Aiming at the problem of equipment system-of-systems effectiveness prediction, an equipment system-of-systems effectiveness prediction method based on extreme gradient boosting （XGBoost） is proposed. First, the effectiveness prediction process based on XGBoost is given. Then XGBoost is used to establish a nonlinear mapping model between these indicators and effectiveness to realize the prediction of equipment system-of-systems effectiveness. In the process of model construction, the grid search is used to determine the optimal parameters of the model, which avoids the blindness of artificial setting. Taking the effectiveness prediction of a certain air-defense missile weapon system as an example, the above-proposed method is validated.

The rudder structure has a significant influence on the dynamic performance of flying vehicles in hypersonic flight, and natural frequencies of the rudder structure is one of the most important evaluation indexes. Based on the basic theory and method of structural bionic topology optimization design, the bionic topology optimization design of rudder structure stiffened with stiffeners is studied. The results show that the bionic topology optimization can quickly obtain a clear skeleton layout. Compared with the initial rudder design scheme, the optimized skeleton layout can reduce the weight of the structure by 21.5% while increasing the first-order natural frequency of the rudder structure by 11%, which validates the efficiency of the bionic topology optimization design of the rudder skeleton design.

For the problems of metal launch tube structure, such as large weight, poor corrosion resistance，easy deformation of welding and less freedom in design, the design of carbon fiber reinforced polymer（CFRP）composite launch tube was researched to meet the more stringent requirements of weapon system for the volume, weight and environmental adaptability of the launch tube. In this research, CFRP and steel lining were used for main body. Through structural optimization and functional laying design, it gives good light weight and high strength characteristics to the main body of launch tube. Relevant tests such as air test, water pressure test, hoisting test, transportation test and launching test were completed ,which verified the correctness of the design.

According to the structure and function characteristics of the surface-to-air missile weapon system, the index system of effectiveness evaluation is constructed, and the index weight is calculated by the improved combination weighting method. Then, an improved grey evaluation model is established to solve the problem of grey interference and judging objects only by their clustering coefficient. Finally, the model is used to calculate the effectiveness of the surface-to-air missile weapon system. The effectiveness evaluation results are analyzed to verify the feasibility of the model.

Augmented reality technology and natural human-computer interaction technology are used to design and develop a data-driven augmented reality electronic sand table for command and control system.The sand table system adopts a modular design. Virtual and real fusion display of the battlefield situation can be realized based on augmented reality technology. Through multi-channel human-computer interaction and coordinated plotting functions, the combat efficiency of the commander is significantly improved. Real combat data or simulation data drives the development of military operations and enhances the reliability of the system in actual combat. In addition, the system is easy to ope-rate, convenient to conduct, and lightweight.

Different from traditional missile loading method, the missile automatic loading technology is a new loading method that can meet the satisfaction of unmanned combat platform. This paper first introduces existing missile loading methods at home and abroad. The differences of “push-loading” and “vision servo manipulator plus flexible and parallel hoisting device” are also analyzed. The research of the latter one is mainly conducted. The manipulator control technology based on improved path planning, machine vision technology and flexibly adaptive adjustment technology are proposed, thus providing ideas for the research of missile automatic loading and unmanned smart combat.

Compound control scheme with aerodynamic force and lateral thrust is proposed based on the established short-period, linearized motion model of compound-control missile. The aerodynamic control subsystem uses three-loop control structure. Overload loop adopts PI control. The angle of attack loop and the angular velocity loop adopt active disturbance rejection control (ADRC). Then aerodynamic/lateral thrust distribution strategy is designed according to the fuzzy control and the ignition logic of the lateral thrust control subsystem is designed with the vector synthesis method. Finally, a specific simulation scenario is designed and verified in Matlab. The results show that a small miss distance can also be ensured during the interception of high-altitude targets. The composite control scheme ensures that the system has rapid overload response characteristics and good stability, which proves that the algorithm in the paper is effective.

In view of poor filtering and noise reduction of target angle data in passive tracking, this paper proposes a self-adaptive modified angle filtering algorithm. It introduces the pseudo-acceleration and obtains the adaptive filter gain by accumulating the residual error of data over a certain period of time. This algorithm has an important engineering significance. For the sensor of passive detection, its measured data can be filtered to improve the guidance precision. Amid interference countermeasures, the measured data can be filtered to reduce noise, and the angular velocity and other information can be obtained to provide auxiliary factors for data fusion. In addition, under the collaborative tracking condition with only two-dimensional angle information, it can provide the target data time alignment method for triangulation so as to improve the positioning accuracy.

