Improving orbit prediction accuracy through supervised machine learning

Due to the lack of information such as the space environment condition and resident space objects’ (RSOs’) body characteristics, current orbit predictions that are solely grounded on physics-based models may fail to achieve required accuracy for collision avoidance and have led to satellite collisions already. This paper presents a methodology to predict RSOs’ trajectories with higher accuracy than that of the current methods. Inspired by the machine learning (ML) theory through which the models are learned based on large amounts of observed data and the prediction is conducted without explicitly modeling space objects and space environment, the proposed ML approach integrates physics-based orbit prediction algorithms with a learning-based process that focuses on reducing the prediction errors. Using a simulation-based space catalog environment as the test bed, the paper demonstrates three types of generalization capability for the proposed ML approach: (1) the ML model can be used to improve the same RSO’s orbit information that is not available during the learning process but shares the same time interval as the training data; (2) the ML model can be used to improve predictions of the same RSO at future epochs; and (3) the ML model based on a RSO can be applied to other RSOs that share some common features.     

我国高校无形资产经营管理分析

高等学校的无形资产经营管理是市场经济条件下各个高校需要解决的一个难题和重点。分析我国高校无形资产经营管理的现状及其问题,并给出相关政策建设。对加快相关的法规建设,规范高校无形资产经营管理具有现实意义。     

复合材料钻削刀具状态集成学习分类技术

刀具状态监测关系到工件加工质量,因此实时掌握刀具的磨损状态具有重要的意义。针对单一模式识别分类器的局限性,提出了基于异态集成学习模型的刀具状态监测系统。在该系统中,根据集成学习基分类器选择原则,选取了支持向量机(SVM)、隐马尔科夫模型(HMM)以及径向基神经网络(RBF)这3个单分类器作为基分类器。为了验证监测系统的有效性,进行了复合材料钻削实验,提取了加工过程中的钻削力信号、振动信号的时域特征并利用局部保持法(LPP)进行了特征选择。通过与单分类器和集成学习分类效果的对比,表明了集成学习模型相比于单一基分类器具有更高的分类精度和更好的稳定性。     

基于改进HHT的一体化电液作动器故障诊断

介绍了机载变排量变转速一体化电动静液作动器(EHA-VPVM,Electro-Hydrostatic Actuator with Variable Pump displacement and Variable Motor speed)的系统结构,根据EHA-VPVM早期故障信号非平稳、时变等特点,采用一种新的时频分析方法希尔伯特黄变换(HHT,Hilbert-Huang Transform)进行信号分析.针对HHT方法的模态混叠和虚假本征模态函数问题,提出两点改进:通过集合经验模式分解算法抑制模态混叠的发生;采用相关系数法保留真实本征模态函数.对EHA-VPVM工程样机进行早期故障诊断实验,用Hilbert边际谱和HHT谱分析永磁无刷直流电机两种工作状态下的振动信号.实验结果表明:改进HHT方法较好解决了HHT的模态混叠和虚假本征模态函数问题,能准确提取研究对象的早期故障特征,对EHA-VPVM早期故障具有良好的诊断效果.     

基于CEEMDAN降噪与双谱分析的滚动轴承故障诊断

滚动轴承早期故障信号中的噪声成分会影响到故障特征的提取。为了提高含噪故障信号中滚动轴承早期故障特征提 取的准确性，将基于自适应噪声的完备经验模态分解（CEEMDAN）用于滚动轴承振动信号的降噪中，并对降噪后的轴承故障信号 进行双谱分析。结果表明：CEEMDAN可有效去除轴承振动信号中的低频噪声干扰，经CEEMDAN降噪后的不同轴承故障信号的 双谱全局图存在明显差异，根据这些差异可在宏观上对不同轴承故障加以区分；通过经CEEMDAN降噪后的不同轴承故障信号的 双谱细节图可以正确提取不同轴承故障的特征频率，从而实现对各轴承故障的有效诊断。CEEMDAN降噪结合双谱分析可为滚 动轴承故障诊断提供一种新的有效方法。     

