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.     

Review and propositions for the sliding/impact wear behavior in a contact interface

A thermal-solid-liquid complex operational environment induces structural interface developing a typical coupling sliding/impact wear behavior. It results in contact damage until systems fail, which may cause significant economic losses and catastrophic consequences. The key point of solving this problem is to reveal the coupling damage mechanism of the sliding/impact behavior in typical systems and life characterization under a complicate evolving environment. This has been a hot topic in the area of mechanical reliability. The main work in this paper can be concluded as follows. Firstly, the main industries in which the “sliding/impact behavior” takes place have been introduced. Then, existing studies on the wear mechanism and degree analysis are presented, which includes surface morphology analysis, wear debris analysis, and wear degree measurement. Meanwhile, existing problems in theoretical modeling and experiments in current research are summarized, so as to point out a bright direction for future research on wear prediction. They include interface contact modeling, mathematic coupling mechanism modeling, wear equation establishment, and wear life characterization, which can provide some new ideas for improving the existing studies on the sliding/impact wear behavior.     

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。     

等质量异形粒子超高速撞击侵蚀

用数值方法模拟双锥，圆柱，椭球、圆锥和倒圆锥五类等质量异形铝粒子五种高宽比共２５种粒子对半无限铝靶的超高速撞击侵蚀，撞击速度为４ｋｍ／ｓ，给出了坑深、坑径、坑形参数和坑体积随粒子形状及高宽比的变化曲线。结果与非圆球异形粒子超高速撞击侵蚀计算有重要参考价值。     

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。     

Emergence of a Habitable Planet

We address the first several hundred million years of Earth’s history. The Moon-forming impact left Earth enveloped in a hot silicate atmosphere that cooled and condensed over ∼1,000 yrs. As it cooled the Earth degassed its volatiles into the atmosphere. It took another ∼2 Myrs for the magma ocean to freeze at the surface. The cooling rate was determined by atmospheric thermal blanketing. Tidal heating by the new Moon was a major energy source to the magma ocean. After the mantle solidified geothermal heat became climatologically insignificant, which allowed the steam atmosphere to condense, and left behind a ∼100 bar, ∼500 K CO₂ atmosphere. Thereafter cooling was governed by how quickly CO₂ was removed from the atmosphere. If subduction were efficient this could have taken as little as 10 million years. In this case the faint young Sun suggests that a lifeless Earth should have been cold and its oceans white with ice. But if carbonate subduction were inefficient the CO₂ would have mostly stayed in the atmosphere, which would have kept the surface near ∼500 K for many tens of millions of years. Hydrous minerals are harder to subduct than carbonates and there is a good chance that the Hadean mantle was dry. Hadean heat flow was locally high enough to ensure that any ice cover would have been thin (<5 m) in places. Moreover hundreds or thousands of asteroid impacts would have been big enough to melt the ice triggering brief impact summers. We suggest that plate tectonics as it works now was inadequate to handle typical Hadean heat flows of 0.2–0.5 W/m². In its place we hypothesize a convecting mantle capped by a ∼100 km deep basaltic mush that was relatively permeable to heat flow. Recycling and distillation of hydrous basalts produced granitic rocks very early, which is consistent with preserved >4 Ga detrital zircons. If carbonates in oceanic crust subducted as quickly as they formed, Earth could have been habitable as early as 10–20 Myrs after the Moon-forming impact.     

Modelling of Ejecta as a Space Debris Source

When a micro-debris or a micrometeoroid impacts a spacecraft surface, a large number of secondary particles, called ejecta, are produced. These particles can contribute to a modification of the debris environment: either locally by the occurrence of secondary impacts on the components of complex and large space structures, or at great distance by the formation of a population of small orbital debris. This paper describes firstly, the ejecta overall production, and secondly, the lifetime and the orbital evolution of the particles. Finally the repartition of ejecta in LEO is computed. Some results describing the population as a function of size and altitude are presented.     

利用遥测数据预报导弹落点的方法

给出利用遥测数据对导弹进行落点预报的方法。根据遥测数据传输多遍的特点，对解码后的ＰＣＭ 数据进行处理，得到误码率很小的数据。然后对头体分离时刻前导弹飞行的状况和遥测数据进行分析，从而对发动机后效误差进行修正，得到较精确的导弹运动参数，最后利用弹道方程预报导弹落点     

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     

超声振动体的耦合振动研究

对一些典型的大尺寸超声振动体如圆柱体、空心圆柱体、长条形六面体和大矩形六面体。本文用通用有限元软件对耦合系数的分布进行了分析，并在耦合振动频率方程的基础上研究了耦合系数与耦合振动的强度之间的关系。