Fuzzy cognitive map (FCM),as a kind of knowledge graphical soft computing model with both fuzzy reasoning and neural network-like features,is highly compatible with the development direction of the third generation of artificial intelligence driven by both knowledge and data,and has been widely used in various fields.Firstly,the basic concepts and principles of FCM theory are introduced,the latest research progress and major existing problems of FCM are systematically analyzed from the three aspects of construction method,learning algorithm and extension model,and the main directions and key contents of the future research are summarized.Secondly,the application research of FCM in unmanned systems (single unmanned systems,multi-unmanned systems,unmanned-manned systems) are comprehensively reviewed and summarized.Finally,the key research contents and main research ideas of FCM in unmanned systems applications in the future are discussed in depth by analyzing in detail the technical requirements of single unmanned systems driven by autonomous intelligence,multi-unmanned systems driven by swarm intelligence,and unmanned-manned systems driven by mutual trust intelligence.

Considering the complex structure of existing recuperators,which often struggle to meet the real-time controllability requirements of recuperation process,this paper proposes an electromagnetic recuperator based on the principle of a double primary tubular permanent magnet synchronous linear motor (DP-TPMSLM).The differential equations governing the recuperation motion are established by analyzing the forces acting on each component during the recuperation process,and the magnitude of the required recuperator force is clarified.For DP-TPMSLM,the decoupling of cogging and end effects and the improvement in the end structure,the fundamental and second harmonics of the detent force are effectively suppressed,resulting in a significant reduction in thrust fluctuations,as verified by the experiments on a small-scale prototype.Furthermore,an electromagnetic recuperator based on the principle of DP-TPMSLM is proposed,and a co-simulation study is made on applying it to a vehicle-mounted artillery system.The experimental and simulated results demonstrate that the detent force of the improved DP-TPMSLM is reduced to 465.9N,which is educed by 34.4% decrease compared to that of the unimproved structure.Meanwhile,the proposed electromagnetic recuperator effectively achieves the real-time control of recuperation process,fundamentally addressing the issue of collision between the breech ring and the cradle.

In order to investigate the effect of polyurea coating on the protective performance of blast-resistant structure,a multi-layer blast-resistant structure reinforced with polyurea is proposed,and the protective characteristics of blast-resistant structure under the actions of shock wave and fragments are analyzed.The overpressure fitting formula of explosive is calculated and obtained,and out-of-plane displacement of blast-resistant structure is measured using a laser 3D scanner.Experimental results of overpressure and displacement are in good agreement with simulated results.Research results show that the position of polyurea coating has great effects on the protective ability of blast-resistant structure.The protective effect of coating located on blast-facing side of sandwich steel plate is better than those of coating located on the back-blast sides of face plate and sandwich steel plate.It can effectively reduce the penetration rate and impact number of fragments,weaken the energy of the combined load ultimately acting on the back plate,and reduce the vibration amplitude and acceleration at the center of back plate.This study can provide a reference for the design of multi-layer blast-resistant structure.

Unmanned aerial vehicle (UAV) remote sensing detection plays an important role in military reconnaissance,and the polarization detection is to utilize the polarization changes generated by the interaction between polarized light and target to improve the target contrast.However,in complex scenes,the small targets are less distinguishable from the background due to their similar features and the insufficient spatial information,resulting in difficulties in detection.To this end,a polarization camouflaged small object detection (PCSOD)-YOLO algorithm is proposed,and an efficient layer attention module-coordinated attention (ELAM-CA) and a spatial pyramid pooling cross stage partial channel-3D weights attention (SPPCSPC-3DWA) module are designed to capture the polarization features and semantic information of target,enhancing the ability to understand the contextual information.A dynamic small target detection head is designed to enhance the ability to extract the features of small targets through dynamic convolution,and the detected results of small target are outputted using the feature information from different scales and the multi-channel feature information.A polarization image of camouflaged small objects (PICSO) dataset is constructed for the camouflaged small target polarization images.Experiments on the PICSO dataset show that the proposed method can effectively detect the camouflaged small targets,with mAP_0.5 and mAP_0.5:0.95 reaching 92.4% and 47.8%,respectively.The detection rate reaches 60.6 frames per second,meeting the real-time requirements.

