The reliability of data link system of unmanned aerial vehicle (UAV, or unmanned system) is the key to determine the success of unmanned system mission execution, and is also a difficult point of reliability modeling and analysis of unmanned system.Aiming at the characteristics of multi-service integration, complex structure and dynamic reconfiguration of UAV data link system, this paper proposes a method to build a dynamic reliability simulation model of data link service based on generalized stochastic Petri net (GSPN).By analyzing the characteristics of the UAV data link system, this method uses the resources, places, transitions and other elements in the GSPN model to describe various resources, states, behaviors and collaborative relationships in the data link system, and uses specific random variables to represent the component states and their durations to simulate the dynamic operation process of the data link system.Three typical services modes of UAV data link system as uplink remote control, downlink telemetry and downlink mission load transmission are modeled and simulated by using the Pipe software tool, which could accurately describe the synchronization, concurrency, distribution, conflict, resource sharing or competition, and reliability of the data link with dynamic reconfiguration behavior under the multi-service background could be evaluated.Finally, this paper proves that the GSPN based method could obtain reliable reliability evaluation results for the data link through a case analysis.
In the context of multidestination material transportation tasks for unmanned aerial vehicles (UAVs) during wartime, task allocation and path planning play crucial roles. Although numerous research methods have been proposed, most algorithms treat these two aspects as relatively independent components, resulting in limited flexibility in decision making and real-time path planning on highly confrontational battlefields. To address this issue, this article presents a novel approach to multidestination path planning based on ant colony decision making and rolling control. First, an information sharing module is established to process real-time updated environmental data, providing a foundation for decision making and path planning. Second, a new ant colony decision method is developed by designing an objective function that minimizes consumption to determine the order of destination material transportation. In addition, an online and multiround destination decision strategy is formulated based on the updated environmental information from the information sharing module. This strategy prevents situations where total consumption for multiple destinations becomes excessive due to UAVs not considering real-time changes in material demand during transportation but making decisions only once per destination. Subsequently, the receding horizon control with extended solution method is employed to achieve multidestination path planning by integrating online path planning and decision strategies. Finally, experiments are conducted in a multidestination environment with obstacles to validate the effectiveness of our proposed method. The results demonstrate that compared to several other advanced optimization methods, our approach exhibits advantages such as shorter paths and lower overall material consumption.
Explosive ordnance disposal (EOD) robots can replace humans that work in hazardous environments to ensure worker safety. Thus, they have been widely developed and deployed. However, existing EOD robots have some limitations in environmental adaptation, such as a single function, slow action speed, and limited vision. To overcome these shortcomings and solve the uncertain problem of bomb disposal on the firing range, we have developed an intelligent bomb disposal system that integrates autonomous unmanned aerial vehicle (UAV) navigation, deep learning, and other technologies. For the hardware structure of the system, we design an actuator constructed by a winch device and a mechanical gripper to grasp the unexploded ordnance (UXO), which is equipped under the six-rotor UAV. The integrated dual-vision Pan-Tilt-Zoom (PTZ) pod is applied in the system to monitor and photograph the deployment site for dropping live munitions. For the software structure of the system, the ground station exploits the YOLOv5 algorithm to detect the grenade targets for real-time video and accurately locate the landing point of the grenade. The operator remotely controls the UAV to grasp, transfer, and destroy grenades. Experiments on explosives defusal are performed, and the results show that our system is feasible with high recognition accuracy and strong maneuverability. Compared with the traditional mode of explosives defusal, the system can provide decision-makers with accurate information on the location of the grenade and at the same time better mitigate the potential casualties in the explosive demolition process.
针对多无人机受模型偏差和外部扰动导致的编队构型不稳定问题,提出一种模型补偿控制的思想,在此基础上设计基于补偿函数观测器(CFO)的模型补偿反步控制器并应用于编队协同控制,把编队协同控制问题转化为传统控制问题,实现多无人机在复杂外部扰动下的编队集合、飞行和队形切换.所提出的控制器不仅保留了基于Lyapunov准则的全局指数渐近稳定性,还采用CFO来准确估计模型偏差和干扰并补偿到控制器中,有效增强了编队系统整体的抗扰能力.最后通过仿真和实验验证了算法的有效性.
针对当前无人机集群协同侦察目标规模小、易重复侦察、不考虑能量约束而导致侦察效能低等问题,提出了一种基于能量约束的集群协同侦察多目标航迹规划算法.首先,对无人机任务过程中所需的各种能量进行建模,定量分析了飞行能量、悬停能量和数据传输能量的消耗;然后,借鉴图论思想对集群的侦察区域和侦察目标进行建模,在能量约束条件下构建了一种新的航迹规划算法模型,旨在对无人机集群航迹进行协同优化,降低集群整体能量消耗.仿真结果表明,该算法在能量消耗和侦察时间等方面都明显优于典型的轨迹距离算法,在10架无人机侦察100个目标情况下,能量消耗降低了48％,其侦察效率较高,收敛速度更快.
