Aimming at the multitudinous battlefield situation information and the difficulty in recognizing the changing trends, based on large models, a situation awareness agent and an intelligent situation awareness inductive method are proposed. Starting from cognitive concepts and combining the abstractness and embodiment characteristics of agents, three key components in the construction of agents have been clarified: learning environment, memory mode, and knowledge generation mechanism. The architecture of the battlefield situation awareness agent is designed, including memory component, planning component, execution component, evaluation component, and key points for agent training. In the long-term memory component, based on the modeling characteristics of complex battlefield states, the paper discusses the application of large language models, multimodal large models and large sequence models.

Capability requirement analysis is the key stage of operational concept development. Based on the formal description of the operational concept capability requirement analysis, a method of operational concept capability requirement analysis based on DRL(deep reinforcement learning) is designed from the perspective of qualitative and quantitative combination. In this method, small sample data sets with high reliability can be obtained through simulation experiments. Based on the experience data, the surrogate model of operation concept is constructed, and the model is optimized and trained by using multi-objective optimization algorithm with the high credibility simulation data set as the input. Finally, the agent model obtained from the training and the DRL framework are interactively optimized to achieve the reverse exploration of the operational concept capability requirements. The experiment results show that the method is feasible.

In view of the urgent need of air defense early warning information system to assess the threat of aerial targets, this paper analyzes the operational scenarios and characteristics of aerial targets. Firstly, eight indicators, such as ammunition type and country, are extracted. A hierarchical indicator system is built through hierarchical division and a quantitative threat scoring model is given for qualitative and quantitative indicators. Secondly, the weight of each index is given based on AHP, and the comprehensive score of aerial targets threat is calculated. Finally, the accuracy and effectiveness of this method are verified in the simulation experiment. The aerial threat assessment results can effectively support the selection of subsequent equipment scheduling strategies and the allocation of anti-air weapons, and have high practical application value.

An ontology-based knowledge graph construction method for military terminology is proposed, which is used to obtain semantic information in military terminologycorpus and construct military terminology knowledge graph. Then the ontology of military terminology is built firstly based on the analysis of military terminologycorpus. In this method, the rule based method and the pre-trained model based method are used to extract the relation of military terminology and the knowledge of military terminology is stored in the graph database at last. This method can construct high quality knowledge graph of military terminology for intelligent applications such as semantic search, intelligent question and answer.

In the process of the battle between the enemy and us on the battlefield, accurately predicting the deployment of the enemy forces will be beneficial to our combat. Based on the situation data of wargame, this paper proposes a method for predicting the unknown operator position of the enemy by training Graph Neural Networks. Firstly, after preprocessing the data, the transformation from situation to graph structure data is realized, and the graph structure data set of wargame situation is constructed for training Graph Neural Networks. Secondly, according to the characteristics of wargame situation and its data, GraphVAE model is modified to complete the graph structure data of wargame situation. Finally, a method for calculating the position of the enemy operator based on the completed graph structure data is designed. The effectiveness and feasibility of the proposed method are verified by experiments.

Aiming at the problem of ship behavior anomaly detection based on massive track data without behavior pattern label, an unsupervised track anomaly detection method based on GRU-VAE model is proposed. The abnormal behavior of the target is found by detecting track anomaly, which is implemented in two steps: model training stage and anomaly detection stage. In the model training stage, the timing modeling ability of GRU gated cyclic Autoencoder (VAE) model is introduced. The Gate Recurrent unit-variational Autoencoder model is trained by historical track data without abnormal information labels. According to the reconstruction loss distribution, the normal distribution method or percentile method is used to delimit the confidence interval as the reconstruction loss threshold. In anomaly detection phase, the model of real-time track data set for testing, regarding the damage threshold of the track to refactor losses above points as abnormal track points, when the track is in the sequence beyond the proportion of abnormal track point accounted threshold, it is judged to be abnormal track sequence, combined with the data anomalies target behavior information are presented to the first-line staff. The experimental results on AIS data show that the highest F1 score of the model is up to 86.36%, and the recall rate is up to 95%. The high sensitivity and low miss alarm rate of this method to abnormal track meet the reconnaissance requirements of first-line units.

