基于小波变换和Involution卷积神经网络的滚动轴承故障诊断方法

传统卷积神经网络在滚动轴承故障诊断中存在梯度扩散、参数爆炸和训练时间长等缺点,为此提出一种基于Involution卷积神经网络的滚动轴承故障诊断方法。首先,通过小波变换将原始数据转换为时频图,经过数据预处理后送入基于Involution的神经网络模型;然后,经过不同Convolution卷积核对原始图像的局部区域特征进行不同方式的提取,扩展输入图像通道数;最后,通过Involution对特征图的每个像素点进行进一步特征提取,经过softmax层输出分类结果。CWRU轴承数据集和试验轴承数据集的分析结果表明,基于Involution卷积的神经网络模型所包含的参数较少,训练时间短,故障分类准确率可达99.75%,优于传统的CNN,DBN,自编码器等模型。     

基于多通道加权卷积神经网络的齿轮箱振动信号特征提取

为了解决单通道振动信号输入不能全面表达故障特征信息及齿轮箱故障早期诊断问题,提出了一种新的深度神经网络(Deep neural network,DNN)模型—多通道加权卷积神经网络(Multi-channels weighted convolutional neural network,MCW-CNN),并应用于齿轮箱振动信号特征学习和故障诊断.首先,采用经验模态分解(Empirical mode decomposition,EMD)对振动信号进行处理,得到多通道一维信号突出振动信号的故障特征,并将其转化为多通道图像输入,从而充分发挥CNN在图像特征提取上的优良性能,将齿轮箱故障诊断问题进一步转化为CNN更为擅长的多通道图像识别问题;其次,针对各通道图像频率和带宽的不同,在卷积层采用动态感受野进行图像特征提取,全面提取多通道图像特征细节;针对各通道图像携带冲击特征的强弱不同,提出了基于峭度加权的多通道融合方法,增强了冲击特征强的通道故障特征.最后,通过故障诊断仿真试验和齿轮箱故障诊断试验验证所提方法的有效性.试验结果表明,MCW-CNN可有效提取振动信号的故障特征,识别正确率明显高于典型的深度学习方法和传统的分类器.     

基于改进CNN的起重机械滚动轴承故障诊断

针对起重机械中的滚动轴承在高转速、重载荷和强噪声背景下,早期故障特征难以提取及有效识别的问题,提出一种改进卷积神经网络(CNN)的故障诊断方法。该方法首先应用短时傅里叶变换(STFT)将传感器采集到的一维振动信号转换为二维时频图,并将其作为改进卷积神经网络的输入,然后利用卷积神经网络强大的特征提取能力自适应地提取故障特征。最后,通过CNN模型最后一层的Softmax层对提取到的特征进行分类从而实现故障诊断的目的。     

多模深度卷积神经网络应用于视频表情识别

由于视频中的手工特征和主观情感之间的直接相关性很小,识别视频序列中的面部表情是一项很有挑战性的任务,为了克服这个缺陷,有效提高视频中的人脸表情识别性能。本方法采用两个深度卷积神经网络,即空间卷积神经网络和时间卷积神经网络,用于视频中的时空表情特征学习。其中,空间卷积神经网络用于提取视频中每一帧静态的表情图像的空间信息特征,而时间卷积神经网络用于从视频中多帧表情图像的光流信息中提取动态信息特征。然后,将这两个深度卷积神经网络学习到的时空特征进行基于深度信念网络(DBN)的特征层融合,输入到支持向量机实现视频中的人脸表情分类任务。在公共的RML和BAUM-1s视频情感数据集的测试结果表明,该方法分别取得了71.06%和52.18%的正确识别率,明显优于现有文献报导的结果。多模深度卷积神经网络的人脸表情识别方法能提高视频中人脸表情的识别性能。     

基于卷积神经网络的水果图像分类识别研究

为了解决传统水果图像分类识别算法人工提取特征的缺陷,将卷积神经网络应用到水果图像识别上,基所创建的数据集,参照经典的卷积神经网络模型Le Net-5结构,提出更适合本数据集的卷积神经网络结构,首先对水果数据集进行分类标签,将苹果、梨、橙子、橘子、桃子分别标记为0、1、2、3、4,然后将图片分批次投入模型训练,该模型构建了一个输入层、两个卷积层、两个池化层、两个全连接层和一个输出层。卷积神经网络通过底层提取特征,再进一步更深层次提取特征,最后得到目标的分类。实验结果表明,所提出的卷积神经网络结构不仅在数据集上取得了较高的识别准确率,而且与传统的水果图像分类识别算法相比较,卷积神经网络避免了人工提取特征的繁琐过程。     

