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
Domain-specific knowledge graph in military field is a bridge to connect all kinds of battle factors, such as combat forces, command system, weapon platforms, etc. It’s also an important means to break through the information gap between different areas of different services. Most of the existing knowledge graph is general knowledge graph for general fields, but there is no mature method of knowledge graph construction and expression for the industry data of military specific fields. So based on the special needs for military knowledge acquisition, storage, representation, query and other technologies in the future information and intelligent operations, and the application scenarios in peacetime and wartime, this paper discusses the current opportunities and challenges of the knowledge graph in military domain. Then the construction of knowledge graph in military domain and application technology framework are proposed. In addition, this paper studies the key problem and core technologies of knowledge representation on ontology, knowledge extraction, and knowledge fusion cross domain, knowledge computing, knowledge application and other aspects of knowledge life cycle, to meet the requirements of military domain for the depth and accuracy of knowledge.
As a key technology of Knowledge Graph(KG) construction, Knowledge Reasoning Technology aims to make up KG and correct wrong relationships in KG. Knowledge reasoning based on statistics has great advantages in the completion of the large knowledge graph, while can utilize the statistical laws followed by KG. This paper presents a systematic survey to knowledge reasoning technology based on statistics. It briefly introduces the concept of knowledge reasoning for KG. Then, it introduces existing knowledge reasoning technology from three aspects: relationship learning based on hidden features, relationship learning based on graph features and type reasoning based on entity distribution law. This paper also discusses the challenges and the future research direction of knowledge reasoning based on statistics.
Based on cooperative air defense information system, there are four operational modes of the ship-to-air missile in cooperative air and missile defense operations. After introducing four operational modes of the ship-to-air missile, this paper gives basic principles of the operational mode selection and prioritization under qualitative analysis. Then, the influence factors of the operational mode of the ship-to-air missile are analyzed, modeled and simulated, including platform formation, acquisition performance, guidance distance and missile capability, and the prioritization of four operational modes under quantitative analysis is obtained. It is hoped to provide reference and basis for the commander to make quick decisions and the design of auxiliary decision system.
Unmanned cluster operations have incomparable advantages such as strong environmental adaptability and rapid penetration capabilities, but the use of these advantages is based on autonomous coordination between clusters. Aiming at the information sharing needs of unmanned cluster collaborative operations, it designs a lightweight blockchain architecture, proposes a data storage solution that combines blockchain and random file storage based on content addressing, and has high performance and high security. The DPOS and PBFT onsensus algorithm builds an information sharing platform suitable for unmanned clusters with limited computing resources and supports multiple combat missions such as unmanned cluster collaborative detection and command control.
There are such problems in joint missile-defense modeling and simulation systems,such as insufficient system completeness,insufficient core position of information system and difficulties in behavior modeling. This paper proposes an object-oriented component modeling and simulation method. This method considers the flexibility and composability of the operational behavior based on the optimization of design modeling framework and physical models. It uses UML and DODAF methods to construct the rational operational behavior model, and it has been verified and validated by the operational simulation system. This method provides a reference method for the joint missile-defense modeling and simulation.
When faced with small sample data, transfer learning has a good processing effect, which is one of the hot research directions of artificial intelligence.However, it is found that there are many problems in the practical application of transfer learning, especially the negative transfer phenomenon, which makes the transfer learning effect not good. In this article, we firstly review the concept of transfer learning and the research status, and then put forward three directions to solve the problem of negative transfer, including multi-source domain data learning, increasing the number of samples in the target domain, and reducing the data differences between domains. And we summarize the related research work to improve negative transfer based on the three directions.Finally, some other directions on improving negative transfer learning are looked forward to, which can provide some references for future generations to further study negative transfer.
The problem of radar countermeasure combat command simulation training is introduced in electronic countermeasure combat, according to the requirement of command simulation training, three design principles of radar countermeasure model system are put forward, including comprehensive elements, reasonable levels and accurate features. The model content system based on control interface and simulation entity and the model component system based on service, platform, auxiliary calculation and effectiveness evaluation are constructed. The two problems of logic rules and counterwork effectiveness in component design are analyzed, four solutions are summarized, which provide strong support for the design of radar countermeasure command simulation training system oriented to command training.
To deal with the problem of possible fire conflict of single surface warship when ship-to-air missile weapon and short range antimissile naval gun weapon conduct near end cooperative air defense operations, a fire compatibility model of near end air defense considering the change of the pitch or roll of the warship is established. Firstly, the assumed conditions are given according to the combat characteristics of the two weapons. Secondly, the changeable surface warship’s rolling and pitching is taken into consideration, the space ballistic equations of the two weapons projectile are given and the fire compatibility model between the two weapons is established. Finally, the simulation analysis is carried out and the results showed that the model of this paper can effectively judge the result of fire compatibility according to the changes of the pitch or roll of the warship, the model proposed in this paper is more practical and helpful compared with the fire compatibility model which doesn’t consider the change of the pitch or roll of the warship.
