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.     

Effect of bristle pack position on the rotordynamic characteristics of brush-labyrinth seals at various operating conditions

Over the last few decades, the research on the effect of bristle pack position on the rotordynamic characteristics of the brush-labyrinth seals is not sufficient. To this end, two kinds of brush-labyrinth seals for the bristle pack element installed upstream of the labyrinth teeth named BSU and installed downstream of the labyrinth teeth called BSD were used to investigate the effect of bristle pack position on the rotordynamic characteristics of the brush-labyrinth seals. Using the numerical model combining the porous medium model and the whirling rotor method, the rotordynamic characteristics of the BSU and BSD at various operating conditions including four kinds of pressure ratios, five kinds of inlet preswirl speeds and four kinds of rotor spinning speeds were conducted. The obtained results show that the effects of operating conditions on rotordynamic coefficients for the different seal configurations are different. The direct stiffness, cross-coupled stiffness and direct damping of the BSU are lower than those of the BSD. The rotordynamic coefficients of the BSU are more insensitive to the operating conditions variation. From the perspective of the seal stability, the BSU is a better brush-labyrinth seal configuration at high pressure ratio, high positive preswirl or high rotor spinning speed conditions. While in the case of low pressure ratio, low positive preswirl or low rotor spinning speed conditions, the BSD is a better choice.     

针对旋翼流场模拟的自适应网格算法

针对基于格心格式求解器的旋翼流场模拟,提出了相应的自适应笛卡尔网格的数据存储结构及自适应算法。给出了相应的单元处理策略,简化了对自适应笛卡尔网格的处理;对于频繁的自适应加密过程中产生的大量重复点,采用了高效的交替数字树算法(Alternating digital tree,ADT)予以删除;对于自适应疏化过程中产生的大量无用点,提出了标记-删除-移动(Mark,delete,move,MDM)算法予以快速地删除,减少了不必要的计算资源消耗。对CaradonnaTung旋翼在不同悬停状态下进行了模拟验证,对比了压力分布系数与桨尖涡位置。之后对HELISHAPE 7A旋翼在前飞情况下进行了模拟验证,计算值与实验值吻合。此外,求解器对桨尖涡的捕捉效果得到了明显的提高,表明本文方法具有良好的有效性与鲁棒性。     

基于合成射流的旋翼翼型动态失速控制研究

针对直升机旋翼工作环境下来流速度和迎角(Angle of attack,AoA)耦合引起的动态失速问题,建立了基于合成射流的旋翼动态失速控制的数值模拟方法。采用运动嵌套网格方法,通过对翼型的平移和旋转实现变来流速度-变迎角的耦合。以积分形式的雷诺平均N-S方程为主控方程,空间离散使用Roe格式,时间离散为隐式LU-SGS方法,以OA209翼型为研究对象,在翼型上表面放置合成射流激振器,开展了射流位置、动量系数、无量纲频率以及偏角等参数对轻度失速、深度失速下翼型动态失速控制的研究。研究发现,轻度失速下,射流位置靠近气流分离点时(20%c附近,c为翼型弦长),对逆压梯度引起的轻度失速控制效果最佳。深度失速下气流分离点虽在5%c之前,但射流位于前缘分离泡后端(10%c附近)时控制效果较好。大迎角需要较大的动量系数才能有效控制。射流频率对涡结构的尺寸和数量会产生一定影响,能改变气动特性波动幅度。较小的射流偏角对轻度失速的控制更有效,而深度失速则需要较大的偏角。     

预测悬停旋翼跨音速流动的一种组合自由尾流/CFD方法

一种新的组合自由尾流 / CFD方法用于悬停旋翼流动的 CFD解中以考虑实际尾流的作用 .用文中描述的尾流分析方法研究了螺旋尖涡的运动 .首先从广义尾流模型开始 ,用半经验公式模化了涡核对旋翼尾流的作用 ;然后在环量收敛和尾迹收敛的条件下完成了自由尾迹计算 ;最后应用 Jameson有限体积龙格 -库塔推进格式求解了欧拉方程 .所得结果与相关文献和实验数据进行了比较     

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。     

微制造隔振试验平台定位系统的轨迹规划

为减小运动部件加减速过程中对整个平台的冲击,在进行运动轨迹规划时,采用了S形曲线对定位系统的运动轨迹进行了平滑处理,有效地降低了运动部件对系统的冲击,有利于系统的减振。     

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。     

扩压器-水泵内非稳定流动研究

水泵内部流动实质上是复杂的三维非稳定流动 ,它对水泵性能及结构振动有重要影响。本文介绍了一种求解这种复杂内流动的数值方法。三维雷诺数平均的纳维斯托克斯方程 ( 3-DReynolds-averaged Navier-Stokes,RANS)以及标准 k-ε的方程用于描述水泵内非定常紊流流场。系统特性方程与水泵的 CFD模型相结合以考虑流体在管道中的加速 ;采用任意滑移网格界面模拟叶轮和静止部件之间的相互干涉 ;将整个叶轮作为分析对象 ,以考虑失速情况下流动的周向非对称。这些技术的结合包括了水泵内非稳定流动的物理实质。一台实验数据比较齐全的离心式 -扩压器水泵被用于验证所提出的数值方法     

某直升机主桨叶翼型改进后经典颤振分析

直升机经典颤振分析是研究刚性桨叶的最低阶挥舞模态与最低阶扭转模态的耦合不稳定性。经过直升机的理论研究与实验研究,已经形成了一套工程上实用的计算方法。这套方法是建立在金属铰接式旋翼之上。本文计算分析了某型机旋翼主桨叶翼型由NACA0012改进为TSAGI 12.XX翼型后旋翼的经典颤振。