基于边缘特征和CNN联合的多视航拍图像配准方法

针对传统卷积神经网络对多视航拍图像进行配准训练时,未能充分利用多视图像间边缘特征之间的联系,为了提取多层图像边缘结构之间的特征信息,提出了一种基于边缘特征和卷积神经网络联合的多视航拍图像配准方法,通过窗口灰度加权算法提取图像的边缘特征图,并将边缘特征图作为卷积神经网络的输入端进行训练,在测试阶段,给出一对新的多视航拍图像,训练后的模型可以预测图像间的空间对应关系。实验结果表明,该算法实现了图像对齐变换,提高了图像配准的精度,优于现有的图像配准方法。     

CNN融合PCA-DT模型的金属缺陷识别研究

针对金属缺陷识别分类,传统机器学习需要人工提取特征,而深度学习需要大量样本的问题,本文针对中小规模缺陷数据集提出了一种基于浅层的卷积神经网络（CNN）和决策树（DT）的金属缺陷分类方法。利用卷积神经网络提取特征,通过决策树分类,实现缺陷分类。引入主成分分析（PCA）方法对特征向量降维,减小过拟合并提升算法识别分类效率。为验证本文方法的通用性,除图像缺陷数据外还引入非图像缺陷数据。实验结果表明,本文方法除了能分类图像缺陷也能分类非图像缺陷,且在识别率等3个评价指标上本文方法优于传统机器学习方法,与深度学习方法持平,但在分类消耗时间上少于深度学习。     

基于CNN和LSTM的自然场景文本检测应用

针对自然场景的文本检测,构建了一种基于卷积神经网络(CNN)和长短时记忆网络(LSTM)的自然场景文本识别框架,运用CNN网络对图像中的静态特征进行提取,LSTM提取上下文特征信息。在解码上,提出了一种混合的CTC-Attention机制对输出层的编码进行解码。     

基于原始振动信号的往复压缩机卷积神经网络故障诊断

往复压缩机振动信号特性复杂,传统特征提取方法难以有效提取故障特征,从而影响故障诊断效果。提出了基于原始振动信号卷积神经网络(RVCNN)的方法,将采集的一维原始振动信号作为输入,充分利用卷积神经网络(CNN)自动提取信号特征的特性,对往复压缩机故障进行特征提取及诊断。使用从试验台获得的压缩机气阀故障数据样本进行测试,结果表明,与传统方法相比,RVCNN方法具有更高的故障识别率和更好的抗噪性能。     

GAPSO-KELM在滚动轴承故障诊断中的应用

为了减小故障特征提取对信号处理方法和人工经验的依赖性、降低诊断模型的计算复杂度、有效提高诊断精度,本文提出了一种卷积神经网络(CNN)与核极限学习机(KELM)相结合的滚动轴承故障诊断方法.首先,直接将不同故障模式下的滚动轴承原始振动信号进行分段处理,用以构建训练集、验证集和测试集.其次,利用CNN卷积运算提取特征,通...     

Minimal Realization of Linear Graph Models for Multi-physics Systems

An engineering system may consist of several different types of components,belonging to such physical"domains"as mechanical,electrical,fluid,and thermal.It is t...     

Non-monotonic material contrast in scanning ion and scanning electron images

30 keV Ga⁺ focused ion beam induced secondary electron (iSE) imaging was used to determine the relative contrast between several materials. The iSE signal compared from C, Si, Al, Ti, Cr, Ni, Cu, Mo, Ag, and W metal layers does not decrease with an increase in target atomic number Z₂, and shows a non-monotonic relationship between contrast and Z₂. The non-monotonic relationship is attributed to periodic fluctuations of the stopping power and sputter yield inherent to the ion–solid interactions. In addition, material contrast from electron-induced secondary electron (eSE) and backscattered electron (BSE) images using scanning electron microscopy (SEM) also shows non-monotonic contrast as a function of Z₂, following the periodic behavior of the stopping power for electron–solid interactions. A comparison of the iSE and eSE results shows similar relative contrast between the metal layers, and not complementary contrast as conventionally understood. These similarities in the contrast behavior can be attributed to similarities in the periodic and non-monotonic function defined by incident particle–solid interaction theory.     

Application of Feature Extraction through Convolution Neural Networks and SVM Classifier for Robust Grading of Apples

This paper proposes a novel grading method of apples,in an automated grading device that uses convolutional neural networks to extract the size,color,texture,an...     

分布动态载荷识别的抗噪处理

针对正交多项式频域法在用多种响应对矩形薄板进行载荷识别中抗噪性较差的问题,综合运用平均法、矩阵预处理和奇异值截断法等方法对之进行改善,并引入空间映射的思想,将该方法的应用范围拓展为复杂的模型.利用仿真算例,证实了该方法具有较好的抗噪性.     