Modern warfare presents a new form of multi domain cooperation, multi mission concurrence and multi element coupling, which poses new challenges to operational missions planning. The reasonable decomposition and standardized description of complex operational missions is an effective means to improve the scientific nature of mission planning, the efficiency of mission planning and the quality of mission completion. On the basis of the systematic explanation of the concepts related to the decomposition of operational missions, the basic principles of the decomposition of operational missions are proposed. Drawing on the basic idea of the "Hall three-dimensional structure", the strategy of the decomposition of operational missions based on the "time dimension, logic dimension, and activity dimension" is proposed. The standardized description form of the meta missions is defined, and the relationship between the meta missions is described from the three aspects of time sequence, logic, and function. The application case study shows that, the proposed method is feasible and effective for the rational decomposition and standardized description of complex operational missions.

Aiming at the limited space and resources of the UAV platform, the inaccurate target labeling and excessive calculation amount of high-resolution SAR image detection, a rapid detection method for UAV-borne high-resolution SAR image targets is proposed. Firstly, a bilateral filter is used to suppress the coherent speckle noise and non-uniform undulation inside the target in the high-resolution SAR image. Then, a large-scale SLIC segmentation is performed, and a small-scale SLIC segmentation is performed on the superpixel unit with under segmentation problem by analyzing the roughness of the superpixel unit. Finally, the over-segmented superpixel units are combined to obtain the target detection results. The experimental results show that this method can not only improve the detection efficiency of high-resolution SAR image targets, improve the SAR image target extraction ability, but also help to find small targets that are easily missed by some manual methods, and has good engineering application value.

Strategic evaluation is the key link of military strategic system and capacity building. Selecting and evaluating the system construction scheme can optimize strategic decision-making and improve strategic management level to a certain extent. This paper constructs an intelligent selection analysis framework of "prospect cost" system construction scheme based on MATE, and uses NSGA-Ⅱ intelligent optimization algorithm to find the Pareto front of alternative scheme in multi-dimensional tradeoff space, which improves the problem of large data volume. Taking a joint operation system as an example, the effectiveness of the proposed method is verified, providing theoretical support for the optimization and evaluation of system construction scheme.

In this paper, the key technologies of multi-radar network and cooperative detection are studied in order to meet the urgent needs of radar network operations in the future strong countermeasure environment. Firstly, the operational capability requirements of radar network are introduced. Secondly, based on the traditional tree hierarchical structure of radar network, the new distributed network architecture is given. Finally, the key technologies of radar network information distribution and sharing, intelligence fusion processing, autonomous cooperative detection and system feedback control are studied. This paper will promote the updating of the concept and the development of the domain technology of the multi-radar network, and will promote the iterative upgrading of radar equipment and intelligence systems.

The complexity of modern war is increasing, and the rapid operational mission planning is of great importance to improve the efficiency of command and control. This paper presents a joint operational Task Matrix (TM) model, which is a theoretical method for mission planning. A belief network model is put forward to describe the relationship among the elements in TM model. A naive bayesian learning method for belief network is designed. A mechanism of imagination is put forward to speed up the learning process. A search algorithm named Deep Minimum Threat Generation Tree(DMTGT) is proposed, which can efficiently calculate task priority by balancing search error and search speed. Finally, the validity of above models and algorithms is verified by simulation experiments.

The dielectric materials with different refractive index are periodically arranged according to a certain structure to form photonic crystals, which can control the photon transmission regularly. The infrared stealth characteristic of this material is one of the current research focuses. In this paper, the related concepts of photonic crystals and the development of foreign photonic crystal infrared stealth materials are introduced in detail, the characteristics of photonic crystal infrared stealth technology are summarized, and the development of photonic crystal compatible stealth technology is studied, and some enlightenment for the development of photonic crystal infrared stealth technology in the future is given.

Submarine-borne laser weapons can improve defense capabilities and increase the types of mission that can be completed. By introducing the research progress of laser weapons, the development status and application situation of laser weapons in the US, submarine installation requirements is proposed. The paper suggests timing for weapon use and analyzes the ability to damage anti-submarine aircraft. And it analyzes the ability to damage anti-submarine aircraft, and Provides reference for relevant research.

Torpedoes are one of the main threats faced by surface ships and submarines in modern naval warfare. How to defend torpedoes has always been a hot and difficult issue in various countries. This paper analyzes the working principle, technical characteristics, application conditions, advantages and disadvantages of several typical anti torpedo technologies, and on this basis, prospects the development trend of anti-torpedo technology.