Solid propellants with crack defects are susceptible to crack propagation under shock wave loading during their service life,significantly affecting their structural integrity.The dynamic mechanical response and defect-induced damage evolution of hydroxyl-terminated polybutadiene (HTPB) propellants under varying shock wave intensities are investigated using a shock tube apparatus,and the schlieren imaging and 3D digital image correlation (3D-DIC) techniques.Shock wave loading experiments are conducted on both defect-free and crack-defected propellant specimens within a pressure range of 0.3 to 0.9MPa,and the dynamic deformation and damage evolution processes of propellant specimens are captured in the experiments.The results indicate that the deformation of the defect-free specimen exhibits a parabolic profile,and The deformation of the sample increases with the increase in impact pressure.The specimens with different crack depths show different degrees of crack growth under 0.9 MPa impact pressure,and the multiple impacts will result in superimposed damage.The critical failure crack depth ratio is 50%-75%.Residual specimen analysis reveales that the matrix cracking,particle debonding,and particle fracture are the primary failure mechanisms.These findings provide valuable insights for assessing the structural integrity of solid rocket motors under ignition shock condition.

The separation of tailstock from projectile and the forward-throwing of tailstock have become significant challenges in the unmanned development of breech-loading howitzers.These challenges are attributed to the influence factors such as artillery structure and charge form.However,there is a lack of available data for reference in this aspect of research.A multi-gunpowder adaptive tailstock forward-throwing technology based on pressure difference separation is proposed,and a tailstock structure suitable for multi-gunpowder launch is designed.The stable and unstable regions of the tailstock-and-projectile separation are analyzed through the establishment of internal ballistic model,gas flow model,tailstock detachment model and so on.And a strategy to adjust the stability domain by aperture is proposed.The universal law of the interaction among gas chamber pore,gas chamber pressure,and tailstock detachment position are summarized.And the relationship between parameters such as muzzle velocity and separation velocity of projectile are also analyzed in this process.The tailstock forward-throwing analysis of a howitzer is presented.The results indicate that the cross-section radius of shear pin should be less than 4.27mm,and the wall thickness of gas chamber should be greater than 6.16mm.The aperture radius for the tailstock forward-throwing should be in the range of 1.00mm-2.75mm,and the stable region ranging from 1.00mm to 1.80mm and the non-stable region ranging from 1.80mm to 2.75mm are divided by taking1.80mm as a boundary.The position of tailstock detachment varies more when the aperture radius is more central.The aforementioned research will establish a theoretical and technical foundation for the advancement of rear loading and unmanned technology for rear loading howitzers.

The influence of strength of jacket materials on the penetration performance of tungsten fibre/Zr-based bulk metallic glass (WF/Zr-MG) rod to obtain the armor piercing rods made of jacketed WF/Zr-MG matrix composite materials with high penetration efficiency.A 60mm-thick C45 steel plate is impacted by a composite structure rod made of two types of jacket materials (Q235 and 30CrMnSi steel) with an impact velocity of 1700-2000m/s in penetration experiment.Additionally,the erosion mechanisms of two types of rods are analyzed using the finite element analysis software.The experimental results indicate that the erosion mode of 30CrMnSi/ WF/-Zr-MG rod gradually changes from “co-erosion” in the initial penetration stage to “bi-erosion”.The jacket separates from the rod and does not play a role in protecting the rod,thus splitting the WF/Zr-MG rod to result in the unstable penetration performance of 30CrMnSi/WF/Zr-MG rods.The penetration efficiency fluctuates greatly within the experimental speed range with a difference of more than 50% (the highest penetration efficiency is 1.68,and the lowest penetration efficiency is only 1.03).In contrast,Q235/WF/Zr MG rods maintaine the penetration efficiency above 1.5 at all the experimental speeds.The Q235 jacket tightly adheres to the WF/-Zr-MG rod during penetration,and fails in a “co-erosion” manner with the rod,therefore suppressing the initiation and expansion of cracks inside the rod,eliminating the “splitting” phenomenon during penetration,providing a radial strength for the rod,and improving its penetration performance.The experimental results show that a suitable jacket material can help increase the penetration stability of WF/Zr-MG rods,but it is not necessarily the case that the higher the strength is,the better the penetration effect is.This conclusion provides theoretical support for the design of armor piercing rods made of jacketed WF/Zr-MG materials.

