"Demand traction, technology promotion" is the main rule of the development of equipment system construction. This paper focuses on the analysis of system requirements, and puts forward the process of system requirements analysis on the basis of analyzing the basic connotation of system requirements analysis, combining the advantages of threat and capability; aiming at the key technical problems such as capability gap measurement and mapping analysis in system requirements analysis. The capacity gap measurement model is established, and the QFD method is used to realize the mapping between the capability requirement-system requirement-technology requirement, and the analysis of the typical space target monitoring system is taken as an example to verify the system demand analysis method proposed in this paper, which provides a theoretical basis for carrying out the system demand analysis.

Facing the continuous improvement of war complexity under the trend of system-of-systems confrontation,this paper introduces MBSE to the modeling design of complex system-of-systems combat. Adopting Unified Architecture Framework, a modeling method based on scenes is proposed by sorting out the modeling needs and internal mechanisms of system operations. Taking the task that searching and attacking multiple target as an example,various kinds of view is constructed including strategic, operating, resources and services. Then, logic verification is carried out based on the model. This method can provide a reference for system-of-system combat design and UAF application.

This paper presents a method of equipment demonstration AoA method considering RMS factors. It puts forward the equipment demonstration AoA framework, and elaborates equipment demonstration AoA measure system. It analyses the RMS and cost factors, and establishes their quantitative models. An AoA model based on Data Envelopment Analysis (DEA) and an application example are given to illustrate the feasibility and effectiveness of the method.

Arming at the coexistence dilemma of inventory overhang and shortage of different maintenance equipment supply nodes, a steady-state coefficient of a supply node has been described with which contains inventory level, the support degree between nodes each other, the demand status of the area guaranteed by the node and the cost of risk when the demand cannot be met. The steady-state coefficient of the inventory network was calculated on the base of all of support nodes. The active adjustment is carried out flowing the corresponding algorithm according to the gap between the steady-state coefficient and the threshold which has been set before. The scientific, automatic and intelligent level of equipment adjustment can be greatly improved, consequently the success rate of maintenance support is improved if the passive stock adjustment is combined because of out of stock at the same time.

The development in artificial intelligence has dramatically changed all industries, among which AI-assisted air combat is a representative case of success. An Intelligent air combat model that consists of the attainment of samples and a decision-making model is constructed in connection with air combat simulator. Considering the characteristics of air combat continuous states and actions, DQN algorithm is selected as the model of intelligent air combat by comparison among several algorithms. Meanwhile, the AI network is trained interactively with AI enemies in the air combat simulation game DCS World, resulting in a model that is able to manipulate aircraft to a degree and many cases of air combat, by analyzing which a collection of winning, losing and dual samples is derived. The result of simulation indicates that the Intelligent air combat model has certain ability to generate strategic samples and enrich tactics in air combat environments.

In order to solve the problem of scientificity and efficiency of force grouping in joint operational planning, a nonlinear method of generating polymeric operational capability from combative element capability is proposed, and a force grouping relationship of "operational subtasks to polymeric operational capability to combative meta-capabilities to battalion combative units" is established. And a modular force grouping model at the joint operational level with multiple optimized targets and multiple constraints is constructed based on the matching of supplying and demanded vectors of operational capability. A model solving framework based on genetic algorithm is proposed, and the processes and methods of coding decided variable, calculating adaptive value and decoding chromosome of the force grouping are explained. Experiments show that the modular force grouping model based on the matching of operational capability can accurately and efficiently group battalion combative units to meet the needs of operational tasks.

In order to improve the probability of underwater target capture, the double-mine parallel heading salvo method has been widely adopted, and the strike advance angle, deployment coefficient and spread angle of the salvo model all affect the target capture probability, and previous research in related fields mainly focuses on the influence of double mine deployment coefficient and spread scatter angle on target capture probability, which has certain limitations. In this paper, a parallel heading salvo model to improve the probability of double mine capture is given, and a multi-parameter optimal solution equation is theoretically derived, and a multi-parameter adaptive optimization method is given to solve the equation. Combined with simulation experiments, based on Monte Carlo method, the feasibility of multi-parameter adaptive optimization method is verified by comparing the target capture probability of the traditional double-ray salvo model with the optimization model. The results of the study provide an effective reference for the further use of torpedo salvo tactics.

The calculation of target distribution area is a prerequisite for anti-ship missile tactical decision-making and target acquisition probability calculation. On the basis of studying the target pursuit model of anti-ship missile, based on the relaxation variable method, the calculation equation for the target distribution is established, sufficient and necessary conditions are proved, the analytical model of target distribution area is obtained. Under the assumption that the target movement direction is arbitrary, and the calculation form under general conditions is given. Through the simulation example, the variation of distribution area under different conditions is compared, which can provide intuitive reference and estimation basis for the decision-making and use of the battle commanders.

