舰载飞机自动着舰系统的研究

介绍了舰载飞机的自动着舰系统（包括了飞机的飞行控制系统，推力控制系统及航空母舰的导引系统），并指出只有精确地控制飞机的不滑轨迹，才能使飞机在航空母舰上安全降落，本文着得讨论俯仰指令型的纵向自动着舰系统的原理、结构及设计，并指出导引指令中对舰体运动的补偿。     

精密GPS卫星钟差的改正和应用

分析了GPS卫生钟差的变化特性，探讨了利用GPS地面跟踪站的观测数据估算GPS卫星钟差的可行性，建立了相应的算法和软件系统，并把由地面跟踪站的实测数据估算的卫星钟差用于星载GPS定轨计算，得到优于1m的定轨精度。     

机器人运动的学习控制

机器人学习控制旨在采用简单的控制器结构和易于实现的控制算法,提高机器人轨迹动态跟踪精度。本文讨论了机器人控制研究中存在的困难,简要回顾了早期学习控制思想的形成和发展,重点介绍了近年来国内外有关机器人学习控制研究的现状。     

X-ray synchrotron nebulae and the origin of neutron stars

“With all reserve, we advance the view that a supernova represents the transition of an ordinary star into a neutron star.”This conclusion, reached just 50 years ago in a classic paper by Walter Baade and Fritz Zwicky (1934), was published three decades before the first direct observational evidence for the existence of neutron stars was uncovered. It still informs the standard picture of neutron star production in the Galaxy. We examine herein some recent evidence bearing on this question which has been derived from Observatory X-ray observations of supernova remnants and radio pulsars. In particular, the discovery that X-ray synchrotron nebulae are found surrounding most young ( 10⁶ yr) pulsars observed to date is discussed. We explore the implications of the lack of such nebulae in the majority of supernova remnants (SNR) for the properties and frequency of neutron star formation in supernova events.     

A319飞机APU启动故障可靠性调查

本文对A319飞机131-9A型APU启动不正常事件进行可靠性调查,对APU启动故障统计分析,对影响启动的部件采取如下措施:老式启动保险6KA质量差主动更换且飞机上配备6KA;启动马达-3构型降级为-2以提高寿命,后续再升级至更高寿命的-4构型;执行改装加长启动线路以降低启动电流;点火激励器软时限控制定期拆下送厂检测。通过针对性措施,有效减少了APU启动不正常事件的发生。     

黄渤海晴空像元下雾霾识别的机器学习算法

为实时有效地识别和监测雾霾，选取2013年10月4日与10月5日的两景MODIS遥感图像，利用不同类型像元的光谱差异，基于神经网络模型，建立海上雾霾的遥感识别机器学习算法。经检验表明，在晴空条件下，机器学习算法反演精度相对较高，已超过98%，利用算法可以实现对中国近海上空雾霾的监测。     

简论高校实验课程的改革

实验教学是高等院校教学过程的一个重要环节,应建立新型的实验室管理模式,从开放实验室和改革教学方法两个方面出发,阐述了实验课程改革的必要性。     

直升机超短波通信链路分析

通过对超短波通信链路的分析,得出直升机超短波通信链路模型;以实现超短波电台通信距离要求为目标,分析通信链路中影响通信距离的各因素及其影响程度,并根据直升机实际情况,对机上配置多部超短波电台及与其他机载设备的电磁兼容性方面提出改善建议。     

战斗机嵌入式训练系统中的智能虚拟陪练

智能化"实虚"对抗是现代先进战斗机嵌入式训练系统的重要功能需求。自主空战决策控制技术在未来空战装备发展中扮演关键角色。将当前的功能需求和发展中的技术结合起来,得到了空战智能虚拟陪练的概念。先进控制决策技术的引入使得智能虚拟陪练能够帮助飞行员完成复杂的战术训练,而训练中真实的对抗场景为技术的验证提供了理想的环境,大量的训练数据为技术的持续迭代优化提供了保障。作为可学习和进化的空战战术专家,智能陪练在人机对抗和自我对抗中不断优化,当其具备与人相当甚至超越人的战术能力时,可应用于未来的无人空战系统。智能虚拟陪练需要具备4项基本能力：智能决策能力、知识学习能力、对抗自优化能力和参数化表示能力。对其包含的关键技术进行了分析,提出并实现了一个基于模糊推理、神经网络和强化学习的解决方案,展示了其各项基本能力及目前达到的空战水平。未来更多的模型和算法可在智能虚拟陪练的框架中进行验证和优化。     

Coactive design of explainable agent-based task planning and deep reinforcement learning for human-UAVs teamwork

Unmanned Aerial Vehicles (UAVs) are useful in dangerous and dynamic tasks such as search-and-rescue, forest surveillance, and anti-terrorist operations. These tasks can be solved better through the collaboration of multiple UAVs under human supervision. However, it is still difficult for human to monitor, understand, predict and control the behaviors of the UAVs due to the task complexity as well as the black-box machine learning and planning algorithms being used. In this paper, the coactive design method is adopted to analyze the cognitive capabilities required for the tasks and design the interdependencies among the heterogeneous teammates of UAVs or human for coherent collaboration. Then, an agent-based task planner is proposed to automatically decompose a complex task into a sequence of explainable subtasks under constrains of resources, execution time, social rules and costs. Besides, a deep reinforcement learning approach is designed for the UAVs to learn optimal policies of a flocking behavior and a path planner that are easy for the human operator to understand and control. Finally, a mixed-initiative action selection mechanism is used to evaluate the learned policies as well as the human’s decisions. Experimental results demonstrate the effectiveness of the proposed methods.