针对高旋弹用MEMS-IMU在传统标定方法中不能全面激活误差,且存在标定流程复杂、标定效率低的问题,设计一种高旋弹用MEMS-IMU自动标定系统和方法.首先分析了高旋弹用MEMS-IMU输出特性,构建误差模型,设计十二位十八速的标定方案,并优化转台转动方案.通过自动标定系统,实现高旋弹用MEMS-IMU的自动标定.实验结果表明,该方法能实现对高旋弹用MEMS-IMU的自动标定,MEMS陀螺仪滚转、俯仰和偏航轴精度较传统方法分别提升98％,72％,73％以上;MEMS加速度计三轴精度分别提升53％,47％,7％,同时整个标定流程时间大幅减少,提高了标定效率.
面对城市低空复杂的电磁环境,无人机在运行过程中GNSS信号极易受到干扰,导致定位不准.为提高无人机定位精度,提出一种基于扩展卡尔曼滤波的数据融合方法,该方法在惯性导航系统的基础上,与基于5G信号的三维定位相融合,并对惯性导航误差进行修正.软件仿真表明,该方法在缺少有效GNSS信号的情况下将姿态误差和位置误差控制在一定的范围内,提高了无人机的定位精度,视距下的平均位置误差为16.6 cm,相比于融合前定位精度提升了49.7％,使得无人机具有长时间较高定位精度,具有一定的工程实用性.
抗分选信号设计是射频隐身信号设计的一个重要方向,其基础是抗分选信号设计原理,本质上是雷达信号分选算法的失效原理.聚类预分选在雷达信号分选中发挥着关键的作用,具有分选速度快、能同时分选出多个辐射源、大幅减轻主分选计算压力的优点.但在射频隐身抗分选信号设计领域,研究统一的、广泛适用的聚类分选失效原理进而指导抗分选信号设计尚未见正式文献披露.通过研究基于数据场K-means聚类算法和模糊C-means聚类算法原理,针对聚类算法中必须进行的数据相似性度量这一步骤,提出一种可以广泛使用的聚类分选失效原理,使得两种聚类算法分选均失效,指导设计射频隐身抗分选信号.公式推导和信号仿真证明了原理的正确性,为射频隐身抗分选信号设计提供了理论支撑,可以提高射频隐身抗分选信号的设计效率.
双螺旋桨推进复合式直升机具有可变飞行模式,过渡段是实现不同飞行模式转换的必经阶段,且两侧螺旋桨的不对称效果加剧横航向耦合,为保证复合式直升机过渡段的飞行安全,设计横航向姿态解耦控制系统.针对复合式直升机过渡飞行阶段存在的控制方式转换与横航向通道间操纵耦合问题,制定了以操纵功效为约束的控制方式线性过渡策略,基于显模型跟踪解耦控制理论设计了控制阵解耦的姿态控制器,构建了横航向姿态解耦控制系统仿真模型.仿真结果表明:该控制系统可以有效保证复合式直升机控制方式平稳转换,并实现横航向通道解耦控制.
针对"热保障"条件下飞机出动架次率难以测算的问题,提出一种基于分层赋时着色Petri网(HTCPN)的飞机出动架次率仿真测算方法.首先,根据飞机基层级维修保障工作,建立飞机连续出动模型与保障流程;其次,运用Petri网理论和CPN tools软件,构建基于HTCPN的机务保障全过程计算机仿真模型;最后,通过算例分析找出制约飞机出动架次率的重要影响因素.结果表明,所提方法不仅能够找出影响飞机出动的重要因素,还能为飞机出动架次率测算提供技术支撑,具有一定工程应用价值.
针对脉冲多普勒(PD)雷达抗主瓣压制干扰问题,提出两种抑制算法.第一种算法基于波束域盲源分离(BSS)抑制思路,通过对相参积累后的多波束回波进行降维,构造待分离信号,并以瑞利熵为指标识别分离后的源信号.第二种算法基于相关滤波抑制思路,以一个波束回波为匹配信号,对另一个波束回波进行相关滤波,再通过逆操作得到抑制后的波束回波.仿真试验验证了所提两种算法的有效性.
研究了四旋翼无人机执行器故障和外部干扰下的高度和姿态容错控制问题.首先,将执行器故障建模为螺旋桨推力定常效率损失(LoE),得到包含执行器故障的四旋翼无人机高度和姿态动力学模型;然后,基于积分终端滑模控制(ITSMC)设计了一种容错控制器,并结合自适应律对干扰进行估计和补偿,借助Lyapunov理论证明了闭环系统的稳定性;最后,数值仿真结果验证了所提出容错控制方案的有效性和鲁棒性.
舰船已经成为海上军事重要的监测目标,针对SAR图像舰船目标检测存在检测效果差、计算量大、泛化能力弱的问题,提出一种基于YOLOv5和Mobilenetv3的轻量化舰船目标检测算法.首先,引入Mobilenetv3主干网络,降低模型计算量与体积,实现模型轻量化处理;然后,引入EIoU损失函数,提高预测框的回归精度和收敛速度;最后,在颈部网络中引入CBAM,在特征融合阶段进行注意力调整,提高模型检测精度与检测效果.在SSDD数据集上的实验结果显示,改进后算法模型体积压缩至原YOLOv5模型的18.32％,训练时间缩短35.22％,参数量减小至原模型的15.94％,计算量减小至原模型的10.76％,平均精度提升至98.3％.实验结果表明,改进后算法在保持高精度检测效果的情况下,大幅降低了参数量和计算量,减小了模型体积,并缩短了训练时间.
