Research on virtual entity decision model for LVC tactical confrontation of army units

According to the requirements of the live-virtual-constructive(LVC)tactical confrontation(TC)on the virtual entity(VE)decision model of graded combat capability,diversified actions,real-time decision-making,and generalization for the enemy,the confrontation process is modeled as a zero-sum stochastic game(ZSG).By introducing the theory of dynamic relative power potential field,the problem of reward sparsity in the model can be solved.By reward shaping,the problem of credit assignment between agents can be solved.Based on the idea of meta-learning,an extensible multi-agent deep reinforcement learning(EMADRL)framework and solving method is proposed to improve the effectiveness and efficiency of model solving.Experiments show that the model meets the requirements well and the algorithm learning efficiency is high.

Targeted multi-agent communication algorithm based on state control

As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.

水下激光填丝直接能量沉积法制备贫双相不锈钢2101的组织和织构演变

贫双相不锈钢2101(LDX 2101)是一种可以替代304奥氏体不锈钢的低镍不锈钢材料,以良好的经济性、力学性能和耐腐蚀性而被广泛研究,在核电工程中具有广泛的应用前景。针对核电工程水下维修技术背景,利用光学显微镜和电子背散射衍射等方法,研究了水下环境激光填丝直接能量沉积工艺制备的贫双相不锈钢2101的微观组织和织构演变。结果表明,水下环境对熔池的快速冷却作用抑制了铁素体向奥氏体的转变进程。由于铁素体的表面能最低,大多数铁素体是沿着密排堆积的(111)α和(110)α平面沉积的,沉积结构呈现典型的立方结构和高斯结构。尽管奥氏体的织构不如穿过沉积层的铁素体的织构强,但结果表明,奥氏体相相对于铁素体相形成了更紧密的Kurdjumov-Sachs取向关系。激光填丝直接能量沉积工艺的循环再加热效应不仅改变了贫双相不锈钢2101的组织和织构,还影响了晶粒尺寸和特殊晶界的比例。提高沉积结构中∑3晶界的含量和分布均匀性,有利于增强沉积层的耐蚀性。

Ultra wear resistant TiC-Fe coating prepared by high efficient and economic plasma cladding method

The key components of engineering machinery frequently failed due to working in the high load and high wear operating envir-onment.And the performance of the Fe-based alloy coatings typically employed need to be improved for fulfilling the service requirements.Herein,a TiC strengthened Fe-based alloy cladding layer,named TiC-Fe coating,was designed and prepared by plasma cladding technology.The frictional wear performance of coating under various loads was tested.The wear morphology of the coating was observed,and its wear mechanism was examined.The results indicated that the TiC-Fe coating was well formed and metallurgically bonded to the Q345C substrate.Its microstructure mainly consisted of Fe-Cr solid solution,α-Fe phase,(Fe,Cr)_(7)C_(3) phase and TiC phase.The coating exhibited an average microhardness of 980 HV0.2,which was about 5.4 times that of the Q345C substrate.The wear mass loss of the TiC-Fe coatings was much smaller than that of the Q345C substrate,which indicated that the wear resistance of the Q345C coating was superior to the substrate,and the wear mechanism of the coating was mainly attributed to the abrasive wear.

Knowledge-oriented modeling for influencing factors of battle damage in military industrial logistics:An integrated method

Modeling influencing factors of battle damage is one of essential works in implementing military industrial logistics simulation to explore battle damage laws knowledge.However,one of key challenges in designing the simulation system could be how to reasonably determine simulation model input and build a bridge to link battle damage model and battle damage laws knowledge.In this paper,we propose a novel knowledge-oriented modeling method for influencing factors of battle damage in military industrial logistics,integrating conceptual analysis,conceptual modeling,quantitative modeling and simulation implementation.We conceptualize influencing factors of battle damage by using the principle of hierarchical decomposition,thus classifying the related battle damage knowledge logically.Then,we construct the conceptual model of influencing factors of battle damage by using Entity-Relations hip approach,thus describing their interactions reasonably.Subsequently,we extract the important influencing factors by using social network analysis,thus evaluating their importance quantitatively and further clarifying the elements of simulation.Finally,we develop an agent-based military industry logistics simulation system by taking the modeling results on influencing factors of battle damage as simulation model input,and obtain simulation model output,i.e.,new battle damage laws knowledge,thus verifying feasibility and effectiveness of the proposed method.The results show that this method can be used to support human decision-making and action.

