Currently, unmanned intelligence is widely used in various fields, and unmanned automatic perception and monitoring related technologies are rapidly developing, opening up a new perspective for military reconnaissance and civilian monitoring. Starting from the perspective of sensor application, this article presents the current research achievements of motion target detection based on unmanned aerial vehicle (UAV) payloads, and discusses the trends of future technological development. Firstly, a common method for UAVs target detection is outlined. Then, the progress of UAVs in infrared, optical, and video synthetic aperture radar (SAR) target detection is highlighted, and the advantages and limitations of related technologies were revealed. Finally, future research directions such as developing cross-modal object detection technology, constructing intelligent detection systems, and enhancing the capability of super large models and so on are discussed, which are expected to provide reference and guidance for subsequent research.

In response to the unclear explanation of the constituent elements and mapping relationships in the description of unmanned combat concepts, as well as the lack of structured and systematic description theory methods, a systematic description method for unmanned combat concepts based on the Department of Defense Architecture Framework (DoDAF) is proposed, which systematically explains the constituent elements of unmanned combat concept and the mapping relationships between constituent elements, building a conceptual architecture framework for unmanned combat targeting a certain capture and control operation relies on this method. The decomposition modeling method based on typical elements provide reference for the development and deduction verification of combat concepts, mining of combat capability requirements, and design of combat systems.

This paper aims to construct a multi-dimensional disturbance model of the marine environment to simulate the constraints of underwater weak communication scenarios and verify the feasibility of AUV (autonomous underwater vehicle) swarm formation control strategies in complex marine environments and adjustment to the AUV’s posture. These differences are then used to test the formation control performance of five types of controllers and their ability to handle AUV pose variations within the disturbance model. Compared with traditional methods, the simulation results demonstrate that the proposed method can achieve AUV swarm formation navigation under communication delay conditions. It shows significant advantages in formation convergence and safe arrival compared to single-constraint and other controller strategies. The proposed method is particularly suitable for swarm navigation under delayed communication and multiple disturbance constraints, offering substantial application potential in deep space and deep sea exploration. It provides a possible command and control method for future AUV deep-sea exploration.

Aiming at the contradiction between fineness, dynamics and planning real-time when planning ground unmanned equipment paths in dynamic and complex environments, a ground unmanned equipment path planning algorithm based on risk fusion cost map and adaptive PRM is proposed. Firstly, the risk fusion cost map is established based on the multi-factor environment scene, the scene adaptive PRM probabilistic road map is constructed through the mechanisms of Gaussian convolution adaptive sampling, nonlinear probability enhancement and secondary sampling strategy, and the local planner is utilized to dynamically update the weights of the probabilistic road map, so as to realize the optimized search of global low-risk cost paths. Simulation results show that the method can better realize the balance of fineness, dynamics and real-time planning in dynamic and complex environments.

Aiming at the problem of how to make intelligent cooperative decision according to the real-time situation in the land penetration operation of multi-vehicle, combined with the process of multi-agent unmanned vehicle penetration operation, Markov (MDP) model is established,and based on the multi-agent depth deterministic strategy gradient algorithm, the decision method of multi-unmanned vehicle collaborative penetration is proposed. In order to solve the problem of mutual influence of multi-agent decision-making agents’ policy changes, an attention mechanism is introduced in AC structure of the algorithm to make each agent pay more attention to those agents that have greater influence on the decision-making and policy evaluation. And the self-attention mechanism is used to calculate the reward weight of each agent, the reward distribution is carried out according to the contribution of each agent, which improves the cooperation of the war shop. Finally, the effectiveness and superiority of the multi-vehicle collaborative penetration decision-making method are verified by experiments in a given environment.

Complex adaptive systems for a wide range of applications in research plays an important role in the study of military issues. On the basis of the analysis of the complex adaptive characteristics of military problems, the CAS theory modelling approach applied to military systems is summarised, analysing the current state of application of CAS theory in the study of military problems from three perspectives: operational problems, equipment maintenance and repair, and other military problems. Finally, a summary of the shortcomings and an analysis of the future development of CAS theory in military systems.

This paper first constructs a simple valley combat model and a plain combat model, and calculates the battle time and casualties of both. Then, two scenarios are compared and analyzed, and the concept of "firefight line" is proposed. It is pointed out that "concentrating forces" to form local advantage is necessary, but simply "concentrating forces" is not enough. It is also necessary to extend your own firefight line to fully unleash combat energy, or shorten the opponent’s firefight line to suppress the release of their combat energy. Finally, seven strategies of utilizing the firefight line are proposed, including extending own firefight line, establishing multiple firefight lines, establishing an arc-shaped firefight line, establishing a wedge-shaped firefight line, compressing the opponent’s firefight line, cutting the opponent’s firefight line, and suppressing the opponent’s firefight line, etc. These strategies are supported by specific tactical ideas and combat scenarios.