Ultra-high molecular weight polyethylene (UHMWPE) is widely used in the protective field due to its lightweight and exceptional mechanical properties,which can effectively resist projectile impacts.However,the micro-scale anti-penetration mechanism and ballistic impact damage modes of UHMWPE remain to be further investigated. This study focuses on two-dimensional woven and unidirectional (UD) UHMWPE composites,establishing a finite element analysis model for ballistic impacts that considers the microstructural characteristics of fiber-reinforced composites.Numerical simulations of normal and oblique penetration were conducted for composite targets with varying thicknesses and fiber layer counts,and the results were compared with experimental data to verify their reliability.Subsequently,the damage modes and energy absorption characteristics of the composite plates under different impact conditions were investigated.The results indicate that the damage modes of the composite plates are similar across different speeds,with lower speeds resulting in larger deformation areas and less energy absorption,reflecting a tendency for the material to experience extensive plastic deformation rather than localized brittle fracture under low-speed impacts.As the penetration angle decreases,the interaction time between the projectile and the target material significantly increases,enhancing energy transfer and absorption.This study not only delves into the ballistic impact mechanical response of UHMWPE composites,but also clarifies the damage modes and energy absorption mechanisms of the material under different impact conditions,providing a solid theoretical foundation for the design of composite plates with high-efficiency anti-penetration performance.

A multi-dimensional enhanced particle swarm optimization algorithm (MDEPSO) is proposed to address the problem of insufficient global search capability and susceptibility to local optima in the 3D trajectory planning process of unmanned aerial vehicles using classical particle swarm optimization algorithms.This algorithm first introduces improvement factors to dynamically adjust inertia weights in various stages of particle optimization,enhancing population adaptability and overcoming local optima; Secondly,relying on dynamic constraint equations to enhance learning factors promotes more efficient information sharing between particles and improves the algorithm’s self-learning ability; Subsequently,the advantages of orderly integration of chaos initialization and elite reverse learning evolution strategies were utilized to re plan the particle swarm evolution process,enhance the balance and diversity of particles in the iterative process,and improve the convergence accuracy of the algorithm.In the experiment,through horizontal comparison of test functions and vertical application in complex 3D task scenarios,the multi-dimensional enhanced particle swarm optimization algorithm showed an improvement in the UAV trajectory planning ability compared to the classical particle swarm algorithm in the new multi-dimensional objective function indicators.It demonstrated good effectiveness and competitiveness among the five comparison algorithms.

In order to enhance and test the fragment penetration resistance of the material structure,the polyurea/aramid fiber aluminum alloy composite protection structure was constructed by spraying polyurea technology with polyurea, aramid fiber and 2024-T351 aluminum alloy materials,and the mechanical properties of polyurea are measured and analyzed. By comparing the protection properties of composite materials under different coating thicknesses and methods,the ballistic limit velocity of different protection structures were obtained,and the failure modes and mechanisms of materials were analyzed.The relationship between coating thickness and protection effect was further studied,and the optimal coating thickness ratio was determined. The results show that the local damage degree of aluminum alloy composite plate coated with 2mm polyurea/2mm aramid fiber is small. The ballistic limit velocity of the coated composite target plate is increased by 96m/s and the protective effect is increased by 36.64% compared with the uncoated condition. The thickness of the protective coating has limited effect on the ballistic limit velocity. Considering the surface density and material strength,the numerical simulation results show that the optimal thickness of polyurea/aramid fiber coating is 4mm to 6 mm,and the optimal thickness ratio is 6:4 ratio of polyurea to aramid fiber for the fragmentation resistance of 4mm aluminum alloy plate.

In order to address the issue of the poor target recognition performance of laser imaging fuze under smoke,dust,and camouflage interference,a target recognition algorithm using linear array laser and linear array near-infrared compound imaging is proposed.A calibration matrix is established according to the imaging model,and the spatial mapping relationship between the laser point cloud and the near-infrared image is obtained.A deep learning-based target recognition algorithmic framework is constructed,and a voxel fusion module is proposed at the data input layer to enhance the point cloud by encoding near-infrared pixel-level features.A BEV fusion module is proposed at the middle layer to achieve feature-level fusion with adaptive dynamic adjustment of bimodal feature weights.The proposed algorithm is validated based on a custom simulation dataset.The experimental results show that the proposed algorithm can significantly improve the accuracy of target recognition under smoke,dust and camouflage interference.

