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.     

太阳能飞机循环飞行的高度剖面能量策略

为满足设定的太阳能飞机多日连续飞行条件，依据飞行过程中当前时刻的飞行高度、光伏输出功率、动力电池组余量等系统状态参数，研究如何分配动力电池组充放电和电推进系统输入等功率。所用策略立足于实时功率平衡，充分利用正午前后的光伏峰值功率用于飞机爬升及充电，在午后下滑过程中利用全部光伏输出，以最大化利用光伏资源；在光伏有效输出不足时则以一定的维持功率下滑，使能量的综合损失最小。方法能够提高以预定夜间飞行高度连续多日续航的成功率，提升飞行高度、纬度、季节范围或搭载能力，或者拓展这几种飞行条件的组合域，优化太阳能飞机的适用性。     

一种基于虚拟页地址映射的NAND Flash管理算法

本文提出了一种基于虚拟页地址映射的NAND Flash管理算法.该算法通过定义坏块表、对应表等结构，以及设计的坏块替换策略和虚拟页地址到实际物理页地址的转换算法，实现上层软件采用虚拟地址对NAND Flash的无坏块连续页地址访问.该算法是一种高效的地址映射算法，能高效地对数据进行索引，占用SRAM空间较少，使系统达到高性能，并使得闪存使用的更加稳定持久.     

27-day variation in solar-terrestrial parameters: Global characteristics and an origin based approach of the signals

The Earth and the near interplanetary medium are affected by the Sun in different ways. Those processes generated in the Sun that induce perturbations into the Magnetosphere-Ionosphere system are called geoeffective processes and show a wide range of temporal variations, like the 11-year solar cycle (long term variations), the variation of ～27?days (recurrent variations), solar storms enduring for some days, particle acceleration events lasting for some hours, etc.In this article, the periodicity of ～27?days associated with the solar synodic rotation period is investigated. The work is mainly focused on studying the resulting 27-day periodic signal in the magnetic activity, by the analysis of the horizontal component of the magnetic field registered on a set of 103 magnetic observatories distributed around the world. For this a new method to isolate the periodicity of interest has been developed consisting of two main steps: the first one consists of removing the linear trend corresponding to every calendar year from the data series, and the second one of removing from the resulting series a smoothed version of it obtained by applying a 30-day moving average. The result at the end of this process is a data series in which all the signal with periods larger than 30?days are canceled.The most important characteristics observed in the resulting signals are two main amplitude modulations: the first and most prominent related to the 11-year solar cycle and the second one with a semiannual pattern. In addition, the amplitude of the signal shows a dependence on the geomagnetic latitude of the observatory with a significant discontinuity at approx. ±60°.The processing scheme was also applied to other parameters that are widely used to characterize the energy transfer from the Sun to the Earth: F10.7 and Mg II indices and the ionospheric vertical total electron content (vTEC) were considered for radiative interactions; and the solar wind velocity for the non-radiative interactions between the solar wind and the magnetosphere. The 27-day signal obtained in the magnetic activity was compared with the signals found in the other parameters resulting in a series of cross-correlations curves with maximum correlation between 3 and 5?days of delays for the radiative and between 0 and 1?days of delay for the non-radiative parameters. This result supports the idea that the physical process responsible for the 27-day signal in the magnetic activity is related to the solar wind and not to the solar electromagnetic radiation.     

杆的纵向振动分析

杆的纵向振动是连续系统的内容，一个连续系统具有分布质量，分丰弹性，分布阻尼，杆的纵向振动可用波动方程来描述，是用空间与时间坐标来描述的，运动方程是偏微方程。     

多孔高氯酸铵的制备及其对固体推进剂燃速的影响

介绍美国和台湾用对流炉和沸腾床制备多孔高氯酸铵(PAP)及包覆法。同时介绍了用PAP部分取代HTPB体系推进剂中的AP和全部取代双基推进剂中的超细AP的燃烧性能研究。结果表明,用包覆的PAP取代超细AP是提高燃速的较好途径。     

企业本质、企业绩效与会计分析的逻辑关系

企业本质被界定为不完备要素使用权资本化交易合约履行的过程，从价值角度可以描述为财务资本、人力资本、组织资本与社会资本的一个不完全契约组合。正确认识企业本质是探讨企业绩效决定因素的关键，会计分析必须从企业资本有机构成角度来衡量企业绩效。     

一万氧压机轴振动控制分析与实践

本文介绍了一种非常规的高速轴振动抑制方法，主要是用振源分析技术，通过确诊设备故障原因来分析影响轴振动的主要因素，调节机器的系统刚度，再通过理论计算修订安装参数，制定设备故障处理对策，在涟源钢铁集团有限公司一万氧压机组上的实践取得了相当满意的效果，很有推广价值。     

球形铝粉的凝聚／燃烧特性

球形与非球形铝粉的表面分析表明,前者表面层比后者均匀;试验表明球形铝粉比非球形铝粉抗凝聚能力好,化学反应能力较差.因此球形铝粉在推进剂燃面形成的凝滴较小,凝滴燃烧速度较慢.这些特性对球形铝粉的合理使用具有指导意义.     

飞行器振动智能分析与诊断

本文通过综合多个领域知识，引进功能特征描述概念，运用证据理论，提出了对飞行器等复杂系统进行分析诊断的一个新方法并初步完成了专家系统原型，通过具体实例，再现了故障现象