By analyzing the characteristics of collaborative decision-making behavior of heterogeneous clusters, this paper introduces quantum decision-making model to solve the autonomous decision-making problem of heterogeneous clusters. Firstly, it is triggered from the OODA loop process to clarify the control mode of heterogeneous cluster collaboration. Then, aiming at the specific problem of heterogeneous cluster cooperative cruise, the tasks of unmanned boat cluster and UAV cluster are split, and the application models of formation optimization and autonomous detection are constructed respectively. The formation optimization algorithm is designed to dynamically generate the best communication formation structure. The quantum decision cloud and feedback scoring mechanism are designed to select the most suitable decision content among many possible detection options. Finally, the effectiveness of formation optimization model and autonomous detection model in heterogeneous cluster cooperative cruise is demonstrated by simulation experiments. Experiments show that the quantum decision model has greater applicability and mobility in decision behavior selection and optimization than the conventional decision model.

In order to improve the search ability of carrier-based early warning aircraft to enemy surface ships and ensure the safe and continuous tracking, monitoring and early warning of carrier-based early warning aircraft, a method for reconnaissance and early warning position configuration of carrier-based early warning aircraft for sea surface targets is proposed. Based on the basic requirements of its position configuration and the conditions that meet the combat background, the factors affecting the early warning distance of the carrier formation provided by the carrier-based early warning aircraft are analyzed, and the patrol line configuration model of the carrier-based early warning aircraft is established. The situation of the carrier-based early warning aircraft at the end of the patrol line is fully considered, and the minimum passive detection distance is calculated. According to the position and motion state of the enemy attacking the surface ship and its combat capability, the quantitative research on the position configuration of our carrier-based early warning aircraft is carried out. The effectiveness of the model is verified by Matlab simulation experiments, and suggestions are made for the position configuration of the carrier-based early warning aircraft to meet the needs of combat use.

In order to achieve real-time stable tracking of moving targets and improve the accuracy and success rate of the tracking system, a kernel correlation filtering-based target tracking method with scale adaptation and feature fusion is proposed to address the situation that the traditional kernel correlation filtering algorithm does not track well when the target is obscured or motion blurred. Firstly, in the feature extraction process, color features are added after the original directional gradient histogram features to improve the recognition capability of target features, that is HOG features are fused with CN features, then a scale pyramid is constructed to perform scale estimation to achieve scale adaptation of the target, and finally the model is updated through a multi-peak detection mechanism. Through testing on the OTB2015 dataset, the accuracy and success rate of the algorithm has been further improved, and the algorithm is able to accurately identify targets and track them effectively.

Re-identification technology for pedestrians and vehicles has been successfully applied in the field of intelligence analysis. However, there is a lack of research on re-identification technology for ship targets. In this paper, we propose a double-feature fusion-based maritime defogging re-identification network for intelligence analysis and supervision of ship targets. To reduce the impact of negative samples on features, we adopt a perspective-assisted adaptive query expansion method and a similarity-based feature fusion method. Furthermore, a defogging branch is embedded in the shallow layer of the re-identification branch. This branch utilizes weight sharing technology to extract fog-free features. The defogged image is then reconstructed using upsampling technology and the pyramid model, enhancing the recognition ability of the re-identification network in low-visibility scenarios. Finally, a pseudo-IOU based non-maximum suppression method is proposed to enhance the detection accuracy of ship targets. This method modifies the confidence of the detection frame. Experimental results demonstrate that the proposed method outperforms existing methods, and each module contributes to the network’s performance.

In order to further solve the optimization problem of reconnaissance constellation and strengthen the construction of space-based reconnaissance system, the current optimization methods of reconnaissance constellation are studied and summarized. The design and optimization of reconnaissance constellation has the characteristics of multi-parameter, multi-objective, nonlinear and discontinuous, which is a typical multi-objective optimization problem. Multi-objective evolutionary algorithm is a kind of biological intelligence algorithm based on population, which carries out probabilistic search in decision space according to predetermined heuristic rules. It does not need continuity, differentiability and other conditions of the problem, and can get a group of solution sets close to Pareto frontier within a limited number of search times. It can effectively solve the multi-objective optimization problem and has been widely used in the multi-objective optimization of reconnaissance constellation. This paper discusses the construction of the reconnaissance constellation optimization model and the classification, advantages and disadvantages of the multi-objective evolutionary algorithm, discusses the application of the multi-objective evolutionary algorithm in the reconnaissance constellation optimization, and points out the development direction of the reconnaissance constellation optimization based on the multi-objective evolutionary algorithm.

Aiming at the problem of error in deep-sea DOA(Direction of Arrival, DOA) estimation based on plane wave sound field model, this paper establishes the array signal model of deep-sea DOA estimation under multipath channel based on ray theory. The characterization method of deep-sea multipath ray propagation time and adjacent array element ray propagation delay difference are also derived. Compared with the propagation delay difference expression of adjacent array elements in the traditional plane wave model, the propagation delay difference expression of adjacent array elements derived in this paper is more universal. Combined with the decoherence DOA estimation algorithm, the performance of deep-sea DOA estimation is improved, and the effectiveness of the algorithm is verified by simulation. The research shows that the time delay difference between adjacent array elements is not only related to the distance between array elements and the target azimuth, but also related to the depth of the sound source and the horizontal distance from the sound source to each array element. The construction of the steering vector in DOA estimation should consider the influence of these factors. At this time, DOA estimation is a multi-dimensional parameter optimization problem. Fully considering the acoustic propagation characteristics of the ocean sound field can fundamentally solve the error problem of deep-sea DOA estimation.