For the problem of early divergence of the guidance control loop when the missile intercepts near space targets, the impact of radome error slope is analyzed in this paper from perspective of engineering application. To reduce this impact, the compensation of effective navigation ratio is proposed, and the known time constant information of control loop is introduced into the design of guidance law. The guidance law is obtained by nonlinear inversion method. The simulation results show that the new guidance law can not only ensure the effective navigation ratio by suppressing the influence of radome error slope, but also delay the divergence of missile line of sight (LOS) angular speed by reducing the equivalent time constant of system dynamics, so as to improve the guidance accuracy of missile.

Aiming at the problem that the traditional jamming algorithm cannot adapt to the change of signal environment, the Q-learning algorithm and the hypothesis method of "cutting" are combined to apply to the design of jamming waveform, so that the jamming waveform can achieve the effect of adaptive radar signal length change. The algorithm is mainly aimed at jamming the radar detection link. Constant false Alarm rate (CFAR) is adopted as the environment interaction model, and the sampling time and forwarding time of intermittent sampling signals are adjusted adaptively through enhanced learning. On this basis, the radar signals of unknown length are processed by "cutting" to achieve the purpose of optimal interference. Finally, simulation is carried out to realize the jamming of unknown radar signal. The simulation results show that the reinforcement learning algorithm can make full use of the historical data when making decision under the condition of uncertain signal model, and can achieve better interference effect compared with the traditional algorithm.

It is difficult to obtain the video image data of air maneuvering military targets under the complex actual combat background. The lack of training data limit the performance of target detection and recognition algorithms based on deep learning. Thus, this paper proposes an improved algorithm based on the deep convolutional generative adversarial networks (DCGAN). The enhanced algorithm could generate air maneuvering target data by injecting random vectors. Besides, the discriminator in this paper uses an improved Wasserstein distance measurement to generate the data distribution of the sample and the real sample, thereby optimizing the loss function and improving the stability of the DCGAN model training process and the quality of the generated image. Experimental results show that the improved DCGAN image generation algorithm can generate air maneuvering military targets images in various actual scenarios. After the improvement, the model training process is stable, the loss function fluctuations are significantly reduced, and the generated images are more realistic. The FID and IS scores in 32×32 resolution images have increased by 9.4% and 7.6% respectively. The FID and IS scores in 64×64 resolution images have increased by 5.9% and 4.8% respectively.

In order to evaluate the marching launch reliability of defense combat vehicle, dynamic virtual prototype modeling and simulation technologies are used to study the marching launch. According to the three-dimensional solid model of the combat vehicle, the multi-body dynamics software is adopted to establish the multi-body functional virtual prototype model. The measured load-displacement curve is used to establish a non-linear oleo-pneumatic suspension model. The contact force between launching box and missiles is simulated by using the non-linear parallel spring damping model. Based on the pavement power spectral density function, a three-dimensional random pavement spectral model is established by using the Sayers theory. The comprehensive dynamic virtual simulation tests were carried out for the defense combat vehicle, and the dynamic characteristics of guns and missiles were obtained during marching launch. The simulation results show that the combat vehicle meets the launching march requirements under the corresponding road conditions and vehicle speed. The simulation results are basically consistent with the results of launching separation test. The simulation analysis effectively guides the design of defense combat vehicle and ensures the success of the launching separation test.

In recent years，the rapid development of near space vehicles has attracted worldwide attention on the construction of near space defense system, and some countries are conducting the specific research into defense technology and equipment. In this paper, the penetrating capabilities of near space hypersonic vehicles are introduced. The adaptability is analyzed regarding main foreign air and missile defense system performance to the interception of near space hypersonic vehicles and the development trends of defense technologies against near space vehicles are studied. Finally, the penetration strategies of near space vehicles are discussed, providing reference for the development of attack-defense confrontation.

In light of new-type weapon equipment in terminal defense-hypervelocity projectile (HVP) by electromagnetic launch, this paper first overviews the concept of electromagnetic rail gun, its system and working principle. Then the features of HVP by electromagnetic launch are analyzed. Based on this, foreign and domestic research status is reviewed. Besides, the key technologies to promote product serialization are discussed, among which includes multi-mode combined guidance, electromagnetic compatibility, etc. Finally, based on research achievements analysis related to HVP at home and abroad, this paper indicates that HVP will develop towards systemization, intellectualization, networking and coordination from product lifecycle management and general development model.