Aiming at the problem of low accuracy and low efficiency of existing network attack detection model, an improved convolutional neural network algorithm based on the principle of natural ecosystem is proposed. Based on the optimization of convolution characteristics, the self-organization and self-regulation principle in the ecosystem is used to design the information flow transfer model based on ecosystem, and then the improved convolutional neural network model is designed. The KDDCup99 data set is used as the experimental object detection improvement. The learning and prediction effects of neural networks. The experimental results show that the improved neural network is not only has higher detection accuracy, but also has higher learning efficiency than standard convolutional neural network and BP neural network. The improved neural network has broad application prospects.
Multi-agent cooperation should be considered in the reconfiguration of combat system, but the cheating behavior of agent cooperation leads to the failure of obtaining the optimal scheme. This paper proposes a multi-agent task allocation algorithm based on the improvement of classical contract network protocol. The task and agent are described by capability information and load information, and then the evaluation function is constructed to analyze the agreement degree between agent and task. Experimental results verify the effectiveness and rapidity of the Algorithm.
According to the characteristic and procedure of warship anti-submarine operation, this paper establishes the basic principle of choosing torpedo shooting position, builds the calculating model of maneuver parameters during occupying anti-submarine position by using Lagrange multipliers, verifies the model by using Matlab, and optimizes the model according to the simulation result. The research can provide a new method for anti-submarine fire control equipment to calculate the maneuver parameters and has some reference value for developing the combat system software.
Command ability, as the core ability of "being able to fight and win", is an important part of the missile force’s combat unit to complete the combat task. Considering that the decision-maker generally needs appropriate linguistic evaluation scale when conducting command ability evaluation, this paper proposes a multi operator evaluation and decision-making method. This paper establishes the command capability index system of the combat unit of missile force, puts forward the evaluation method based on the language information aggregation operator, determines the index weight by AHP, and evaluates and ranks the command capability of different combat units of a missile force. The research results show that this method can solve the uncertainty characteristics of the evaluation data, provide some reference for decision-makers, and has a certain practical value.
Aiming at evaluating the contribution rate of new research equipment in the navy equipment system, this paper does a normalized method study. Firstly, we build a process framework and analyse the theory and method in the process of evaluation. Secondly, the evaluation of contribution rate for new research large caliber naval gun system in the combat system as a case, we build a model to analyse the operation parameters. Then, we establish the task-ability matrix to evaluate the operation capability and operational effectiveness of active and new research weapon system in the task scenario qualitatively and quantitatively. Finally, we come to a conclusion of contribution rate for large caliber naval gun system. The system contribution rate evaluation framework established in this paper can give a good consideration to the relationship between operational requirements and capability indicators,laying a reference basis for the research, evaluation and inspection of new equipment, having certain reference value for the naval system combat application.
Target support of joint operations is a comprehensive work of cross department, cross system and cross specialty, which plays an important supporting role in the operation efficiency. First of all, combined with the actual situation, this paper summarizes the research status of the target support of our joint operations from four aspects: theoretical research, mechanism and system construction, target integration, target selection and strike; then, it analyzes the existing problems and the gap faced, and points out the direction for improving the target support ability of our joint operations.
The special problems about preventive maintenance work of vehicle equipment assembly are analyzed. The applicability of the opportunity maintenance and combined maintenance method used in the decision-making interval of vehicle equipment assembly preventive maintenance is compared. The preventive maintenance strategy of the vehicle equipment assembly is proposed. Based on the maintenance work combination method, the decision-making model of the vehicle equipment assembly preventive maintenance interval is established with the maintenance cost per unit time. Finally, the efficiency of the method is verified by an example of the EQ1118GA clutch.
In the missile strike system, it is necessary to study whether the target can be hit accurately. Based on the research of satellite coverage, target motion model and terminal guidance, an integrated simulation system for investigation and strike is established, and how to strike the target accurately after missile re-entry into the atmosphere is studied, when the reconnaissance satellite discovers the target, how to send the target information back to the command center quickly. Through simulation, the whole process and result analysis of detecting satellite discovering target, selecting communication mode and finally to missile attack target are shown. The simulation results show that the more the number of missiles, the smaller the distance between the final hit point and the target, the higher the positioning accuracy and the smaller the residual error. The choice of LEO satellite as relay satellite communication can effectively reduce the communication delay.
The lane-changing model is an important module in microscopic traffic simulation, and it is of great significance for its research. Most of the proposed lane change models are based on drivers’ thinking and machine learning based modeling methods. However, none of these models consider urgency and the model accuracy is low. This paper introduces urgency and proposes a new machine learning based lane change model. The data set is divided according to the urgency by the clustering algorithm, and the gradient boosting decision tree is used to learn the data sets of different urgency levels, and the lane change model with different urgency degrees is obtained. The experimental results show that the proposed machine learning-based lane change model has higher prediction accuracy than other machine learning lane change models. Finally, based on the analysis of the feature importance of the gradient decision tree, it is shown that the urgency plays an important role in the decision-making process.