A review of novel ternary nano-layered MAX phases reinforced AZ91D magnesium composite

In recent decades, the demand for lightweight and high specific strength materials brings about the development of magnesium matrix composites. Different from some traditional binary ceramic particles, such as SiC, Al_(2)O_(3), the novel ternary nano-layered M_(n+1)AX_(n)(MAX)phase carbide or nitride ceramics exhibit metal-like properties and self-lubricate capacity(where “M” is an early transition metal, “A” belongs to the group A element, “X” is C or/and N, and n = 1–3). Ti_(2)AlC, as the representative of the MAX phase, was interestingly introduced into the magnesium matrix. Layered Ti_(2)AlC MAX phased reinforced AZ91D magnesium composites manufactured through the stir casting exhibit sufficient deformation capacity due to unique deformation behaviors of MAX, namely delamination and the formation of kinking band. Further,the Ti_(2)AlC-AZ91D composites exhibit a distinctive characteristic in strengthening mechanism, damping mechanism and tribological capacity due to the other special properties of MAX phase, such as self-lubricated property. Accordingly, to give a comprehensive understanding, we overviewed the fabrication process, microstructural characterization, mechanical properties, damping property and tribological capacity on these composites. In order to understand the A-site effect in MAX phase on the microstructure, we introduced another representative Ti_(3)SiC_(2)MAX phase to explain the interfacial evolution. In addition, due to the high aspect ratio of MAX, MAX particles could be orientationally regulated in Mg matrix by plastic deformation such as hot extrusion. Herein, we discussed the anisotropic mechanical and physical properties of the textured composites produced by hot extrusion. Moreover, the potential applications and future development trends of MAX phases reinforced magnesium matrix composites were also given and prospected.

Fabrication and performance of 3D co-continuous magnesium composites reinforced with Ti_(2)AlN_(x) MAX phase

Magnesium composites reinforced by N-deficient Ti_(2)AlN MAX phase were first fabricated by non-pressure infiltration of Mg into three-dimensional(3D)co-continuous porous Ti_(2)AlN_(x)(x=0.9,1.0)preforms.The relationship between their mechanical properties and micro-structure is discussed with the assessment of 2D and 3D characterization.X-ray diffraction(XRD)and scanning electron microscopy detected no impurities.The 3D reconstruction shows that the uniformly distributed pores in Ti_(2)AlN_(x) preforms are interconnected,which act as infiltra-tion tunnels for the melt Mg.The compressive yield strength and microhardness of Ti_(2)AlN_(0.9)/Mg are 353 MPa and 1.12 GPa,respectively,which are 8.55%and 6.67%lower than those of Ti_(2)AlN/Mg,respectively.The typical delamination and kink band occurred in Ti_(2)AlN_(x) under compressive and Vickers hardness(V_(H))tests.Owing to the continuous skeleton structure and strong interfacial bonding strength,the crack ini-tiated in Ti_(2)AlN_(x) was blocked by the plastic Mg matrix.This suggests the possibility of regulating the mechanical performance of Ti_(2)AlN/Mg composites by controlling the N vacancy and the hierarchical structure of Ti_(2)AlN skeleton.

Reconstruction resolution enhancement of EPISM based holographic stereogram with hogel spatial multiplexing

We investigate how the splicing mode of a holographic element(hogel)affects the reconstruction of a 3 D scene to improve the reconstruction resolution of a holographic stereogram fabricated using the effective perspective image segmentation and mosaicking method(EPISM).First,the effect of hogel spatial multiplexing on holographic recording and reconstruction is studied based on the mechanism of recording interference fringes in the holographic recording medium.Second,combined with the influence of multiple exposures on the hologram's diffraction efficiency,the diffraction efficiency of the holographic stereogram is analyzed in the spatial multiplexing mode.The holographic stereogram is then regarded as a special optical imaging system.The theory of spatial bandwidth product is adopted to describe the comprehensive resolution of the holographic stereogram,which explains why hogel spatial multiplexing can significantly improve the reconstruction resolution of a holographic stereogram.Compared with the traditional printing method under the same parameters in optical experiments,hogel spatial multiplexing has a lower diffraction efficiency but a higher quality of reconstructed image,consistent with the theoretical analysis.

Slip-Control Strategy of Dual Independent Electric Drive Tracked Vehicle

In order to improve the brake performance of a dual independent electric drive tracked vehicle,a dynamic model for braking situation was established.Then,a sliding model controller(SMC)with an auxiliary system was designed to control the slip and its effectiveness was proved.A hardware-in-loop simulation through MATLAB/XPC was compared with the normal SMC and normal integral sliding mode controller(ISMC),the results show that SMC with the auxiliary system has a better performance:a smaller overshoot and steady state error.The disturbance is suppressed effectively.In the initial speed of 65.km/h,the brake distance was shortened by 3.4%and 6.8%compared with the other two methods,respectively.Finally,initial speeds of 30-36.km/h tests was carried out on a flat soil road.Compared with a no-control brake,the displacement was shortened by 1.8.m.It demonstrates the effectiveness of the slip-control strategy.In the same situation,the error between the simulation and test is 18.1%,which validates the accuracy of models.

