A new bearing fault diagnosis method based on modified convolutional neural networks

Fault diagnosis is vital in manufacturing system. However, the first step of the traditional fault diagnosis method is to process the signal, extract the features and then put the features into a selected classifier for classification. The process of feature extraction depends on the experimenters’ experience, and the classification rate of the shallow diagnostic model does not achieve satisfactory results. In view of these problems, this paper proposes a method of converting raw signals into two-dimensional images. This method can extract the features of the converted two-dimensional images and eliminate the impact of expert’s experience on the feature extraction process. And it follows by proposing an intelligent diagnosis algorithm based on Convolution Neural Network (CNN), which can automatically accomplish the process of the feature extraction and fault diagnosis. The effect of this method is verified by bearing data. The influence of different sample sizes and different load conditions on the diagnostic capability of this method is analyzed. The results show that the proposed method is effective and can meet the timeliness requirements of fault diagnosis.     

A drilling tool design and in situ identification of planetary regolith mechanical parameters

The physical and mechanical properties as well as the heat flux of regolith are critical evidence in the study of planetary origin and evolution. Moreover, the mechanical properties of planetary regolith have great value for guiding future human planetary activities. For planetary subsurface exploration, an inchworm boring robot (IBR) has been proposed to penetrate the regolith, and the mechanical properties of the regolith are expected to be simultaneously investigated during the penetration process using the drilling tool on the IBR. This paper provides a preliminary study of an in situ method for measuring planetary regolith mechanical parameters using a drilling tool on a test bed. A conical-screw drilling tool was designed, and its drilling load characteristics were experimentally analyzed. Based on the drilling tool-regolith interaction model, two identification methods for determining the planetary regolith bearing and shearing parameters are proposed. The bearing and shearing parameters of lunar regolith simulant were successfully determined according to the pressure-sinkage tests and shear tests conducted on the test bed. The effects of the operating parameters on the identification results were also analyzed. The results indicate a feasible scheme for future planetary subsurface exploration.     

月球表层采样样品智能确认方法

表层采样是月球采样探测的重要方式，样品智能确认有助于提升工作效率与复杂问题处理能力。结合月球表层采样铲挖工作过程，分析了铲挖过程中臂载相机图像的特点，模仿有人参与识别过程，提出了层次解耦的月球样品智能识别流程，利用深度学习方法构建了一类深度卷积识别网络，完整地描述了图像、特征、标记在网络中的正反传递关系，并在月球表层采样地面试验中进行了验证，结果表明该方法对不同光照、不同背景、不同过程、不同形态的样品，具有较好的泛化识别能力，误识别率优于8.1%，平均单幅识别时间约0.7 s。     

飞机大攻角非定常气动力建模与辨识

采用一阶微分方程描述由非线性非定常效应引起的气动力增量 ,从而建立了一种新的飞机大攻角非定常气动力数学模型。研究了模型在缓变运动下的线化形式和动导数表达式。讨论了模型参数的辨识问题。算例证实了所建立的气动力数学模型的正确性和所述模型参数辨识方法的有效性     

基于拓扑优化的航空发动机滑油箱支架设计

支架是航空发动机滑油箱组件中的重要部件,用于连接和固定滑油箱组件中的箍带.但现有支架设计会引起与之相连的箍带承受偏心拉力,导致结构应力水平偏高进而发生疲劳破坏.本文提出了一种考虑结构局部刚度的拓扑优化方法,能够在提升支架整体刚度的同时兼顾局部刚度,使支架的刚度分布更加合理,进而显著降低与之相连的箍带的应力水平.利用该优...     

