data information.
Nuclear power stations are important pillars of the national nuclear system, whose defense security is an important guarantee for ensuring the safety and sustainable development of nuclear energy, providing support for national energy security. Based on the possible means of attack by war risk or terrorists, the realistic risks faced by nuclear power plants, such as violent terrorist activities, ultra-low altitude drone attacks, and cyber electronic attacks, are analyzed and the characteristics of various risks and threats are described. Three categories of detection and navigation, combat performance and destruction effect are distinguished, and 11 typical factors affecting risk generation are proposed. The logical relationship and mechanism of enemy "detection-fight-consequence" is analyzed, and the index evaluation system of influencing factors of nuclear power station attacked risk is constructed, which provides theoretical and methodological support for scientific measurement of the attack risk faced by nuclear power plants, targeted strengthening of nuclear power plant defense measures and optimization of emergency force application.