Tailoring microstructure evolution and mechanical properties of a high-performance alloy steel through controlled thermal cycles of a direct laser depositing process

Direct laser deposition(DLD),as a popular metal additive manufacturing process,shows advantages of technical flexibility and high efficiency to gain a high-performance alloy steel component.However,during the processing of DLD,the deposited steel layer is affected by the subsequent layer depositing.The DLD block shows different microstructure and mechanical properties at the bottom,middle and top of the deposited parts.To date,there are few research works about the effects of inter-layer interval time and laser power on the microstructure evolution and mechanical properties of the deposited layers.In this study,the idle time and laser power layer by layer during DLD of 12CrNi2 steel were controlled to cause the deposited layers to maintain a high cooling rate,while the bottom deposited layer was subjected to a weak tempering effect.Results show that a high proportion of martensite is produced,which improves the strength of the deposited layer.Under the laser scanning strategy of laser power 2,500 W,scanning velocity 5 mm·s^(-1),powder feeding rate 11 g·min^(-1),overlap rate 50%,and a laser power difference of 50 W and a 2 min interval,the tensile strength of the deposited layer of 12CrNi2 steel is in the range of 873-1,022 MPa,and the elongation is in the range of 16.2%-18.9%.This study provides a method to reduce the tempering effect of the subsequent deposition layers on the bottom layers,which can increase the proportion of martensite in the low-alloy high-strength steel,so as to improve the yield strength of the alloy steel.

Understanding the changing mechanism of arc characteristics in ultrasound-magnetic field coaxial hybrid gas tungsten arc welding

Ultrasound-magnetic field coaxial hybrid Gas Tungsten Arc Welding(U-M-GTAW)is proposed as a means to control arc characteristics.The arc characteristics and the mechanism to change them,in an ultrasound-magnetic field coaxial hybrid GTAW,were studied by both experimental and theoretical analyses.The results showed that a periodic rotation and compression of the arc shape were obtained in U-M-GTAW and the arc energy was also enhanced.The most obvious compression of the arc shape in U-M-GTAW was obtained,compared with GTAW,M-GTAW and U-GTAW.At the same time,a periodic rotation of the arc was observed in U-M-GTAW.The geometric parameters of the arc shape in U-M-GTAW are reduced more than double compared with traditional GTAW.The arc voltage in the hybrid GTAW was increased,especially in the U-M-GTAW.The electromagnetic force and acoustic radiation force were the main factors for the change of arc characteristics in the U-M-GTAW.

Artificial Monitoring of Eccentric Synchronous Reluctance Motors Using Neural Networks

This paper proposes an artificial neural network for monitoring and detecting the eccentric error of synchronous reluctance motors.Firstly,a 15 kWsynchronous reluctance motor is introduced and took as a case study to investigate the effects of eccentric rotor.Then,the equivalent magnetic circuits of the studied motor are analyzed and developed,in cases of dynamic eccentric rotor and static eccentric rotor condition,respectively.After that,the analytical equations of the studied motor are derived,in terms of its air-gap flux density,electromagnetic torque,and electromagnetic force,followed by the electromagnetic finite element analyses.Then,the modal analyses of the stator and the whole motor are performed,respectively,to explore the natural frequency and the modal shape of the motor,by which the further vibrational analysis is possible to be conducted.The vibration level of the housing is furtherly studied to investigate its relationship with the rotor eccentricity,which is validated by the prototype test.Furthermore,an artificial neural network,which has 3 layers,is proposed.By taking the air-gap flux density,the electromagnetic force,and the vibrational level as inputs,and taking the eccentric distance as output,the proposed neural network is trained till the error smaller than 5%.Therefore,this neural network is obtaining the input parameters of the tested motor,based on which it is automatically monitoring and reporting the eccentric error to the upper-level control center.

Research on the Design Method of Equipment in Service Assessment Subjects

Combined with equipment activities such as combat readiness,training, exercises and management, it is proposed that the design of equipment in-service assessment subjects should follow the principles of combination, stage and operability. Focusing on the design of equipment in-serviceassessment subjects, a design method for in-service assessment subjects basedon the combination of trial and training mode is proposed. Based on theactual use of high-equipment use management and training and the established indicator system, the army’s bottom-level equipment activity subjectsand bottom-level assessments are combined. The indicators are mapped andanalyzed. Through multiple rounds of iterations, the mapping relationshipbetween in-service assessment indicators and military equipment activitysubjects is established. Finally, the equipment activity subjects whose data iscollected (reflecting the underlying assessment indicators) are generated inservice assessment subjects. The orthogonal test method is used to optimizethe samples in the assessment subjects to form an in-service assessmentimplementation plan. Taking a certain type of armored infantry fightingvehicle as an example, the sample optimization design of the initially generatedin-service assessment subjects is analyzed. It provides methods and ideas tocarry out in-service assessment work.