The anti-jamming capacity of traditional digital beamforming system is limited by the quantization accuracy of analog-to-digital converter (ADC).To address this situation,this paper proposes a hybrid analog-digital adaptive beamforming method.The interference signals are suppressed preliminarily by introducing the analog beamforming at the radio frequency channel,which prevents sampling saturation.Subsequently,the interference signals are suppressed with the digital beamforming technology.A hybrid analog-digital adaptive beamforming signal model is established.The proposed hybrid analog-digital method is theoretically derived,and its anti-interference performance is analyzed.The simulated results demonstrate that the proposed method can effectively reduce the impact of quantization accuracy and has the excellent performance for different interference intensities.Compared with traditional digital beamforming method,the superiority of the proposed method for blanket jamming suppression is also demonstrated.

In order to solve the thermal failures such as thermal buckling caused by excessive radial temperature difference of friction elements in the wet multi-disc shifting clutch,the numerical simulation and experimental research are made on the homogenization of radial contact pressure and the gradient design of friction coefficient of friction elements.Firstly,based on the compact structure of clutch,a back plate is designed and topologically optimized.The stiffness of the optimized back plate is improved and the deformation trend of friction elements is reduced,thereby reducing the maximum pressure difference and temperature difference of friction elements by 28.64% and 28.48%,respectively.Then the texture treatment and test are carried out on the surface of friction plate.It is found that the friction coefficient decreases with the increase in the texture line density.A gradient design method for the texture density decreasing along the radial direction of friction plate is proposed,reducing the maximum temperature difference by 17.69%.Finally,the optimized back plate and textured friction plate are comprehensively applied to homogenize the radial contact pressure and decrease the radial friction coefficient.Compared with the original design,the maximum temperature difference and thermal bending moment are reduced by 41.73% and 45.33%,respectively.This study provides a theoretical basis for the design of higher power density clutches.

In air-ground collaborative systems,the coordinated landing of unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs) is of paramount importance for extending the task scenarios of heterogeneous intelligent agent clusters.Current trajectory optimization-based autonomous landing methods couple the temporal and spatial dimensions by designing the optimal control laws for joint trajectory optimization.However,the optimization objective function design is relatively complex,and it cannot fully utilize the actuator’s optimal performance.A novel spatio-temporal decomposition planning (STDP) method is proposed to address the excessive coupling of time and space in traditional trajectory optimization methods.The STDP method optimizes the landing trajectories separately in spatial and temporal dimensions,enabling UAVs to adopt more aggressive flight strategies in complex scenarios.Furthermore,the objective function is meticulously designed to account for the UAV’s landing time and motor power consumption model,formulating a second-order cone programming problem to expedite the solution process while ensuring high-quality and efficient solutions.Simulated results indicate that,compared to spatio-temporal coupled planning methods,the STDP method generates the trajectories that closely adhere to kinematic constraints,substantially reducing the task completion time and enhancing the mission efficiency.Additionally,the empirical tests in real-world scenarios confirm the reliability and efficacy of STDP method in practical application.

To rapidly and accurately calculate the correction command of high-spin and tail-controlled correction projectiles,a correction capability prediction model based on hyperband algorithm-Bayesian optimization-long short-term memory (HBBO-LSTM) network is proposed for the prediction problem of correction capability.A 7DOF ballistic model of the high-spin and tail-controlled correction projectile is established.It is numerically simulated using the Runge-Kutta method to generate a large amount of sample data.By analyzing the dataset,a preprocessing method based on Ramanujan’s approximation formula is proposed to preprocess the original dataset for obtaining the sample data with uniform spatial distribution.A HBBO-LSTM network prediction model is constructed,and the optimal structural parameters are obtained through training.A learning rate decay strategy combining cosine annealing with restart mechanism and exponential decay is proposed to ensure the speed and stability of training process.The proposed model is compared with the long short-term memory network,gated recurrent unit network and back propagation network models on the same test set through simulation.It is also evaluated against the numerical integration method for 4DOF correction projectile ballistic equation.The results show that the prediction accuracy of the HBBO-LSTM network model is superior to those of other models with an overall mean squared error of 0.17m² and an overall mean absolute error of 0.33m.Additionally,the HBBO-LSTM model outperforms the numerical integration method in both computation time and prediction accuracy.This demonstrates that the HBBO-LSTM network model has high feasibility and reference value.