As an important part of the weapon system, the fire control system is the key to whether the weapon can destroy the target when performing the combat mission. The precise distribution of each subsystem of fire control is the premise of fire control system design. Based on the air-to-surface laser-guided weapons, this paper analyzes the composition and error causes of the airborne fire control system, and analyzes, calculates and models the key parameters from the two aspects of the probability of interception of the middle guidance and the probability of the hit of the terminal guidance according to the General Requirements for Error Analysis of the Fire Control System of Airborne Weapons of HB 6518. At the same time, the Monte Carlo method is used to simulate the model. The experimental results show that the model models the tactical indicators of low-speed targets with a CEP of 2 m, a long-range attack distance of 10 km, and a ground attack of less than 10 m/s.

This paper proposes an element-matching based order-based accusation partition tasking method. The aim is to improve the flexibility and precision of operational command and control and the integration and synergy effectiveness of the combat system. The method is based on the construction of an integrated framework. This integrates and coordinates operational tasks, ensures no resource conflicts, and provides alternatives for responding to battlefield variables. The approach employs a planning network model to illustrate the logical interrelationships among operations. It then utilizes mission adaptive analysis and a two-phase process optimization to achieve the optimal matching of the aggregation of underlying operations to sub-tasks and accusation sites. In particular, the mechanism considers the multi-level attributes of the mission, including hierarchical, logical, temporal, spatial, and functional relationships, as well as the matching rules between the core baseline elements and the auxiliary reference elements, in order to ensure a high degree of fitness between the mission deployment and the accusation partitions. Furthermore, the method places significant emphasis on dynamic adjustment and mission adaptability. This is achieved through the utilization of the flexibility of edge command nodes, which enables them to cope with unexpected situations and guarantee the continuity of the operational command link, thus facilitating the efficient achievement of operational goals.

The command information system software forms a network through sophisticated interactions, where a single software failure can widely propagate within the network and cause severe consequences. Based on a weighted undirected connected graph, this paper constructs a static model of the complex network for the command information system software, proposes a hierarchical centrality algorithm for the multi-layer neighbor influence of nodes, realizes the prediction of software network fault sources, and mines the fault propagation path based on the ant colony system algorithm. Through simulation experiments analyzing the fault mode of a certain command information system software, the effectiveness of the proposed method is verified.

Our military’s exploration of equipment support mission planning is still in its infancy, traditional methods are difficult to meet the current equipment support needs, and there is an urgent need to combine with intelligent algorithms, machine learning and other new technology means to complete the support mission. Three typical multi-objective optimization models of equipment maintenance support mission planning were summarized and studied on the basis of analyzing the characteristics and content process of internal law of equipment maintenance support mission planning. The research status of the optimization model of maintenance demand estimation and force formation, maintenance mission assignment optimization model, maintenance job scheduling optimization model, and the solutions of the heuristic solution and mixed intelligent solution methods were summarized. Finally, a research outlook on intelligent mission planning for equipment maintenance support is presented.

Focusing on deployment planning for the overall equipment under ongoing combat-readiness circumstances, a mission-oriented approach to equipment status classification is proposed. The transition mechanism between different equipment states is analyzed as well as the implementing process of deployment planning based on it. An algorithm model aiming to optimize the deployment scheme is designed based on NSGA-Ⅱ, which efficiently coordinate response time, consumption replenishment, benefits and other multiple conflicts. The algorithm is proved effective with the scenario data and has strong reference significance to the overall equipment deployment planning and resource situation shaping.

Knowledge of weaponry and equipment is a crucial basis for formulating equipment utilization strategies and development pathways. To address issues such as data redundancy, high interaction difficulty, and low match accuracy of question answers, this paper constructs a Q&A system based on a knowledge graph for weaponry and equipment. The system achieves named entity recognition and classification of questions by fine-tuning the BERT model; it generates graph database query statements by filling named entities into question templates and generates answers by filling answer templates. Analysis of test results shows that this system is capable of effectively ranking correct answers at the top and has achieved a good balance between accuracy and comprehensiveness, although there is still room for improvement.

Service support brigade is a comprehensive emergency support force integrating maintenance, medical service, transportation and other support elements, in which the support capacity building of "one group of five teams" is a comprehensive embodiment of the efficiency of combining human and equipment, and strengthening "one group of five teams" is the basic support for building war logistics. Therefore, it is of great significance to accurately evaluate the afterloading support capability of the service support brigade for the armed police mobile detachment to carry out various tasks. In this paper, the fuzzy analytic hierarchy process (AHP) is used to establish the evaluation model of the afterloading support ability of the service support brigade and make a systematic analysis, so as to identify the shortcomings and weaknesses of the afterloading support ability and provide scientific guidance for improving the comprehensive emergency support ability of the service support brigade in the next step.