For the problem that the high sea condition adaptability of the naval gun weapon system often cannot be tested under the actual conditions, on the basis of the systematic analysis of the factors and mechanism of the influence of high sea condition environment on each link of the naval gun weapon system, tidys out the main content of the high sea condition adaptability evaluation system, and gives out the evaluation method of high sea condition adaptability for the strength and stiffness of each equipment structure, tracking servo performance, tracking detection performance and attitude measurement performance. It has a certain guidance role on the high sea condition adaptability evaluation of the naval gun weapon system.
Intelligentization is an inevitable trend in the development of military aviation materials security. The design of the security system is an intuitive manifestation of the intelligent guarantee function of aviation materials. Using Python language as the development tool, the system is layered from the business layer, the logic layer and the data layer, and the functional modules of the system are designed and customized to achieve the intelligent guarantee of the aviation material. At the same time of improving the aviation material demand formulation, inventory strength presentation, aviation material transportation route selection, aviation material sharing, aviation maintenance and other aviation materials protection, the development of military aviation material intelligent guarantee is promoted from the application level.
This paper analyzes the trajectory characteristic of missile, and the building target to be hit is equivalent to the ground projection. Based on the characteristics of building target, we proposes a shooting method synthesizing both accuracy and obliquity of trajectory, and proves the theory that point of fall is the centre of projection. The hitting probability model is proposed and hitting probability method is deduced. An example concerning typical target is presented using the proposed method. According to the calculating results, influences on the hitting probability by accuracy, height, obliquity of trajectory and direction angle are analyzed. The results show that the proposed method is reasonable and feasible.
In order to solve the minimum launch-timing sequence problem of ballistic missile cluster launching, the dynamic model of ballistic missile flight and the error covariance matrix model of missile position are established and the collision probability in 3D-space has been simulated in different time intervals. The computing of minimum launch timing and accurate solution of trajectory intersection problem is introduced, which provides a theoretical method for the optimization of fire plan of cluster launching.
IMS (IP Multimedia Subsystem) is the target evolution direction of next generation networks. SIP (Session Initiation Protocol) is the core control protocol of the IMS network for establishing, modifying, and terminating multimedia sessions. This paper discusses the mechanisms and deficiencies of several existing key distribution methods for the confidential communication requirements of private mobile communication systems. In this paper, the key distribution function is regarded as a new service, which is implemented by the service trigger mechanism of IMS. Through the research and extension of SIP signaling, a new key distribution scheme based on SIP and call setup process is proposed. By comparison, the new scheme has the characteristics of adapting to the IMS network, simple process, reduced delay, and easy service deployment. Finally, the experimental environment is set up to verify the feasibility of the new method.
Aiming at the practical problem that radar/infrared imaging guidance anti-ship missile has strong anti-jamming ability in surface ship anti-missile combat, the countermeasures of outboard active jamming and smoke jamming are studied by analyzing the guidance principle of radar/infrared imaging composite guidance. The simulation results show that outboard active jamming and smoke screen jamming can effectively jam the radar/infrared imaging guided anti-ship missile. The research results can provide reference for relevant electronic jamming in combat.
Conventional fault diagnosis methods of the weapon system include on-site technician investigations and remote expert diagnoses. However, on-site investigations cost massive manpower and material resources, and remote diagnoses need high technical requirements. For overcoming these drawbacks, the fault diagnosis methods of the weapon system based on the intelligent customer service technology is proposed. The mapping knowledge domain is employed to construct domain knowledge base. Multi-task scenarios are preset according to common faults occurring in the weapon system. Multi-round task-driven intelligent customer service dialogues are used for error checking and troubleshooting. Through practical cases, the intelligent customer service technology of the weapon system can assist users to eliminate faults effectively, indicating a promising application prospect.
To solve the problem of uncertain control results caused by the uncertain parameters of the chaotic ship steering control model, the adaptive control is combined with the Backstepping method, and parameter estimation error compensation is introduced when designing the controller. As a result, the system parameters can be effectively and correctly identified, and an improved adaptive Backstepping control method has been concluded. Our experimental results demonstrate stable and effective control of the chaotic ship steering with unknown key system parameters, provide an effective approach for high accuracy course keeping.
Based on analysis of the characteristics of civil routes and civil flight rules, a simulation method of radar threat air situation is proposed. This method takes civil aircrafts as the target by using the ADS-B receiving technique. The basic structure of the air situation simulation system is also given. This method provides simulation air condition for radar operation skill training, command training and equipment effectiveness testing in complex electromagnetic environment. In addition,it can also be used to construct multi-directional air threat situation, which has some application value.
Instructors operating station (IOS) is the control center of flight simulation system, and mainly used to control and monitor the whole training process. Focusing on the characters of aviation unit tactical simulation training system, this paper summarizes the main functions of traditional IOS for the single flight simulator, deeply analyzes the relevant extended functional requirement of IOS, and studies the module structure of the system and critical implementation technology. Until now, IOS has already been used in several different kinds of aviation unit tactical simulation training systems. Practice result indicates that IOS has complete functionalities, easy usability and strong practicalities. Therefore, IOS has great value for similar systems to study when building systems.