The deformation and stress of typical additively manufactured frame components are simulated by using transient heat source algorithm,thermal cycle curve algorithm,full thermal cycle algorithm and intrinsic strain algorithm,and the prediction accuracies and calculation efficiencies of the different algorithms are analyzed.The results show that the maximum deformation position predicted by the transient heat source algorithm is the top four corners of the frame,and the stress is mainly distributed in the corners and top areas of the frame,which is in good agreement with the experimental results,and the prediction accuracies of feature point deformation and stress are 96.59% and 95.01%,respectively,and the calculation time is 326h;The prediction accuracy of the thermal cycle curve algorithm is comparable to that of the transient heat source algorithm,but the calculation time is shortened to 117h,and the predicted deformation contour and stress curve are in good agreement with the experimental results.Compared with the first two algorithms,the prediction accuracies of the full thermal cycle and intrinsic strain algorithms for feature point deformation are 85.68% and 65.86%,respectively,and the predicted deformation contour is quite different from the experimental results.The reliabilityies of the full thermal cycle and intrinsic strain algorithms are low,but their calculation times are shortened to 4h and 2h,respectively,and their efficiencies are significantly improved.

An non-parametric model of multi-stage synchronous induction coilgun (MSSICG) based on the particle swarm optimization and recurrent neural network (PSO-RNN) algorithm is proposed to solve the problems such as multi-physics field coupling and long iteration time of existing optimization methods.And the ejection velocity of the armature is also predicted by the model.A sample set with the turns per coil,triggering time and trigger position as inputs and the ejection velocity as output is obtained through the orthogonal and random experiments.The RNN algorithm is used to train the sample set and the non-parametric model is established.The parameters of the RNN model are further optimized by the PSO algorithm,to improve the prediction performance of the non-parametric model.The ejection velocity of the armature is predicted using the proposed PSO-RNN model and compared with the experimental result.The MSPE,MAPE,and RMSE of the non-parametric model are 0.0028,0.036,and 2.18,respectively,which are reduced by 39%,38%,and 46% after the optimization of PSO.The difference between the predicted and experimental velocities is 1.2m/s with the error percentage of 1.8%,which is less than 5%.The study provides a novel idea for the modelling and engineering design of MSSICG.

The mechanical response,crack morphology and evolutionary path of NEPE propellant during the crack propagation are investigated through single-edge notched tension (SENT) experiment at a tensile rate of 100mm/min.Based on the bond-based peridynamic (BBPD) theory,the failure process of crack propagation in NEPE propellant is simulated,the critical stress intensity factor of fracture toughness is calculated,and a fracture criterion considering the burning rate of the propellant is proposed.Experimental results show that a blunting fracture occurs in NEPE propellant during crack propagation.Prior to macroscopic crack propagation,an internal damage takes place in the propellant.The BBPD method can accurately simulate the crack propagation process of NEPE propellant,compute the stress intensity factor,and visualize the internal damage.This suggests that the peridynamic technique provides a new approach to simulate the fracture process of NEPE propellant.