针对舰载火箭炮在海上射击时的精度问题,提出一种基于RBF神经网络对最优滑模控制进行优化的控制策略.首先,建立舰载火箭炮随动系统数学模型,结合线性二次型最优控制理论与滑模控制设计一种全局最优滑模控制器(GROSMC),既提高了系统响应速度又保证了良好的鲁棒性;接着,采用RBF神经网络对切换控制项的增益进行动态调节,削弱滑模在切换时的抖振问题;最后,通过仿真对比验证所设计控制器的有效性,表明该策略具有良好的控制性能,满足系统要求.
遥感图像实时检测是遥感应用领域的关键技术问题之一,针对目前主流的目标检测算法在图像处理器(GPU)上存在模型参数量大、实时性差、功耗大和成本高的问题,提出一种基于现场可编程门阵列(FPGA)的遥感图像实时检测方案.首先,为减少参数量、提高检测速度,采用MobileNetv2作为特征提取网络,融合深度可分离卷积,使得模型轻量化便于部署;接着,采用CA注意力模块提高检测精度;最后,将模型浮点数参数量化为8位定点数,并将量化后的网络模型在FPGA上完成部署.实验表明,在遥感数据集VisDrone 2019上,所提设计方案平均精度均值(mAP)达到14.79％,FPS达到46.78帧/s,平均功耗为8 W,比CPU提高375.4％的检测速度,比GPU降低96.8％的功耗.该方案可以满足实时目标检测的要求,并且能够部署在功耗受限的卫星、无人机等设备上.
随着人工智能和无人技术的发展应用,未来制空作战的规模化对抗进程加快.分析了未来制空作战平台及制空作战武器的发展情况,梳理了规模化空战具备的参战平台高密度协同对抗、制空武器饱和协同攻击、网络信息作为基础支撑的主要特点,从作战使用、生产制造、设计研制等方面分析了规模化空战对未来空空导弹发展的需求和影响,可为空空导弹的未来发展提供一定的技术借鉴.
针对无人机在三维空间里的航迹规划问题,从加快收敛速度和保证收敛效果的角度,对标准人工鱼群算法进行改进.首先,引入自适应视野和自适应步长的改善因子α,加快算法的收敛速度;然后,设定最小视野和最小步长,保证算法的搜索能力;最后,增加跳跃行为,确保算法在后期可以跳出局部最优.通过软件进行算法的仿真和对比验证,仿真实验结果表明,算法在搜索初期具有较快的搜索速度和较好的收敛效果,搜索后期可以跳出局部最优,算法的有效性得到验证;对比实验结果表明,算法在搜索后期,最佳适应度有所改善,算法的优越性得到验证.
针对红外无人机目标识别过程中特征信息较少、特征丢失严重、识别准确率低等问题,提出一种基于YOLOv7的红外无人机目标检测方法.通过引入注意力机制来增强目标区域的特征表达能力,提升图像的空间信息含量.采用改进的串行连接方式将通道注意力模块与空间注意力模块连接,在结合了目标通道特征信息和空间特征信息的同时,改进结构降低了通道注意力对红外图像识别的负面影响,可以更好地实现对红外目标的特征加强作用.选择基于角度向量回归的SIoU损失函数作为边框损失函数,进一步提升了模型的收敛性和检测精度.实验结果表明,改进的算法模型推理速度达到了43帧/s,准确率为95.4％,召回率为87.3％,mAP为96.1％,在红外无人机检测任务中取得了更好的检测效果.
近年来,深度学习虽然在合成孔径雷达(SAR)目标识别领域已得到广泛应用,但目前带有标注的SAR数据样本量的不足严重制约了深度学习在SAR目标识别中的发展.而迁移学习可以攻破深度学习数据驱动的限制,利用有限SAR样本进行迁移学习.对基于迁移学习的有限SAR样本目标识别算法进行了分析,首先,介绍了迁移学习的基本概念、类型、常用策略并分析了其在小样本SAR目标识别领域应用的可行性;然后,根据迁移数据与目标域数据是否同源,分别对两类基于迁移学习的方法在SAR图像识别领域具有代表性的算法进行了梳理归纳;最后,从样本量的不足与网络的普适性两个方向出发,讨论了迁移学习在SAR图像识别任务中存在的不足与下一步的研究方向.
针对新一代机载航空电子系统对航空电子网络的应用需求,分析了机载交换网络的结构特点,介绍了新一代航空电子网络系统的运行管理方法和航空电子时间敏感网络(ATSN)控制技术特点.通过对ATSN控制技术方案的详细说明,阐述了面向未来机载系统应用实现新一代机载数据通信交换网络控制的设计思路.
