查看更多>>摘要：Camouflaged people are extremely expert in actively concealing themselves by effectively utilizing cover and the surrounding environment.Despite advancements in optical detection capabilities through im-aging systems,including spectral,polarization,and infrared technologies,there is still a lack of effective real-time method for accurately detecting small-size and high-efficient camouflaged people in complex real-world scenes.Here,this study proposes a snapshot multispectral image-based camouflaged detection model,multispectral YOLO(MS-YOLO),which utilizes the SPD-Conv and SimAM modules to effectively represent targets and suppress background interference by exploiting the spatial-spectral target information.Besides,the study constructs the first real-shot multispectral camouflaged people dataset(MSCPD),which encompasses diverse scenes,target scales,and attitudes.To minimize infor-mation redundancy,MS-YOLO selects an optimal subset of 12 bands with strong feature representation and minimal inter-band correlation as input.Through experiments on the MSCPD,MS-YOLO achieves a mean Average Precision of 94.31％and real-time detection at 65 frames per second,which confirms the effectiveness and efficiency of our method in detecting camouflaged people in various typical desert and forest scenes.Our approach offers valuable support to improve the perception capabilities of unmanned aerial vehicles in detecting enemy forces and rescuing personnel in battlefield.
查看更多>>摘要：This paper investigates the design of an attitude autopilot for a dual-channel controlled spinning glide-guided projectile(SGGP),addressing model uncertainties and external disturbances.Based on fixed-time stable theory,a disturbance observer with integral sliding mode and adaptive techniques is proposed to mitigate total disturbance effects,irrespective of initial conditions.By introducing an error integral signal,the dynamics of the SGGP are transformed into two separate second-order fully actuated systems.Subsequently,employing the high-order fully actuated approach and a parametric approach,the nonlinear dynamics of the SGGP are recast into a constant linear closed-loop system,ensuring that the projectile's attitude asymptotically tracks the given goal with the desired eigenstructure.Under the proposed composite control framework,the ultimately uniformly bounded stability of the closed-loop system is rigorously demonstrated via the Lyapunov method.Validation of the effectiveness of the proposed attitude autopilot design is provided through extensive numerical simulations.
查看更多>>摘要：Reinforcement learning has been applied to air combat problems in recent years,and the idea of cur-riculum learning is often used for reinforcement learning,but traditional curriculum learning suffers from the problem of plasticity loss in neural networks.Plasticity loss is the difficulty of learning new knowledge after the network has converged.To this end,we propose a motivational curriculum learning distributed proximal policy optimization(MCLDPPO)algorithm,through which trained agents can significantly outperform the predictive game tree and mainstream reinforcement learning methods.The motivational curriculum learning is designed to help the agent gradually improve its combat ability by observing the agent's unsatisfactory performance and providing appropriate rewards as a guide.Furthermore,a complete tactical maneuver is encapsulated based on the existing air combat knowledge,and through the flexible use of these maneuvers,some tactics beyond human knowledge can be realized.In addition,we designed an interruption mechanism for the agent to increase the frequency of decision-making when the agent faces an emergency.When the number of threats received by the agent changes,the current action is interrupted in order to reacquire observations and make decisions again.Using the interruption mechanism can significantly improve the performance of the agent.To simulate actual air combat better,we use digital twin technology to simulate real air battles and propose a parallel battlefield mechanism that can run multiple simulation environments simultaneously,effectively improving data throughput.The experimental results demonstrate that the agent can fully utilize the situational information to make reasonable decisions and provide tactical adaptation in the air combat,verifying the effectiveness of the algorithmic framework proposed in this paper.
查看更多>>摘要：Improving the energy conversion efficiency in metallic fuel(e.g.,Al)combustion is always desirable but challenging,which often involves redox reactions of aluminum(Al)with various mixed oxidizing en-vironments.For instance,Al-O reaction is the most common pathway to release limited energy while Al-F reaction has received much attentions to enhance Al combustion efficiency.However,microscopic understanding of the Al-O/Al-F reaction dynamics remains unsolved,which is fundamentally necessary to further improve Al combustion efficiency.In this work,for the first time,Al-O/Al-F reaction dynamic effects on the combustion of aluminum nanoparticles(n-Al)in oxygen/fluorine containing environments have been revealed via reactive molecular dynamics(RMD)simulations meshing together combustion experiments.Three RMD simulation systems of Al core/O2/HF,n-Al/O2/HF,and n-Al/O2/CF4 with oxygen percentage ranging from 0％to 100％have been performed.The n-Al combustion in mixed O2/CF4 en-vironments have been conducted by constant volume combustion experiments.RMD results show that Al-O reaction exhibits kinetic benefits while Al-F reaction owns thermodynamic benefits for n-Al combustion.In n-Al/O2/HF,Al-O reaction gives faster energy release rate than Al-F reaction(1.1 times).The optimal energy release efficiency can be achieved with suitable oxygen percentage of 10％and 50％for n-Al/O2/HF and n-Al/O2/CF4,respectively.In combustion experiments,90％of oxygen percentage can optimally enhance the peak pressure,pressurization rate and combustion heat.Importantly,Al-O re-action prefers to occur on the surface regions while Al-F reaction prefers to proceed in the interior regions of n-Al,confirming the kinetic/thermodynamic benefits of Al-O/Al-F reactions.The synergistic effect of Al-O/Al-F reaction for greatly enhancing n-Al combustion efficiency is demonstrated at atomic-scale,which is beneficial for optimizing the combustion performance of metallic fuel.
查看更多>>摘要：The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to imple-ment accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 dB and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96％on seven modulation types and recognition accuracies of more than 94％on each mod-ulation type under SNRs of-12 dB and above,which represents a good AMR performance of radio fuzes under low SNRs.
万方数据
维普