查看更多>>摘要：Federated Learning(FL),a promising deep learning paradigm extensively deployed in Vehicular Edge Computing Networks(VECN),allows a distributed approach to train datasets of nodes locally,e.g.,for mobile vehicles,and exchanges model parameters to obtain an accurate model without raw data transmission.However,the existence of malicious vehicular nodes as well as the inherent heterogeneity of the vehicles hinders the attainment of accurate models.Moreover,the local model training and model parameter transmission during FL exert a notable energy burden on vehicles constrained in resources.In view of this,we investigate FL client selection and resource management problems in FL-enabled UAV-assisted Vehicular Networks(FLVN).We first devise a novel reputation-based client selection mechanism by integrating both data quality and computation capability metrics to enlist reliable high-performance vehicles.Further,to fortify the FL reliability,we adopt the consortium blockchain to oversee the reputation informa-tion,which boasts tamper-proof and interference-resistant qualities.Finally,we formulate the resource scheduling problem by jointly optimizing the computation capability,the transmission power,and the number of local training rounds,aiming to minimize the cost of clients while guaranteeing accuracy.To this end,we propose a reinforcement learning algorithm employing an asynchronous parallel network structure to achieve an optimized scheduling strategy.Simulation results show that our proposed client selection mechanism and scheduling algorithm can realize reliable FL with an accuracy of 0.96 and consistently outperform the baselines in terms of delay and energy consumption.
查看更多>>摘要：Aircraft wake turbulence is an inherent outcome of aircraft flight,presenting a substan-tial challenge to air traffic control,aviation safety and operational efficiency.Building upon data obtained from coherent Doppler Lidar detection,and combining Dynamic Bayesian Networks(DBN)with Genetic Algorithm-optimized Backpropagation Neural Networks(GA-BPNN),this paper proposes a model for the inversion of wake vortex parameters.During the wake vortex flow field simulation analysis,the wind and turbulent environment were initially superimposed onto the simulated wake velocity field.Subsequently,Lidar-detected echoes of the velocity field are simulated to obtain a data set similar to the actual situation for model training.In the case study validation,real measured data underwent preprocessing and were then input into the established model.This allowed us to construct the wake vortex characteristic parameter inversion model.The final results demonstrated that our model achieved parameter inversion with only minor errors.In a practical example,our model in this paper significantly reduced the mean square error of the inverted velocity field when compared to the traditional algorithm.This study holds significant promise for real-time monitoring of wake vortices at airports,and is proved a crucial step in developing wake vortex interval standards.
查看更多>>摘要：With the rapid development of space activities,non-cooperative space targets increase swiftly,such as failed satellites and upper stages,threating normal spacecrafts seriously.As there are some problems in the capture process,such as excessive collision and fast tumbling of targets,manipulator with redundant Degrees of Freedom(DOFs)can be used to improve the compliance and therefore solve these problems.The Rope-Driven Snake Manipulator(RDSM)is a combina-tion of hyper-redundant DOFs and better compliance,and therefore it is suitable for capturing mis-sion.In this paper,a snake manipulator mechanism is designed,and the complete kinematic model and system dynamic model considering RDSM,target and contact is established.Then,to obtain the configuration of joint with hyper-redundant DOFs,an improved motion dexterity index is pro-posed as the joint motion optimization target.Besides,the force-position collaborative optimization index is designed to adjust active stiffness,and the impedance control method based on the modified index is used to capture the space target.Finally,the proposed force-position collaborative opti-mization method is verified by virtual prototype co-simulation.The results demonstrate that based on the proposed method,the collision force is reduced by about 25％compared to normal impe-dance control,showing higher safety.
查看更多>>摘要：To efficiently and accurately design satellite constellations equipped with Reentry Glide Vehicles(RGVs),new analytical solutions are developed for calculating their coverage perfor-mance.Specifically,a new coverage model is established by approximating the Reentry Reachable Domain(RRD).However,the computation of real-time relative distances between satellites and targets,which is essential for coverage analysis based on this model,imposes a significant compu-tational burden.To address this challenge,a coverage analysis method based on two-dimensional map theory is proposed.This method represents the coverage conditions of a target as a fixed area on a two-dimensional map and transforms the satellite trajectory into a series of parallel lines.By determining the intersection points between these lines and the area boundaries,the coverage ana-lytical solutions for a target point are derived.On this basis,coverage theorems are presented for rapid calculation of the constellation coverage performance for an area.Simulation results demon-strate the effectiveness and high precision of the proposed analytical solutions.
查看更多>>摘要：This paper investigates the spatial-temporal cooperative guidance problem for multiple flight vehicles without relying on time-to-go information.First,a two-stage cooperative guidance strategy,namely the cooperative guidance and the Proportional Navigation Guidance(PNG)stage strategy,is developed to realize the spatial-temporal constraints in two dimensions.At the former stage,two controllers are designed and superimposed to satisfy both impact time consensus and impact angle constraints.Once the convergent conditions are satisfied,the flight vehicles will switch to the PNG stage to ensure zero miss distance.To further extend the results to three dimensions,a planar pursuit guidance stage is additionally imposed at the beginning of guidance.Due to the inde-pendence of time-to-go estimation,the proposed guidance strategy possesses great performance in satisfying complex spatial-temporal constraints even under flight speed variation.Finally,several numerical simulations are implemented to verify the effectiveness and advantages of the proposed results under different scenarios.
