Semi-supervised gear fault diagnosis using raw vibration signal based on deep learning

In aerospace industry, gears are the most common parts of a mechanical transmission system. Gear pitting faults could cause the transmission system to crash and give rise to safety disaster. It is always a challenging problem to diagnose the gear pitting condition directly through the raw signal of vibration. In this paper, a novel method named augmented deep sparse autoencoder (ADSAE) is proposed. The method can be used to diagnose the gear pitting fault with relatively few raw vibration signal data. This method is mainly based on the theory of pitting fault diagnosis and creatively combines with both data augmentation ideology and the deep sparse autoencoder algorithm for the fault diagnosis of gear wear. The effectiveness of the proposed method is validated by experiments of six types of gear pitting conditions. The results show that the ADSAE method can effectively increase the network generalization ability and robustness with very high accuracy. This method can effectively diagnose different gear pitting conditions and show the obvious trend according to the severity of gear wear faults. The results obtained by the ADSAE method proposed in this paper are compared with those obtained by other common deep learning methods. This paper provides an important insight into the field of gear fault diagnosis based on deep learning and has a potential practical application value.     

深空探测器推进系统

以技术较成效的月球探测器、火星探测器推进系统为重点，介绍了国外深空探测活动的情况。简述了深空探测对推进系统的需求、我国航天器液体推进技术的现状。认为我国的推进技术经一些适应性发展，即可满足深空探测的需求，并且设想了我国近期较为可行的深空探测器推进系统方案。     

深空探测通信技术发展趋势及思考

阐述了深空探测通信的重要地位和意义，就深空探测通信中的主要问题和特点开展论述，分析了深空探测通信的国内外研究现状。提出了利用地球静止轨道卫星编队的方法构建我国自主的天基连续测控和通信系统的构想，并以月球为中继、利用地月系统内的拉格朗日点开展深空探测。建议当前开展深空探测通信中星际互联网络体系结构、高效信道编码技术和空间协议研究的构想。     

基于局部几何特征的稠密点云配准方法

针对现有的稠密点云配准方法依赖初始位置设定、计算成本高、配准成功率不高等问题，提出了一种基于点云局部几何特征的稠密点云配准方法。采用深度卷积网络模型提取点云的局部几何特征，从而减少了三维点云数据的噪声、低分辨率和不完备性等带来的影响。在此基础上，使用K维树搜索完成局部几何特征描述子的关联工作。最后，通过随机采样一致算法对点云的相对位姿进行鲁棒的估计。通过对开源数据集上5个典型场景中的数据测试表明，该方法的配准成功率达到92.5%，配准精度达到0.0434m，配准时间相对最邻点迭代配准算法缩短了74.7%，实验结果验证了该方法的有效性、实时性和鲁棒性。     

Expectations for Infrared Spectroscopy of 9P/Tempel 1 from Deep Impact

The science payload on the Deep Impact mission includes a 1.05–4.8 μm infrared spectrometer with a spectral resolution ranging from R∼200–900. The Deep Impact IR spectrometer was designed to optimize, within engineering and cost constraints, observations of the dust, gas, and nucleus of 9P/Tempel 1. The wavelength range includes absorption and emission features from ices, silicates, organics, and many gases that are known to be, or anticipated to be, present on comets. The expected data will provide measurements at previously unseen spatial resolution before, during, and after our cratering experiment at the comet 9P/Tempel 1. This article explores the unique aspects of the Deep Impact IR spectrometer experiment, presents a range of expectations for spectral data of 9P/Tempel 1, and summarizes the specific science objectives at each phase of the mission.     

深空测控通信技术发展趋势分析

为满足21世纪我国深空探测任务的需要，参考国外深空测控通信系统的先进技术，归纳和总结了未来相关技术发展的7个趋势，为我国深空测控通信技术的发展提供一些参考。     

深空探测器无线电干涉测量开源数据处理系统构建及试验

为更好地开展深空无线电干涉测量试验,基于DiFX(Distributed FX,分布式FX型相关处理)、SPICE(Spacecraft Planet Instrument Camera-matrix Events,航天器行星仪器照相机矩阵事件)、HOPS(Haystack Observatory Postprocessing System,Haystack克天文台后处理系统)及AIPS(Astronomical Image Processing System,天文图像处理系统)等开源软件,搭建了一套可用于深空探测器信号相关处理的无线电干涉测量数据处理系统。首先介绍了该系统的整体架构及组成,然后介绍了系统各组成模块的功能及工作原理,最后利用该系统对嫦娥三号着陆器开展了观测试验,并对观测数据进行了处理。试验结果表明,该系统能成功实现深空航天器信号的相关处理、条纹拟合,以及时延解算等功能,有望为我国嫦娥五号任务及火星探测任务数据处理提供支持。     

基于深度学习的组合体航天器模型预测控制

利用模型预测算法先预测控制结果后控制的类人行为特点，借助深度学习在多参数寻优上的优势，提出了一种基于卷积神经网络的模型预测控制算法，满足航天工程低硬件需求，实现组合航天器多场景下姿态控制律的重构。该算法首先利用模型预测控制将组合航天器从初始状态控制到预期状态，然后将控制过程中状态量用于3层3核卷积神经网络的训练，训练完成后，用该卷积神经网络代替模型预测对组合航天器进行控制，从而降低计算资源需求。仿真校验表明：该算法可预测5个控制周期内的控制参数，相比传统模型预测算法所需硬件计算时间降低约5倍，在一般硬件环境下30 s内即可完成各场景下的组合航天器姿态控制，控制精度在10 -4 量级。     

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.     

离子推力器多模式化研究

为了实现离子推力器多模式化,分析了离子推力器功率宽范围调节限制因素,提出了两种宽范围调节策略;针对我国小行星探测任务,完成了30cm多模式离子推力器研制、功率宽范围调节限制条件确定、以及两种调节策略下多模式工作点设计及对比研究。结果显示,通过降低放电室磁场强度可延伸离子推力器最小稳定工作功率,提高束流均匀性,实现离子推力器更宽功率范围多工作点设计;功率宽范围调节主要是屏栅电压和束电流的宽范围调节,二者通过栅极导流系数限制和交叉限制而约束;推力随功率增加呈线性增加关系,比冲随功率的增加总体上呈先快速增加后趋于稳定的趋势;30cm多模式离子推力器在0.25kW～5kW内稳定工作,推力10mN～186mN,比冲1522s～3586s。