Maneuvering target tracking of UAV based on MN-DDPG and transfer learning

Tracking maneuvering target in real time autonomously and accurately in an uncertain environment is one of the challenging missions for unmanned aerial vehicles(UAVs).In this paper,aiming to address the control problem of maneuvering target tracking and obstacle avoidance,an online path planning approach for UAV is developed based on deep reinforcement learning.Through end-to-end learning powered by neural networks,the proposed approach can achieve the perception of the environment and continuous motion output control.This proposed approach includes:(1)A deep deterministic policy gradient(DDPG)-based control framework to provide learning and autonomous decision-making capa-bility for UAVs;(2)An improved method named MN-DDPG for introducing a type of mixed noises to assist UAV with exploring stochastic strategies for online optimal planning;and(3)An algorithm of task-decomposition and pre-training for efficient transfer learning to improve the generalization capability of UAV's control model built based on MN-DDPG.The experimental simulation results have verified that the proposed approach can achieve good self-adaptive adjustment of UAV's flight attitude in the tasks of maneuvering target tracking with a significant improvement in generalization capability and training efficiency of UAV tracking controller in uncertain environments.     

Survivability assessment of spacecraft impacted by orbit debris

To help optimize the spacecraft design and reduce the risk of spacecraft mission failure, a new approach to assess the survivability of spacecraft in orbit is presented here, including the following three steps:1) Sensitivity Analysis of spacecraft. A new sensitivity analysis method, a ray method based on virtual outer wall, is presented here. Using rays to simulate the debris cloud can effectively address the component shadowing issues. 2) Component Vulnerability analysis of spacecraft. A function"Component functional reduction degree — Component physical damage degree"is provided here to clearly describe the component functional reduction. 3) System-level Survivability Assessment of spacecraft. A new method based on expert knowledge reasoning, instead of traditional artificial failure tree method, is presented here to greatly improve the efficiency and accuracy of calculation.     

作战构想风险性评估模型

作战构想是制定作战方案、定下作战决心的依据,在任务规划中起着承上启下的作用,意义重大.针对构想风险难以定量分析的难题,基于作战构想的组成要素、战场情况分析研判数据,从周密性、机动、打击、防护等角度构建了作战构想风险性评估指标体系,并提出了对各个指标进行定量分析的评估模型.最后,采用实例对提出的方法进行了验证,结果表明,该方法可行有效,避免了定性分析中存在的主观性、模糊性等不足,为作战构想评估提供了新的思路和方法.     

基于GEO SAR辐射的星机协同融合探测系统

为提高机载平台对隐身目标的探测能力,提出一种基于地球同步轨道合成孔径雷达(GEO SAR)辐射、多个机载平台接收的多基雷达协同探测系统,该系统具有覆盖范围广、机载射频隐身、生存能力强等优势.分析了星机协同的作战优势,可获取目标RCS空间闪烁增益、双基RCS增益以及融合增益.分析了星机双基协同探测威力与多基融合探测威力,可提高隐身目标探测距离.通过仿真实验验证了分析的有效性.     

战场弹药储备布局探索性分析决策方法

对战场弹药储备布局决策问题进行了详细的分析,建立了相应的多目标优化数学模型,并利用探索性分析方法实现了战场弹药存储布局问题的决策方案。     

天基反卫星攻击模式研究

为了探讨反卫星导弹动能杀伤弹头的机动性能对反卫星作战的影响,建立了反卫星导弹的动能杀伤弹头的六自由度模型.对动能杀伤弹头的六自由度模型进行仿真,通过讨论不同可用过载下动能杀伤弹头的攻击区特征,总结动能杀伤弹头的机动性能,提出了天基反卫星的前置攻击模式.仿真结果证明这种攻击模式更有利于天基反卫星的实现.     

建筑中庭排烟性能化设计与分析

采用火灾烟气控制工程计算方法,设定较适合的火灾场景,对某中庭建筑排烟方式进行性能化分析,得出采取自然排烟方式的可行性建议,并确定了排烟设备的选型、数量和控制方式。     

基于LabVIEW的齿轮箱故障诊断

着重介绍了齿轮箱故障诊断系统的实现过程和设计思想,及通过虚拟仪器开发软件LabVIEW、小波变换和神经网络技术,来实现齿轮箱故障诊断系统的核心内容,最后通过实例验证了此设计的可行性。     

基于LabVIEW的变速箱状态检测系统

采用门限关联度理论进行变速箱状态检测,并构建了以虚拟仪器为核心的变速箱状态采集系统,建立了表征变速箱状态的特征参量和正常故障判定准则,采用LabVIEW开发了检测与故障判定软件系统。     

阶次跟踪分析在齿面磨损故障诊断中的应用

详细讨论了阶次跟踪分析的原理,并与传统频谱分析进行了比较,阐述了阶次跟踪分析的优越性及重采样方法实现的原理,通过对某型齿轮箱齿面磨损故障进行实例验证并提取特征参量,证明其有效性。