Military regulations are of great significance to modern military operations. However, consulting the texts is inefficient and error-prone. A military legal question answering system is constructed by integrating retrieval and knowledge graph technologies. The optimized TF-IDF model is used to establish a data structure for the hierarchical retrieval of laws and regulations to improve the efficiency. Knowledge graph technologies are used to generate a large amount of knowledge for the clauses of laws and regulations, ensuring the ability of question understanding. According to the characteristics of military laws and regulations, the algorithms of question processing and clause retrieval are designed, and the complete answer is composed of a short answer, clause content and an answer source. Analysis and testing show that the underlying data constructed is highly hierarchical and semantically rich. The prototype system can accurately answer questions from multiple perspectives, and it combines the advantages of retrieval and knowledge graph technologies. The system can provide decision aid for the commander to deal with legal problems, and the technologies are also applicable to regulations in other fields.

In order to improve the operational effectiveness of multi-sensor cooperative detection of carrier-borne fighter, based on the scene of air interception, according to the combat airspace from far to near, the scene model of the extended range search of carrier-borne fighter, the radar infrared fusion detection, the cooperative guidance of formation and radar multi-beam detection are established. In the over-the-horizon, medium-range and short-range search phase, the extended range detection, interference and multi-beam detection in the multi-sensor cooperative detection mode are simulated and analyzed. According to the different combat distance, the design of multi-sensor cooperative detection mode under the combat flow is innovatively carried out.

Aiming at the cooperative pursuit and confrontation task of multiple UAVs in the unknown escape UAV environment, a multi-UAVs cooperative pursuit and confrontation strategy based on P3C-MADDPG algorithm is proposed. First, in order to solve the problem of slow training speed and over estimation of Q value of Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, In MADDPG algorithm, Prioritized Experience Replay (PER) based on tree structure storage and a parallel Critic network model with 3 threads are prioritized respectively, and the P3C-MADDPG algorithm is proposed. Then, based on the kinematics model of UAV, training elements such as state space, reward function combining sparse reward and guided reward, pursuit action space with different accelerations are designed. Finally, based on the above training elements, the P3C-MADDPG algorithm is used to generate the cooperative pursuit and confrontation strategy of multiple UAVs in the unknown escape UAV environment. Simulation experiments show that the P3C-MADDPG algorithm increases the training speed by 11.7% on average, and decreases the Q value by 6.06% on average. The generated multi-UAV cooperative pursuit and confrontation strategy can effectively avoid obstacles, and more intelligently realize the pursuit of unmanned aerial vehicles with unknown strategies.

The cooperative region search of UAV swarm can obtain ground information of the mission region and reduce the uncertainty of environmental information effectively. The traditional collaborative region search methods based on the balanced allocation of divided region and the heuristic algorithms depend on the pre-designed rules and heavy computation, and have no ability to generate new rules of the cooperative search. These algorithms belong to the algorithms that can not evolve new rules. Due to the complexity of the mission environment, the algorithms must contain fast,intelligent and robust characteristics, the cooperative searching algorithms of UAV swarm based on emerging theory with strong information fusion ability, self-learning ability have been widely concerned. Evolutionary and reinforcement learning algorithms are the important parts of the emerging theory and both of them can generate some new cooperative searching rules according to the different environment and task. The paper would systematically analyze and summarize the current research status and progress of cooperative search methods. Finally, the shortcomings of the existing research and the further development are put forward.

In order to study the problem of damage to typical targets by naval guns and weapons of coast guard vessels in rights protection law enforcement tasks and improve the operational capability of naval guns and weapons of coast guard vessels, a simulation model and simulation process are constructed. Through simulation calculation of the damage probability and ammunition consumption expectation of different targets, the relationship between the damage probability of typical targets, ammunition consumption expectation and shooting distance are analyzed. Furthermore, the destructive firing strategies of different typical targets are obtained. The research results can provide reference for coast guard vessels to carry out the task of safeguarding rights.

Based on the analysis of operation system capability testing and evaluation, this paper studies the data resource system of operation system capability testing and evaluation from operation, business and engineering aspects. A 3-View data resource framework is presented. And some suggestions on data resource construction are given. The research can help to clarify the data needs, improve the consistent understanding of joint operation system capability evaluation data, and promote the development of the data resource and data integrated service platform.