Overview of Condition-Based Maintenance Decision-Making Optimization Modeling of Multi-component System

Overview about three key contents of condition-based maintenance decision-making of a multi-component system is analyzed based on maintenance optimization and modeling. The component deterioration model, the correlation between the degraded components and the system configuration are analyzed separately in the deterioration model of multi-component system.For the maintenance polices,the opportunistic maintenance( OM)policy and the grouping maintenance( GM) policy are analyzed and summarized in combination with the condition-based maintenance( CBM) modeling of multi-component system. It is put forward that CBM modeling of multi-component system should be further researched based on the inspection interval and the maintenance threshold of multi-component system in availability.

A universal design for triggering the precise micro-structure reconstruction through in-situ electro-regulating to boost the pseudocapacitance of MnO_(2)

Developing a precise controllable strategy for modulating the micro-morphology,atom coordination environment,and electronic structure of electrode materials is crucial for the performance in the field of energy storage,yet still a tremendous challenge.Herein,a facile and universal in-situ electrochemical self-optimization design,electro-regulating,is designed to controllably produce electrode materials with abundant defects.Through detailed characterization studies,the microstructure of MnO_(2) is reconstructed after electro-regulating,which exhibits a structure of small fragments with numerous holes due to the partial self-dissolution of acidic oxides under an alkaline operating environment.Furthermore,the electro-regulating strategy not only presents the formation steps of numerous holes but is also accompanies by a number of O vacancies generation process due to the activation of an external electric field.This study provides a new inspiration for reasonably designing advanced functional electrode materials for various electrochemical applications and beyond.

Research and Practice on Teaching Reform of University Computer Foundation

In order to solve the problems of students’basic difference,more course content and less class hours,it is difficult for students to apply what they have learned.This paper puts forward the teaching reform scheme of university computer foundation course.From the optimization of teaching content,the construction of case scenarios,the improvement of teaching philosophy,the adjustment of teaching mode and assessment mode,etc.,we should give prominence to teaching students in accordance with their aptitude,apply what they have learned,and fully mobilize the subjective initiative and enthusiasm of students.According to the implementation and feedback of two consecutive years,the reform effect of the course is good.

Preparation of Cu@Ag Nanoparticles for Conductive Ink

In order to overcome the shortcomings of low-cost anti-oxidation conductive ink and its preparation method in the field of printing electronics, core-shell coated Cu@Ag nanoparticles were used to prepare conductive ink, and a printed circuit was obtained by inkjet printing. Copper nanoparticles were prepared by a chemical reduction method and then coated with Cu@Ag particles by a copper-based self-catalytic reaction. Conductive ink was prepared by ball milling and dispersion and printed on PI film to form a conductive coating. After characterization and analysis, the particle size and dispersion of the obtained Cu@Ag meet the requirements and can be stored stably under normal atmospheric conditions. The resistivity of the conductive film sintered at 300˚C is only 10.6 μΩ∙cm.

Conceptual Modeling and Simulation Application Analysis of In-service Assessment

Firstly,this paper expounds the conceptual connotation of inservice assessment in the new system,then applies modeling and Simulation in the field of in-service assessment,establishes the conceptual model of inservice assessment and its process,and finally analyzes the application of modeling and simulation in the specific links of in-service assessment.

The Construction of a Combined OBE-based Teaching Model

This paper proposes a teaching model based on the concept of outcome-based education(OBE).OBE is meant to be a student-centered learning model.Based on OBE,the characteristics of project-based learning(PBL)and lecture-based teaching approach are analyzed.Then,a combined teaching model is constructed based on Acharya’s research findings and PBL.This proposed model integrates PBL and lecture-based teaching approach to help achieve ideal learning outcomes.It enhances learners’learning initiative and creativity while ensuring holistic and systematic learning outcomes.

Interactive Transformer for Small Object Detection

The detection of large-scale objects has achieved high accuracy,but due to the low peak signal to noise ratio(PSNR),fewer distinguishing features,and ease of being occluded by the surroundings,the detection of small objects,however,does not enjoy similar success.Endeavor to solve the problem,this paper proposes an attention mechanism based on cross-Key values.Based on the traditional transformer,this paper first improves the feature processing with the convolution module,effectively maintaining the local semantic context in the middle layer,and significantly reducing the number of parameters of the model.Then,to enhance the effectiveness of the attention mask,two Key values are calculated simultaneously along Query and Value by using the method of dual-branch parallel processing,which is used to strengthen the attention acquisition mode and improve the coupling of key information.Finally,focusing on the feature maps of different channels,the multi-head attention mechanism is applied to the channel attention mask to improve the feature utilization effect of the middle layer.By comparing three small object datasets,the plug-and-play interactive transformer(IT-transformer)module designed by us effectively improves the detection results of the baseline.