The mixing process,as a crucial step in the fabrication of solid propellants,typically involves the incorporation of particulate phases such as aluminum (Al),ammonium perchlorate (AP),and RDX into a polymeric binder matrix.The binder slurry is applied onto the solid particles through mechanical kneading and stirring.The dispersion accompanied by dynamic blade kneading during the co-mingling of solid particulate phases in a mixer is simulated based on the Mixture solid-gas-liquid multiphase flow model.Dynamic rheological measurements of slurries with varying solid contents (0%-95%) are performed to construct a rheological model of propellant slurry.Considering the dynamic changes in granular concentration and their impact on local rheological properties,the mixing dynamic processes at different granular injection flow rates are simulated.The analysis focuses on the temporal patterns of granular concentration,pressure fields,and torque under various operating conditions.The results indicate that the proposed numerical simulation method is in good agreement with experimental results in Ref.[39] with an average error of less than 15%.The study reveals that the greatest pressure occurs at the tips of the near and far blades,while a low-pressure zone exists in the middle of the blades.During mixing,the blade torque exhibits a serrated fluctuation,and gradually increases with the addition of the particulate phase.A slight increase in the granular injection flow rate results in a minimal torque change.However,a significant increase in flow rate could lead to a torque increase of up to 90%.In the continuous feeding mixing process,the torque value at the farthest blade from the axis of rotation continues to rise,eventually reaching an average value 19 times that at the initial stage.This research provides insights for enhancing the efficiency and safety studies of solid propellant mixing processes.

Gel propellant has the advantages of controllable combustion,easy to storage and good safety,which has potential application prospects in space micro-propulsion technology.Thus,in order to effectively improve the pipeline transportation efficiency of gel propellant and study the factors affecting its ignition and combustion characteristics,the rheological properties and the ignition and combustion characteristics of hydroxylamine nitrate (HAN)-based electronically controlled gel propellant are experimentally studied by using a rotary rheometer and an electro-chemical combustion diagnostic system.The results show that the viscosity of gel propellant can be dramatically declined by increasing the shear force and rising the temperature.When the gel propellant is subjected to a significant shear force,its loss modulus is more dominant than the storage modulus under external shear,and it begins to change from a solid to a fluid.The viscosity of gel propellant will increase rapidly when the external shear action disappears,which highlights the solid properties.In this experiment,the most suitable electrode material for HAN-based electrically controlled gel propellant is Mo electrode,which has the lowest ignition delaytime of 0.3s and the fastest volumetric burning rate of 0.21mL/s at 250V (25℃).On the other hand,the temperature has a significant effect on the ignition delay of gel propellant.The ignition delaytime of gel propellant decreases from 5.3s to 1.5s with the rise on temperature at 175V.But the temperature has no obvious effect on the volumetric burning rate.Combining with R-type thermocouple,the flame temperature distribution of gel propellant measured based on the thermocouple temperature measurement technology is in the range of 1200-1400K.

Coral sand is widely used in military protection projects of islands because of its convenience and well anti-explosion buffering performance.It is necessary to obtain the shock Hugoniot data of coral sand before investigating the high-pressure shock equation of state.A shock wave test system for multi-medium is designed based on continuous pressure-conducted electrical resistance probe.The test system can be used to determine the detonation wave and shock wave time history curves of explosives,standard material and tested material in a explosion test.Then the shock Hugoniot curve of the material under test could be calculated based on the impedance matching principle.A feasibility test is carried out using water as the test material to verify the reliability of the method.Finally,the shock Hugoniot curve,represented by shock wave pressure P and particle velocity U_p, of coral sand is determined using the proposed method,which is compared with the Hugoniot data of quartz sand.The experimental results show that the shock Hugoniot curve of test material can be conveniently and reliably determined based on the continuous testing system of multi-medium shock waves and the impedance matching principle.The exploration work provides a supplement to the experimental research on the shock equation of state for large-scale heterogeneous materials.

The trajectory tracking control of unmanned vehicle with a sequence of human-like behavior primitives as the desired trajectory is studied.A trajectory tracking control method combining the offline optimization of behavior primitives and the online coordination of game is proposed.Based on the behavior primitive library extracted directly from real driving data,a model-based nonlinear optimization method is applied to generate a behavior primitive library that satisfies the constraints of vehicle kinematic properties.The optimal control parameters for each category of primitives in the behavior primitive library are obtained by offline optimization using the particle swarm algorithm,and a multilayer perceptual machine is applied to establish the mapping relationship between the optimal parameters of controller and the categories of behavioral primitives.Based on the optimization of the control parameters within the primitives,the online game coordinated control method is used as the core to generate the optimal control parameter between the behavior primitives.The experimental results show that the proposed trajectory tracking control method can significantly improve the tracking accuracy of the behavior primitive sequences and effectively solve the problem of stable and smooth transition between independent behavior primitives.