Aiming at some "pain points" in data access of the wargame system, a bus-based real-time data collection and management platform for wargame is designed by absorbing the experience and lessons of domestic and foreign wargame systems. The distributed storage platform is introduced as the underlying storage foundation, and the in-memory database is introduced as the external service interface. The bus-based data collection is used as the collection source, and data cleaning and branch management based on data segments are performed. The system as a whole is divided into three modules, namely collection module, management module, and service module. It realizes real-time collection, cleaning, storage and management of wargame data. The practical application shows that the platform provides high-speed and reliable data access support for other modules in the wargame system.

By analyzing the performance and main penetration technology of typical subsonic anti-ship missile of formidable enemy, this paper proposes a similarity analysis method based on the characteristic decomposition of threat target and constructs the similarity model of simulated threat aircraft. And the proposed method and model are used to evaluate the similarity of the target drones and analyze the difference between the target drones and the typical simulated objects. On this basis, this paper studies the current methods of building typical threat situation and analyzes the deficiency. According to the above results, this paper puts forward some thoughts on how to improve the ability to simulate the formidable enemy anti-ship missile target, how to improve the air defense and anti-missile training effect and how to build a systematic air blue force. These considerations provide the basis of the construction of the air threat situation for the firing range.

Aiming at the specific target search and controllable angle guidance of unmanned surface ships in uncertain waters, this paper explores the target detection method based on YOLO and the guidance control method based on side angle constraint. On the basis of analyzing the uncertain conditions such as sea fog, the paper designs the correlation filter with improved YOLOv5 algorithm to extract the target features, combines depth information to realize the detection and positioning of water surface targets, sliding mode variable structure guidance control to achieve the high maneuverability target side angle constraint guidance. TCP/IP combined with ROS is used to create a corner constrained terminal guidance system for information processing. Two-dimensional simulation experiment is completed with Autolabor platform, and the result of target guidance error is 1.54%, which proves the effectiveness of the method proposed.

The design and evaluation of exercise training subject is an important part of military training, the quality and effectiveness of military training can be effectively improved by scientific training subject design and reasonable subject design and evaluation methods. In view of difficulty to design exercise training subject and the unscientific evaluation of exercise training subject, the paper analyzes the requirements of training subject design, studies the design method of training subject and training mode based on task, and proposed similarity-based the evaluation method for training subject design. The research results have formed a complete set of training project design and evaluation model, it can provide reference for the army to organize exercises and training.

In view of the problems existing in the current exam system, such as separation from the command information system and difficulty in carrying out remote group training, a scalable and extensible command training exam system architecture is proposed to provide technical support for integrating and invoking the relevant components of the command information system and carrying out large-scale group training. Firstly, the component integration framework of multi-system integration and the integrated exam course evaluation mode are proposed to realize the assessment of each course including command skills. Then, a multi-level server exam structure is designed. On this basis, through the application of virtualization cluster and other technologies, the rapid deployment of the system under diverse conditions and the large-scale remote group training application is realized.

The materials supply for sea islands is the basis for ensuring survival needs of persons on sea islands. Considering factors such as transportation cost, storage cost, recycling demand and transportation capacity, it is a vehicle path planning problem with time window and capacity limit to use many transportation tools to supply materials for sea islands within a time cycle. The intelligent algorithm provides a preferable solution to solve this complex irregular optimization problem. The paper establishes a mathematical model of mission planning of materials supply for sea islands, explores the solving process of genetic algorithm, and uses an example to calculate it. The optimization result shows that the scheme can save transportation costs and storage costs, and also meet the need of materials supply cycle, which can provide a reference for scientific mission planning of materials supply for sea islands.

Aiming at the problem of "fast and precise" in the optimization of joint fire strike scheme, a cross-entropy-quantum particle swarm optimization algorithm is designed, and an intelligent optimization method of joint fire strike scheme based on this algorithm is proposed. The algorithm fully combines the good global optimization ability of the cross-entropy algorithm and the efficient operation of the quantum particle swarm algorithm. By constructing a discrete probability matrix, the uncertain motion of the particles is more directional and the cooperative optimization ability of the particles is improved. The experimental results show that the intelligent optimization method of the joint fire strike scheme based on this algorithm can effectively improve the optimization effect and optimization efficiency of the joint fire strike scheme, and has obvious advantages compared with the standard cross-entropy algorithm and the standard quantum particle swarm optimization algorithm.