查看更多>>摘要：Inertial characteristics of non-cooperative targets are crucial for space capture and sub-sequent on-orbit servicing.Previous methods for identifying inertial parameters involve proximity operations,which are associated with the risk of collision with non-cooperative targets.This paper introduces a long-range,contactless method for identifying the inertial parameters of a non-cooperative target during the pre-capture phase.Specifically,electrostatic interaction is used as an external excitation to alter the target's motion.A force estimation algorithm that uses measure-ments from visual and potential sensors is proposed to estimate the electrostatic interaction and eliminate the need for force sensors.Furthermore,a recursive estimation-identification framework is presented to concurrently estimate the coupled motion state,weak electrostatic interaction,and inertial parameters of the target.The simulation results show that the proposed method extends the identification distance to 170 times that of the previous method while maintaining high identifica-tion precision for all parameters.
查看更多>>摘要：The navigation system plays a pivotal role in guiding aircraft along designated routes,ensuring precise and punctual arrival at destinations.The integration of scene matching with an inertial navigation system enhances the capability of providing a dependable guarantee for success-ful accomplishment of flight missions.Nonetheless,assuring reliability in scene matching encoun-ters significant challenges in areas characterized by repetitive or weak textures.To tackle these challenges,we propose a novel method to assess the reliability of scene matching based on the dis-tinctive characteristics of correlation peaks.The proposed method leverages the fact that the sim-ilarity of the optimal matching result is significantly higher than that of the surrounding area,and three novel indicators(e.g.,relative height,slope of a correlation peak,and ratio of a sub peak to the main peak)are determined to conjointly evaluate the reliability of scene matching.The pro-posed method entails matching a real-time image with a reference image to generate a correlation surface.A correlation peak is then obtained by extracting the portion of the correlation surface exhibiting a significant gradient.Additionally,the matching reliability is determined by considering the relative height,slope,and ratio of the peak collectively.Exhaustive experimental results with two sets of data demonstrate that the proposed method significantly outperforms traditional approaches in terms of precision,recall,and F1-score.These experiments also establish the efficacy of the proposed method in achieving reliable matching in challenging environments characterized by repetitive and weak textures.This enhancement holds the potential to significantly elevate scene-matching-based navigation.
查看更多>>摘要：Analysis of cluster behaviors of the on-coming cluster is an essential measure for high value locations on the battlefield.Unlike target tracking and clustering analysis,cluster behaviors analysis under cluster security requirements remains an open issue,which is a joint analysis of clus-tering,intent reasoning and activity regions.To address this issue,a framework for cluster behav-iors analysis is proposed by incorporating expert knowledge and domain knowledge,and a knowledge-assisted score function with is designed to improve the accuracy of intent reasoning net-work,overcoming the effects of possible knowledge errors.The framework consists of three mod-ules for cluster analysis,intent reasoning and activity region analysis for typical tasks,in which an intent reasoning network is constructed to obtain cluster intents by using a hybrid knowledge and data driven approach.Furthermore,considering the complexity of the battlefield environment,dif-ferent tasks and corresponding activity region optimization functions are designed for cluster activ-ity region analysis,which are vital elements of cluster behaviors analysis.Simulations demonstrate the effectiveness of the proposed cluster behaviors analysis framework.
查看更多>>摘要：The electrical performance of radomes on high-speed aircraft can be influenced by the thermal and mechanical loads produced during high-speed flight,which can affect the detection dis-tance and accuracy of the guidance system.This paper presents a new method that uses the Finite Difference Time Domain(FDTD)method to calculate the electrical performance of radomes under Thermo-Mechanical-Electrical(TME)coupling.This method can accurately characterize the effects of material dielectric temperature drift and structural deformation on the electrical performance of the radome under flight conditions,enabling high-precision full-wave calculations of the broadband electrical performance of the radome.The method initiates by utilizing a Finite Element Grid Model(FE-GM)of the radome to sequentially acquire the radome's response temperature field and structural deformation field through thermal and mechanical simulations.Subsequently,spatial mapping techniques are developed to accurately incorporate the dielectric temperature drift and structural deformation of the radome into its Yee grid Electromagnetic(EM)simulation model.A verification case was designed to test the proposed method,and the results confirmed its high computational accuracy.Additionally,the effectiveness and necessity of the method were further demonstrated by analyzing the electrical performance of a fused silica ceramic radome used on a high-speed aircraft.
查看更多>>摘要：The dynamic failure behavior of CoCrFeNi High-Entropy Alloy(HEA)under plane biaxial stress was investigated in detail.The dynamic biaxial tensile tests were conducted using an Electromagnetic Biaxial Split Hopkinson Tensile Bar(EBSHTB)system.For comparison,the quasi-static uniaxial and biaxial tensile tests,as well as dynamic uniaxial tensile tests,were per-formed respectively.A cruciform specimen suitable for large plastic deformation was designed and employed in the experiments.The Finite Element Method(FEM)verified that the improved cruciform specimen could satisfy the basic requirements.The feasibility of the proposed specimen was further confirmed through loading tests.Finally,the quasi-static and dynamic yield loci of the HEA in the first quadrant of the principal stress space were plotted.The results indicate that the alloy exhibits obvious strain hardening effect and strain rate strengthening effect,the yield locus and plastic work contours can be accurately described by Hill'48 criterion.
NETL
NSTL
万方数据