For the cooperative guidance issue of high-hypersonic re-entry gliding vehicles to simultaneously hit a target at a specified angle in a complex environment,a cooperative guidance law based on meta-learning and reinforcement learning algorithms is proposed.Considering the interference caused by complex combat environment,a Markov decision model for the cooperative guidance issue is established,taking the gliding vehicles’ motion status and proportional guidance factor as the state space and action space.A reward function is designed by comprehensively considering the vehicle-target distance,remaining flight time difference,and overload situation for multiple gliding vehicles attacking a target.Based on meta-learning theory and reinforcement learning algorithm,the proximal policy optimization algorithms are combined with the gated recurrent units to learn the common features of similar cooperative guidance tasks.This approach enhances the accuracy of cooperative guidance strategies in complex interference environments to achieve the constraints on angle of attack and attack time,while also improving the adaptability of cooperative guidance strategy to different combat scenarios.Simulated results indicate that the proposed cooperative guidance law enables multiple aerial vehicles to simultaneously attack a target at a specified attack angle in complex battlefield environment and quickly adapt to new cooperative guidance tasks.The cooperative guidance law maintains good performance even when the cooperative combat scenario changes.

There are complex multi-layers accumulation and thermal effects in the wire arc hybrid additive-subtractive manufacturing process.The manufacturability is affected by many factors and difficult to be evaluated effectively.These factors make the process planning difficult to implement and inefficient.To address the aforementioned issues,a process planning method of wire arc hybrid additive-subtractive manufacturing considering weld bead sagging phenomenon is proposed.The relationship between forming quality and deposition height in different areas of wire arc additive manufacturing is studied,and the implicit models of target part and machining tools based on level set functions are constructed.A preliminary machining sequence construction method is proposed based on the matrix of the heights of the segmentation planes.The evaluation methods for tool interference and forming quality are established,and a process planning model based on particle swarm optimization algorithm is developed.The performance of the proposed method is verified through simulation and experiments.The results indicate that the proposed method can obtain an effective alternative scheme for the wire arc hybrid additive-subtractive manufacturing process,and is more efficient and adaptable for the wire arc additive manufacturing compared to traditional methods.

A general dynamic analytical model is proposed to study the non-stationary vibration of corrugated sandwich panels under moving random load.The governing differential equation of a single cell unit is derived by using a simplified first-order shear deformation theory and Hamilton principle.Based on the reverberation-ray matrix method and the pseudo excitation method,the recursive technique is introduced to effectively simulate the global response of the whole structure under moving random loads.In addition,a unified loading mechanism for moving random loads is proposed by dividing the continuous load moving process into three stages,and the accuracy of the calculation model is verified by finite element simulation software.Then the calculated results are compared with the simulation data of the finite element software.The findings indicate that the Bragg band gap of the structure can be effectively widened by adjusting the thickness and inclination angle of the corrugated sandwich panel.The low-velocity moving random loads will cause more vibration behaviors within the action time;The study can provide theoretical support for the design and optimization of corrugated sandwich panels under complex load conditions,and offers the valuable insights for the development of related equipment in aerospace and marine engineering.

The complexity and variability of noise in modern wireless radio communication environment and the great diversity of the duty cycles of signals in different sensing periods cause the decline in the sensing ability of signal spectrums,even lead to interference to authorized users by unauthorized users.An intelligent wireless signal spectra sensing method based on the estimation of kurtosis is proposed to solve the above problems.A deep neural network framework is constructed based on the idea of multi-scale skip connections,which usestypical non-Gaussian noise distribution (McLeish distribution) as the general background noise.The multi-scale features of target signal are captured by means of the attention mechanism.The kurtosis value of target signal is estimated under the condition of uncertain duty cycle in the sensing period.The wireless signals under different noise models are sensed by judging the estimated value.The simulated results indicate that the average detection probability reaches over 84.3% when P_f=0.02 and duty cycle 0.5≤η<1 under the condition of SNR≥-10dB.And it reaches over 96.1% when noise power estimation error ε≤2 and P_f=0.01.It is proven that the proposed method has strong resistance to duty cycle and noise power uncertainty,and has certain theoretical research significance and engineering practical value.