Learning Routes from Visualizations for Indoor Wayfinding: Presentation Modes and Individual Differences

Abstract

Participants (N = 78) studied a visualization of a route through a complex building and walked that route in the real building without further assistance. Erroneous turns on the route as well as indicators of uncertainty such as hesitations were assessed. Three types of route visualizations were compared: (1) an allocentric, map-based visualization with the route indicated in floor maps, (2) an ordered sequence of pictures of decision points shown from the egocentric perspective, and (3) an animation showing a virtual walk of the route from the egocentric perspective. In addition to the experimental variation, gender differences, differences in visual-spatial abilities and differences in self-reported wayfinding strategies were considered as predictor variables. Wayfinding performance did not differ between allocentric (map) and egocentric (decision point pictures and animation) visualizations. However, wayfinding performance was better with animated than with static egocentric visualizations. Individual differences in the ability to encode visual-spatial information from the visualization played a critical role for route learning. Self-reported sense of direction related to egocentric wayfinding strategies also predicted wayfinding performance. Gender differences were attributable to differences in visual-spatial abilities and egocentric wayfinding strategies. Interactions between visualizations and individual differences were not found. It is concluded that animations of virtual walks are suitable to convey route information in complex buildings. Successful acquisition of route knowledge from maps is possible but might depend on the comprehensibility of the structure of the building.     

中国共产党人学习观研究述评

学习在多学科的共同探索和推进下,已成为当下的一个前沿和热门课题。由此,探究当前中国共产党人学习观研究中已取得的主要理论成果、薄弱环节、有待进一步创新之处,对于进一步深化对中国共产党人学习观的科学研究,构筑一个完整的中国共产党人学习观的科学体系具有重要意义。     

飞行员导航专家系统

论述一个飞行员导航专家系统方案。此系统包括二次通道：飞行员助理（ＰＡ）通道和飞行员助理学习（ＰＡＬ）通道。ＰＡ通道完成导航计算、形势判断和决策，通道还将显示出当前形势及给飞行员提出的建议。ＰＡＬ通道完成知识库（ＫＢ）的更新，包括：对飞行员完成的操作作出评价、综合归纳知识和规则以及知识库的修正更新。对系统所涉及的一些原则方法和算法进行了研究。     

基于卷积神经网络的航天复合材料缺陷智能检测

针对传统的缺陷图像识别处理方式存在着准确度与辨识度不足,且处理缺陷种类单一的问题,提出了一种基于Cascade R-CNN和Mask R-CNN的神经网络模型。首先,为了提高缺陷检测的可视化效果和检测准确度,在实例分割卷积网络Mask R-CNN的基础上,结合级联神经网络Cascade R-CNN结构,组合成了新的级联实例分割Cascade Mask R-CNN网络;其次,对组合而成的级联卷积神经网络进行了训练,将训练好的模型对复合材料缺陷图像进行了检测。实验结果表明:检测的平均准确度达到了91.5%,平均置信度达到了97.3%,达到了检测精度的要求。该研究成果可运用于航天复合材料缺陷识别。     

航空发动机叶片表面损伤与检测研究进展

航空发动机叶片的工作环境极其恶劣,表面会出现各种类型的损伤。在损伤早期进行表面检测能够有效预防因损伤扩展导致的叶片失效断裂。发动机叶片表面损伤的检测和评估主要由人工操作,严重依赖工作经验,但人工检测不仅效率低下,而且检测结果容易受到人为因素的影响。为了高效、高精度地检测发动机叶片表面损伤,从叶片失效形式出发,综述了发动机叶片在停放和运行2种状态下的损伤机理,并重点阐述了涡流检测、渗透检测等常用于叶片表面损伤检测的方法。总结了基于机器视觉的检测技术,分析机器视觉检测面临数据集稀缺和单一性的挑战,认为收集大量数据并进一步完善评估标准是未来发动机叶片表面损伤检测系统研究的重点方向。