Helicopter is the superior combat force of low altitude and ultra-low altitude. With the increasingly complex battlefield environment and the continuous upgrading of battlefield threats, the combat capability of helicopter is required to be higher. This paper briefly describes the helicopter construction and application of Russian air forces during the conflict between Russia and Ukraine, summarizes the helicopter battle loss, analyzes the causes of helicopter battle loss, and puts forward measures and suggestions to promote the helicopter equipment construction and development based on the research of the helicopter ability defects, which has a certain reference value for helicopters to adapt to the future battlefield environment and combat effectiveness improvement.

In order to solve the problem of how to quickly and accurately obtain the location information of self-organizing networks or target objects in the narrow and closed battlefield environment, such as the enemy command center, cabins, and underground buildings, this paper proposes a positioning algorithm based on the communication module provided by individual intelligent terminal equipment, we use the support of hardware devices such as visible light sensors, and study the communication signal fingerprint of swarm intelligence perception, combined with image matching algorithm. This algorithm mainly communicates with fingerprint data to achieve preliminary positioning, combines a weighted average algorithm of fused images and attitude sensors, and uses swarm intelligence perception to supplement and update positioning data. By adjusting the image matching strategy, while maintaining accuracy, compared to a single image matching positioning algorithm, it reduces computational power requirements and improves real-time performance in battlefield environments with complex communication conditions. Compared with the standard WKNN (Weighted K-Nearest Neighbors) algorithm, it improves the stability of localization in complex environments, and the average localization error is less than 1.72 m, reducing the error by about 50%.

Mission planning of border control operations refers to the process in which the relevant forces of border control make use of the mission planning system to plan and design relevant actions in order to achieve a specific action destination, so as to form a relatively scientific and reasonable action plan. In this paper, strategic analysis is carried out from the subject object, system composition and hierarchy of border control action task planning, and based on the transmission algorithm, the basic process of border control action task planning is discussed.

An Unscented Kalman Filter with multi model adaptive estimation algorithm (MMAE-UKF) based on dynamic characteristic template is proposed to solve the problem of trajectory estimation of interceptor in boost phase by using passive detection method for single aircraft. Under the condition of incomplete observation information, by introducing the interceptor dynamic characteristic template, the design parameters of flight program model and launch azimuth angle are expanded to target state components. Based on the flight program model and dynamic characteristic template, a nonlinear MMAE model set is constructed. The flight program model and design parameters of the interceptor are identified using the MMAE-UKF algorithm, and the motion state of the interceptor in boost phase is estimated. The simulation results show that the algorithm can quickly and accurately identify the flight program model and design parameters used in the boost phase of the interceptor. Compared with the traditional expanded state filtering algorithm, the motion state estimation error is significantly reduced, and the filtering stability speed is greatly improved.

In this paper, the theoretical innovation is made on the traditional fire distribution problem. Considering the actual situation of the ship’s fault, based on the principle of multi-objective optimization, the improved distributed genetic algorithm is used for preliminary solution. And the corresponding fault-tolerant control law is formulated to correct the fault-tolerant strategy, so as to ensure the better fire strike effect and maintain a high fault tolerance. Finally, through simulation experiments, it is verified that this method can converge to the optimal solution quickly, and can reduce the loss to the maximum extent when compensating. It has certain research value for combat.

Aiming at the problems of low efficiency of minor repair and maintenance of military equipment in the synthetic force, strong randomness of maintenance human resource allocation, and unbalanced and unreasonable resource utilization, taking the armored equipment as the research object, this paper analyzes the task and demand of the operation process of relying on maintenance workshops to carry out equipment minor repairs in peacetime. The optimization goals are to minimize the total maintenance period and maximize the balance of maintenance personnel allocation, taking the professional and quantity requirements of maintenance personnel in the maintenance process as constraints, a mathematical model of the equipment minor repair operation process is constructed. And then aiming at the sequence relationship of maintenance procedures, a maintenance network process update algorithm with tabu table and a genetic algorithm considering equipment parallel maintenance operations are proposed to optimize the maintenance human resource allocation strategy for equipment minor maintenance operations. The example shows that the algorithm is reasonable and feasible.

Being the important composition, the efficiency of information transmission system affects directly degree of system operational task. Aiming at the characteristics of warship information transmission efficiency evaluation multiple requirements and complex system organization application, the paper applies the method combining technique quantification model and restriction factors. Rounding single link, multiple links and marshalling operations information transmission requirements, the system structure of information transmission efficiency evaluation based on operational task is established, which can offer efficient supplication for warship communication command.