This article adopts a combination of Analytic Hierarchy Process (AHP) and Ideal Point Method (IPM) to construct a decision-making model for ammunition supply methods, which includes six influencing factors: operational process time dimension, battlefield advance distance, task importance, task urgency, possibility of resource allocation around and ammunition demand. Firstly, we select four typical ammunition supply methods: fixed point supply, mobile supply, adjustment supply, and accompanying supply, and determine the decision-making attributes of the ideal situation. Then, we calculate the weights of each influencing factor through expert evaluation and scoring. Finally, based on the numerical calculation of each influencing factor given by various experts on the battlefield and the closeness of each ideal wartime ammunition supply method, the one with the highest closeness is the optimal wartime ammunition supply method. Through case analysis, the effectiveness of this method is verified, which has guiding significance for the decision-making of ammunition supply methods in actual wartime, and provides methods and ideas for in-depth research on ammunition supply decision-making.

A scheduling method based on equipment load balancing rules is proposed to solve the problem of unbalanced load of each observing device in traditional space target monitoring resource scheduling. In this paper, the visibility of space targets is taken as the mathematical basis, STK software package is used to forecast the visibility of tracking arcs of space targets, the equipment load balancing scheduling rules are integrated into the traditional scheduling process, and the observation requirements are respectively 3 laps, 4 laps and 5 laps as the input for experimental simulation. The generated scheduling scheme is presented in the form of Gantt chart. Finally, the constructed evaluation index is used to evaluate the value. The experimental results show that the scheduling rules based on equipment load balancing can well achieve the balance of the working time of each observation equipment, and can realize the tracking and monitoring of more space targets.

To solve the problem of low recognition accuracy of radar active jamming in strong noise environment,an algorithm for ER-C-L(Extended ResNet-CNN-LSTM) network model based on one-dimensional composite features is proposed. Firstly, the amplitude, instantaneous frequency, instantaneous envelope of power spectrum and their composite features are taken as network input to compare their recognition accuracy in ResNet-CNN model. The composite features of amplitude and instantaneous envelope of power spectrum with high detection probability and small data volume are selected as the optimal features. Then, the complex features are injammed into the ER-C-L network to identify six new active jamming models. Simulation experiments show that the recognition accuracy of jamming is 98.5% in strong noise environment within the JNR of -10 dB. Compared with other deep learning algorithms such as CNN, ResNet-CNN, extended ResNet-CNN and LSTM, it has higher interference recognition accuracy.

In order to mine the key nodes in the spatial information network in the real task scenario and protect them,based on the mission tasks undertaken by spatial information network in the context of system, node types and information flow relationships are distinguished with the help of operational ring theory. Considering the high dynamic nature of spatial information network, time-varying graph analysis method is used to model the network. Based on the spatial information dynamic network model, the value factor of the operational ring is given by considering the formation time of the operational ring and combining with the traditional complex network indicators, the importance evaluation index of the spatial information network nodes is proposed as time-varying ring betweenness.The effectiveness and rationality of the proposed method are verified by comparing the node importance under indexes of time-varying ring betweenness, degree centrality and number of operational rings through experimental simulation.

Aiming at the importance of the infocommunication wargame as a research platform to improve commanders’ command and planning of infocommunication support, the infocommunication wargame counters are chosen for modelling studies as an important component. Firstly, the modeling framework of infocommunication wargame counters is designed, the modeling steps of entity decomposition, attribute extraction, data description and corresponding products are clarified. Then a pre-categorization ontology-based approach for modelling infocommunication wargame counters is proposed, defining the base classification of entities, the ontology models of different entities and the computer language description of the counters. Finally, with the help of the ontology modelling software Protégé, an experimental analysis is carried out, using the example of infocommunication support in island offensive battles, verifying the feasibility and scientificity of this method.

Aiming at the demand for accurate damage assessment of building targets, a new damage assessment method based on finite element simulation results recognition is proposed. The structural dynamic finite element analysis software SAP-2000 is used for numerical simulation and analysis of target damage, and the pre-assessment of target damage before attack is realized by numerical simulation images feature recognition and quantization combined with the target functional and physical damage level discrimination criteria. The rationality and availability of the method are verified by the simulation of examples.

Underwater multicell single-layer thin metal plate corner reflectors can’t form a relatively stable TS in a large space because of its strong frequency characteristics. To solve the problem, the paper designs the underwater multicell cavity corner reflectors. Then using FEM coupled DBEM solver to simulated its scattering acoustic field in incident wave frequence varies from 5.0 kHz to 15.0 kHz. The results show that the underwater multicell cavity corner reflectors has weak frequency characteristics, obvious decoupling effect and strong scattering ability. Underwater multicell cavity corner reflectors can maintain stable target strength in a large space, and has better reflection ability, so it is an ideal underwater acoustic reflection device.