基于MELTAC-N平台的核电厂安全级DCS环网研究与测试

针对工程实践中环网通讯相关问题的处理缺乏理论基础及国产化安全级DCS平台的开发缺乏成熟经验借鉴问题,对基于MELTAC-N平台核电厂安全级DCS环网的软硬件实现进行了研究。提出了安全级DCS环网双环网冗余设计、光切换开关设计等硬件设计方法,以及以RPR协议为基础,采用全数据收发策略的软件设计方法。在CPR1000安全级DCS平台上对安全级DCS环网的可靠性及实时性进行了评价,并进行了容错能力、响应时间及响应时间稳定性测试验证实验。结果表明,基于MELTAC-N平台安全级DCS环网软硬件设计具有较好的容错能力及响应时间稳定性。     

The laboratory simulation of abrasive wear

Abrasive wear has long been recognised as one of the most potentially serious tribological problems facing the operators of many types of plant and machinery; several industrial surveys have indicated that wear by abrasion can be responsible for more than 50% of unscheduled machine and plant stoppages. Locating the operating point of a tribological contact in an appropriate operational ‚map’︁ can provide a useful guide to the likely nature and origins of the surface degradation experienced in use, though care must be exercised in choosing the most suitable parameters for the axes of the plot. Laboratory testing of materials and simulations of machine contacts are carried out for a number of purposes; at one level for the very practical aims of ranking candidate materials or surface hardening treatments in order of their wear resistance, or in an attempt to predict wear lives under field conditions. More fundamentally, tests may be aimed at elucidating the essential physical mechanisms of surface damage and loss, with the longer term aim of building an analytical and predictive model of the wear process itself. In many cases, component surface damage is brought about by the ingress of hard, particulate matter into machine bearing or sealing clearances. These may be running dry although, more usually, a lubricant or service fluid is present at the interface. A number of standardised wear test geometries and procedures have been established for both two- and three-body wear situations, and these are briefly described. Although abrasive wear is often modelled as following an ‚Archard’︁ equation (i.e. a linear increase in material loss with both load and time, and an inverse dependence on specimen hardness) both industrial experience and laboratory tests of particularly lubricated contacts show that this is not always the case: increasing the hardness differential in an abrasively contaminated lubricated pair may not always reduce the rate of damage to the harder surface.     

Limits of topographic measurement by the scanning tunnelling and atomic force microscopes

Parameters describing the topographic character of a surface (height, surface wavelength, slope and curvature) can be derived from equivalent sinusoidal profiles. The response of a surface-measuring instrument may be modelled in terms of instrument parameters such as stylus radius, and scanning range and resolution. The performance of the instrument may then be mapped as a zone in amplitude-wavelength (AW) space to show the sinusoidal profiles it is capable of measuring. In a first-order analysis the STM and AFM are considered as equivalent to contact-stylus instruments with a notional stylus radius equal to the tip radius plus the gap. Comparisons between different instruments and types of instrument are readily made by mapping in AW space. The error arising from convolution of the sinusoidal profile with that of the finite tip may be quantified and plotted as contours in AW space.     

Fractional order nonsingular terminal sliding mode control for flexible spacecraft attitude tracking

This paper investigates a fractional terminal sliding mode control for flexible spacecraft attitude tracking in the presence of inertia uncertainties and extern...     

奥氏体不锈钢表面双辉等离子渗锆的动力学

利用双辉等离子渗金属技术在0Cr18Ni9Ti奥氏体不锈钢表面制备了一层均匀、致密、呈良好冶金结合的渗锆合金层,并对1 060℃下的渗锆动力学进行了研究。结果表明:随着距锆合金层表面距离的增加,锆元素的含量呈梯度递减,扩散系数逐渐减小,而扩散激活能逐步增大;在1 060℃采用双辉等离子技术渗锆时,渗锆合金层表层的空位密度为2.945×(1012~1013)cm-2,与相同温度下采用常规渗金属工艺相比,提高了1~2个数量级。     

气化炉三维扫描测量与数据处理

以德士古气化炉耐火砖的内壁蚀损检测设备为基础,对采集到的点云数据做了进一步处理.通过对数据的筛选和剔除,实现了数据点的平滑降噪细化和精简.然后利用点云对整、网格划分和分色显示等方法,最终完成了内壁腐蚀情况的三维建模.重点讨论了点云数据的预处理及后处理的方法,并根据内壁耐火砖的腐蚀阈值,提出了一种气化炉内壁腐蚀区域的识别与分割方法.对耐火砖的腐蚀分析、气化炉的生产与维修提供了可靠依据,并在工程应用中获得了一致认可.