The accurate prediction of driving intention and driving tracks of surrounding vehicles is the basis to ensure the safe driving of Intelligent Connected Vehicles in complex road scenes. This paper proposes a driving intention and behavior prediction model of intelligent connected vehicles based on BLSTM-DCG-ATT by combining Bi-directional Long Short-Term Memory, Deep Convolutional Generic Adversary and Attention Mechanism. The data with dual characteristics are obtained through the forward and reverse Bi-directional LSTM link and attention mechanism, and then the characteristic data are convolved through the Deep Convolutional Generic Adversary to iteratively generate the lane change intention and driving data of the intelligent connected vehicle and surrounding vehicles in the future. The simulation results show that the model can accurately predict the lane change intention and driving track of the intelligent connected vehicle and its surrounding vehicles under the condition of complex road network and dense traffic flow, and the prediction accuracy reaches 94%.

As one of the main ammunitions for attacking air targets, the fragmentation and shock wave power of grenades are important parts of evaluating damage ability. In order to study the comprehensive power of grenade, grenade simulation ammunition is designed refers to Italy’s Oto Melera 127 mm ammunition. On the basis of experiment, numerical simulation and empirical formula, the fragmentation velocity, fragmentation spatial distribution and shock wave overpressure are analyzed. The experimental results show that,the scattering direction angle of the grenade simulation ammunition is 93.67°, the scattering angle is 65.42°, and the initial velocity of the fragments is 1 451 m/s. The simulation and calculation results show that, for the scattering angle, the deviation between theoretical and experimental values is relatively small, for fragmentation velocity, the error between theoretical calculation and experimental value is less than 20%, for shock wave overpressure, the error of theoretical value, simulation value and experimental value is less than 15%.

Aiming at the demand for real-time numerical/semi-physical simulation in the research process of automated aerial refueling for unmanned aerial vehicle (UAV), this paper develops an automated aerial refueling distributed simulation system based on ZeroMQ and C++/Qt. Firstly, the simulation communication network of distributed simulation system is designed. Then, the program framework is designed and the management node and simulation node are defined. Finally, the above mentioned context is programmed through ZeroMQ and C++/Qt. The distributed simulation system can realize the real-time simulation for automated aerial refueling, and leave the convenient interface for semi-physical simulation.

In order to give full play to the maneuverability of sea-based ballistic missile defense force and expand the level of sea-based ballistic missile defense, this paper studies the deployment of early warning and detection ship in ballistic missile defense operations, and establishes the radar detection model of early warning and detection ship from the aspects of ballistic missile movement characteristics, radar detection power and visual range limitation. Taking medium-range ballistic missiles with a range of 500 km-5 500 km as an example, three trajectory forms of minimum energy trajectory, low launch trajectory and high launch trajectory are distinguished, and the detection capability of the early warning detection ship against the incoming ballistic missile under different deployment positions is simulated and analyzed. Based on this, the corresponding deployment method of early warning detection ship is given. The conclusions obtained can provide reference for the force deployment in sea-based ballistic missile defense operations.

Explorative simulation experiment is an important mean to understand and study warfare, but it often faces problems such as high complexity of scenario sample space and explosion of space dimensions. To solve all above problems, a qualitative and quantitative method for screening experimental factors based on multi-label learning(MLL)is proposed. First, based on qualitative analysis, a pre-simulation experiment is designed and implemented, experimental data are collected and processed, and the problem of missing machine learning sample data is solved. Then, the input control layer is introduced to build a deep neural network, and sparse regularization is introduced to achieve feature selection during multi-label model training. Then, regression qualitative analysis is used to supplement and improve the experimental factors. Finally, the simulation of stereoscopic projection action is used for experimental verification. The experimental result shows that the method is feasible and valuable in military.

Aiming at the uncertainty problem in the current evaluation of synthetic brigade equipment maintenance support capability, a cloud model-based evaluation method for synthetic brigade equipment support capability is constructed. Based on five aspects of command and control, maintenance preparation, establishment of field emergency repair institutions, equipment rescue and equipment emergency repair, the evaluation index system of synthetic brigade equipment maintenance support capability is constructed. The combination of analytic hierarchy process (AHP) and entropy weight method is used to determine the weights of evaluation indicators, avoiding the one-sidedness of weight calculation. By establishing evaluation standard cloud, evaluation index cloud and calculating comprehensive evaluation cloud, the evaluation level is determined, and the feasibility of the evaluation method is verified by an example, and the effective evaluation of the maintenance support capability of synthetic brigade equipment is realized.