基于卷积盲分离的强干扰下通信信号分离算法

针对目前通信辐射源个体识别算法在实际试验中由于各类干扰信号和多径衰落导致识别率较低的问题,提出一种用于识别算法前端的信号分离算法,可有效地减少其他电磁信号对于识别算法输入信号的影响,从而提高在复杂电磁环境中通信辐射源个体识别的正确识别率。该算法将灾变策略和搜索状态的自适应引入量子粒子群算法,通过对混合信号的联合对角化从截获的观测信号中提取出目标通信辐射源的有用信号。为了更加系统、直观地衡量算法的分离效果,提出分离熵来量化算法的整体性能。仿真结果表明,该分离算法可以把目标通信辐射源的有用信号从复杂电磁环境中提取出来,从而提高通信辐射源个体识别在复杂电磁环境中的正确识别率,具有较好的可行性和有效性。     

基于非线性有限元的网套补偿器轴向刚度特性及计算方法研究

网套补偿器在航天管路系统中广泛使用,补偿器的轴向刚度是其基本力学参数,然而其复杂的微结构特征使得轴向刚度呈现强烈的非线性。为实现对网套补偿器轴向拉伸全过程的仿真计算,从钢丝网套入手,基于钢丝的螺旋梁模型,分析了轴向长度、螺旋角及网套直径对轴向刚度的影响,结果表明轴向长度和螺旋角将显著影响轴向刚度;分析了边界条件的影响,结果表明在计算轴向刚度时固定边界与约束径向位移的循环边界可以互换。结合网套刚度分析的结论,提出了基于接触关系的子网套刚度分析方法,解释了拉伸时轴向刚度非线性变化原因,进一步建立了2/N波纹管-螺旋梁复合模型以及2/N单波-单锭螺旋梁复合模型用于不同刚度阶段的有限元计算。算例结果表明,仿真获得的力-位移曲线与试验曲线一致性较好,高刚度阶段的轴向刚度误差为3.40%。     

用于识别双星故障的RAIM算法

由于传统的基于识别门限的卫星故障识别算法存在漏检和误警致使识别率较低,为此提出一种可用于识别双星故障的接收机自主完好性监测算法.该算法通过构造新的奇偶矢量与故障特征平面,利用奇偶矢量与故障特征平面之间的几何关系来识别卫星故障,使得算法不再受限于识别门限的影响,从而有效地避免了由于识别门限引起的识别效率较低的问题.计算机仿真结果表明:改进后的算法与传统的基于识别门限的算法相比,双星故障正确识别的性能有显著的提高,正确识别率可达到90%.同时,与基于门限识别的重构最优奇偶矢量法相比,计算量可减少约61.2%以上.     

风致内压对大跨屋盖风振响应的影响

本文利用气体质量守恒原理与气体状态方程推出了考虑风致内压的大跨屋盖风振响应的三阶动力微分方程,并给出了其稳态频响函数的表达式,通过数值算例分析了风致内压对大跨屋盖风振响应的影响.研究表明:考虑风致内压在本质上是给屋盖附加了随特征频率变化的气承刚度与气动阻尼,对于正常封闭建筑采用不考虑风致内压的频域分析法是偏于保守的;对于给定设计风速,任何建筑必存在一个最优孔隙率,会使大跨屋盖的风振响应达到最小,因而合理设置墙面孔隙是大跨屋盖最为有效的气动减振措施.     

燃气轮机周向拉杆转子连接刚度对转子振动特性影响的研究

为研究燃气轮机周向分布式拉杆转子轮盘间存在的连接刚度对轴系转子振动特性产生的影响,本文提出一种基于六自由度的弹簧单元等效方法;首先将轮盘接触刚度与拉杆弯曲刚度同时等效进连接界面,便于使用一维梁单元求解其临界转速与振动响应变化,验证其与全三维有限元法吻合度在3％以内;然后改写了非线性动力学方程,采用谐波平衡法对其进行求解,使用经典Newmark方法验证其准确性;最后使用该等效方法计算了某模拟转子连接刚度对其临界转速、响应特性、非线性特性等的影响。计算结果表明：当连接面剪切刚度与弯曲刚度减小3个数量级,均造成了临界转速的降低和振动响应的提高,而其影响程度可由各阶振型大致推测,且响应幅值受剪切刚度影响较大;使用临界转速趋于收敛时的连接刚度与试验值的对比误差小于2％,较连续模型提升显著;在连接刚度各向异性时,每一阶临界转速均出现两个响应峰值,轴心轨迹变成椭圆;考虑刚度随位移变化（非线性刚度）后,转子的响应峰值发生“歪扭”特性,且该峰值特征随不平衡量、无量纲阻尼等因素变化而呈现“波浪形”变化。