Aiming at the problem of simultaneous attack of multiple missiles against the important targets,a three-dimensional fixed-time attack proportional guidance law based on variable power sliding mode is proposed for multiple missiles.A missile-target dynamics model in three-dimensional space is established.To reduce the complexity of designing a control method in three-dimensional space,a reference plane is determined in three-dimensional space,and the missile-target state vector in three-dimensional space is decomposed into two components parallel and perpendicular to the reference plane.Control methods are designed separately in the reference plane.The method parallel to the reference plane is based on the proportional guidance method,The tangential and normal accelerations are designed as the control inputs to drive the missile to reach the remaining flight time consistency before the desired attack moment.Additionally,for the component perpendicular to the reference plane,a guidance law is designed using an improved sliding mode control method based on variable power to achieve the rapid convergence in the early stage and the stable control in the terminal stage for the multi-missile system.When the consistent control of both components along the reference plane is realized in a preset attack time,the multi-missile system can complete the synchronized attack in the three-dimensional space.Furthermore,the synchronized attack on the target by the multi-missile system in the asynchronous launching scenario can be realized by compensating the launch delay of each missile in the guidance law.The performance of the proposed three-dimensional guidance law is verified by simulation,which is characterized by fast convergence and high stability.The guidance law is not only applicable to synchronous launching scenarios,but also adds only the launch delay of each missile to the input to complete the consistency control of attack time.

Amphibious vehicle is a mobile platform capable of operating in both terrestrial and aquatic environments,and has significant application value and development potential in both military and civilian fields.The development history of amphibious vehicles is reviewed,and the characteristics and development trends of different types of amphibious vehicles are compared and analyzed.The key technologies for the navigation of amphibious vehicles on water are expounded from three aspects:modeling and simulation,high-speed amphibious vehicle design,and navigation control.The difficulties and challenges in achieving the unmanned operation of amphibious vehicles on water are discussed based on the research progress of unmanned technology for amphibious vehicles,and the future research direction of amphibious vehicles is prospected.

The impact of shock waves in front of projectile under high-speed flight conditions is studied to improve the ranging accuracy of projectile-borne pulse laser fuze. Based on the traditional pulse laser echo model,a semi-analytical method is proposed to model the pulse laser echo signals disturbed by shock waves,and the concept of the optimal confidence interval is introduced to construct a ranging data distribution and error evaluation model. A Reynolds average navier-stokes (RANS) solver is used for aerodynamic flow field calculation to obtain the density field distribution around the projectile by taking a typical high-explosive anti-tank cartridge as the research object. The optical path difference (OPD) and Strehl ratio (SR) are used as the evaluation criteria for the aerodynamic optical effects,and a high-precision fourth-order Runge-Kutta method is employed to trace the laser beam passing through the non-uniform flow field in front of the projectile. The effects of different flight Mach numbers,target angles,and detection distances on the pulse laser echo waveforms and detection accuracy are analyzed through simulation. The simulated results show that the ranging performance of pulse laser fuzes below 3 Mach is slightly affected,and the systematic error and random error reach the minimum and maximum,respectively,at 4 Mach. This study provides theoretical foundations for suppressing the aerodynamic optical effects of pulse laser fuzes under high-speed flight conditions.

In order to study the variation law of the penetration power of shaped charge jet under lateral disturbance,the finite element models of the dynamic penetration of shaped charge jet are established,and the evolutionary process of jet penetration from static to dynamic conditions is analyzed.Based on the virtual origin theory and dimensional analysis method,a virtual source is introduced to characterize the jet in the dimensional analytical model.An engineering prediction model for dynamic jet penetration depth,which considers lateral disturbance,jet and target plate strength,is established.A jet dynamic penetration test based on a rocket sled is designed and conducted,and the numerical simulation and prediction models are validated.The research results indicate that the dynamic penetration depth of shaped charge jet decreases exponentially with the increase in the lateral disturbance of target plates.The numerically simulated results,prediction model,and experimental results are in good agreement with each other,and both the prediction model and numerical simulation have a certain degree of accuracy and effectiveness.The proposed prediction model can describe the influence of lateral disturbance on the penetration power of shaped charge jet,thus providing a basis and reference for evaluating the dynamic damage power of formed charges.