In order to meet the requirements of on-demand data sharing and real-time data stream transmission in Command Control and Simulation high-performance cluster systems, a high-speed interconnection mechanism based on Multi-hosts memory mapping is designed by using the native PCIe channel and the proposed one-way message queue. The interconnection mechanism provides three different protocols for transferring data, including inline, short, and long protocols. Combined with the PCIe Multi-hosts memory segment mapping method, it implements the functions of memory sharing, reflection memory, RDMA and other functions between the nodes. The proposal has the characteristics of low overhead, low latency, high bandwidth, etc., and can support the sharing and flow of batch data between local nodes in Command Control and Simulation systems. The final test results show that the proposed interconnection mechanism has high-speed data transmission capability, and the RDMA transmission rate can reach 9 000 MB/s with PCIe X16 lanes, and the data transmission delay can be effectively reduced.

Passive sonar operator of a ship needs to concentrate on observing sonar interface and underwater or surface target situation for a long time to extract key information manually maritime operations when surface vessels pass through sensitive waters, there is the risk of missing and false alarm. A station auxiliary operation technology for sonar digital image processing based on machine vision is proposed. First, the transient signal detection algorithm is used to extract the threat target mutation signal. Secondly, we use trajectory detection algorithm to extract key features of target, such as wideband trajectory and narrowband trajectory. Then, the threat judgment of an incoming threat target in each position within the effective observation range of sonar is generated by synthetically using the situation of a surface or underwater target. Finally, the sonar is automatically controlled to track the threat target according to the result of arbitrage. This technology can effectively reduce the work intensity of sonar operation, shorten the risk of false alarm and improve the threat target adversarial efficiency.

Protocol reverse is a solution for detecting and analyzing location or proprietary protocols, and packet clustering for protocol formats is the basic way to identify unknown protocol packets. In this paper, we propose an Unknown Protocol Packet Clustering MethodBased on Format Matching (CUPFC), which introduces the enhanced Barcos paradigm, defines Token Format Distance (TFD) and Message Format Distance (MFD) to represent the format similarity of Token and packets, and introduces Jaccard distance and an optimized sequence alignment algorithm to calculate them. Then, the MFD is used to establish a distance matrix and input it into the DBSCAN model to cluster unknown protocol packets into classes of different formats. On the two simulation datasets, the harmonic mean v measure of clustering is above 0.91, and the FMI and coverage are not less than 0.97, which has great advantages compared with previous work.

At present, army mainly relies on the live engagement system in the live training, integrating live, virtual, and constructive simulations. However, the implementation of integrated LVC joint simulation confrontation training faces significant challenges such as synchronizing virtual-real data, limited perception of virtual-real forces, and intricate interaction between virtual-real models, which severely impede the progression of LVC training. To address these issues, this paper proposes an interaction design method for a LVC confrontation training system based on intelligent target agents, building upon the existing live engagement system: ① Introducing targets as field agent for virtual forces models resolves challenges in real force perception of virtual force and model interactions. ② Utilizing behavior trees as the decision-making algorithm for target virtual forces models facilitates intelligent control of target agents. ③ Employing quintic spline interpolation algorithms to smoothen and denoise low-frequency sampled data from target devices, enabling real-time synchronization of real and virtual data. Initial experiments demonstrate that the proposed method for designing the LVC confrontation training system enables intelligent interaction and confrontation between real and virtual forces. The system is stable and reliable, providing effective support for developing integrated LVC training systems.

Mission planning in warfare operations requires high speed and accuracy in generating mission planning schemes. In response to the current issues such as modeling elements without adaptively adjustment, weak online planning capability, significant deviation of planning results and restricted effectiveness of planning results for mission planning system, the concept of mission planning in warfare operations oriented parallel simulation is proposed and then the parallel simulation system architecture is designed. Finally, the execution process model of mission planning in warfare operations oriented parallel simulation is established. As a result, the research provides certain reference significance to assist the generation of mission planning schemes in warfare operations with accuracy and rapidity.

In the modeling process of the air force behavior of the enemy in the field of simulation training such as radar and ground guidance, the random execution of actions between different rounds is often adopted to avoid the trainees to operate completely based on prior knowledge and affect the training effect. At present, the reactive behavior tree commonly used for modeling the force behavior of the enemy uses continuous action nodes. When modeling a certain type of air force behavior such as "penetration", the start and end states of action nodes in the front and back subtrees must be effectively connected. In this case, the random execution of actions will bring huge complexity to the functional design of action nodes. To solve this problem, this paper proposes a method of modeling the air force behavior of the Enemy based on self-cyclic behavior tree. In this method, the basic framework of self-cyclic behavior tree is designed, and the function design process of node is simplified by using transient action nodes. A new node feedback state is introduced and the execution logic is adjusted to realize the autonomous control loop running of the behavior tree, so as to achieve the complete modeling of the behavior process. Finally, the feasibility of the method is verified by simulation experiments and practical cases.

Aiming at the model construction of the identification antagonism between friend and foe in the command antagonism activity, This paper presents a simulation modeling method for identification and confrontation between friend and self in electromagnetic battlefield environment. The architecture design, main functions, mathematical model and operation flow of the model are described in detail, This paper reflects the application method of IFF system in reconnaissance and jamming in combat simulation, It provides an effective means to enrich the training of command on frontation.