基于改进MP的稀疏表示快速算法及其滚动轴承故障特征提取应用

在恒定转速情况下,旋转机械中滚动轴承的局部故障往往导致周期性冲击,从而产生周期性瞬态振动信号。对局部故障的瞬态特征提取一直是故障检测的关键问题。基于匹配追踪(Matching Pursuit,MP)算法的稀疏分解是一种信号自适应分解算法,是强噪声背景下微弱特征提取的有效方法之一。针对滚动轴承故障振动信号稀疏表示过完备字典的选择与构造问题,基于相关滤波法优选与冲击波形匹配的Laplace小波原子构造稀疏表示中的过完备字典;针对基本匹配追踪算法计算量大、效率低的问题,结合FFT快速运算特性,通过互相关运算替换基本匹配追踪算法中的内积运算,研究基于改进MP的稀疏表示快速算法,进而提高计算效率。仿真与滚动轴承故障实验分析结果表明该算法能准确的提取滚动轴承故障特征且计算效率高。     

钢包耳轴根部焊缝的相控阵超声检测与信号处理

采用匹配追踪算法和小波变换对低信噪比(2dB和-5dB)钢包耳轴根部焊缝缺陷检测信号进行预处理对比分析,在定制试块上采用64阵元超声相控阵探头对深度为230mm的耳轴根部焊缝进行检测,并且结合基于Gabor原子库的匹配追踪算法对回波信号进行消噪后成像.结果表明,在低信噪比(-5dB)条件下,匹配追踪算法较小波变换有更好的预处理效果;对深度位于220mm和230mm处的钢包耳轴焊缝缺陷的实际检测信号进行去噪处理时,匹配追踪算法能够准确定位缺陷位置并显著提高缺陷处信噪比.     

薄板腐蚀缺陷兰姆波成像检测的有限元模拟

基于A0模式兰姆波对薄板腐蚀缺陷进行成像检测,在频率一定时,由于腐蚀造成板厚的改变将进一步影响检测兰姆波速度的变化,通过检测兰姆波波速的变化可以对板材腐蚀类缺陷进行监测.根据A0模式兰姆波的频率特征,测量发射探头与接收探头之间的兰姆波走时,结合波的实际传播路径,计算出实际检测兰姆波的速度,采用联合迭代重建技术(SIRT)对走时数据进行群速度图像重建.基于有限元数值方法,采用A0模式兰姆波对薄铝板中的腐蚀类缺陷进行模拟检测,给出了成像检测结果.     

时频流形自适应稀疏重构的遥测振动信号特征增强方法EI北大核心CSCD

针对遥测振动信号非线性、非平稳性、瞬态冲击性等特点,提出一种基于时频流形自适应稀疏重构的遥测振动信号特征增强方法,对振动信号进行相空间重构提取其时频流形;以时频流形为基础,采用KSVD算法自适应构建过完备字典,并从中找到最匹配的时频原子,根据得到的原子与相空间展开信号的时频分布,依次匹配计算获得其重构的稀疏系数;利用稀疏系数和时频原子对相空间中各维信号的时频分布进行重构,通过时频分布的逆运算和相空间还原得到特征增强信号。仿真和实测信号处理结果验证了算法的有效性。     

基于字典学习的轴承早期故障稀疏特征提取

针对低速重载机械滚动轴承早期故障的振动信号中故障特征冲击成分微弱易被噪声覆盖难以识别,而利用稀疏表示方法提取冲击成分时因轴承工况非平稳性,准确匹配冲击成分字典难以构造问题,提出基于字典学习的轴承早期故障稀疏特征提取方法。利用改进型K-SVD字典学习算法构造自适应字典;采用正交匹配追踪算法(Orthogonal Matching Pursuit,OMP)对振动信号进行稀疏分解,计算每次迭代逼近信号的峭度值,找出最大峭度值对应的逼近信号;重构特征成分并进行包络谱分析,获得故障类型。仿真及轴承振动数据测试结果表明,所提方法能更好匹配早期故障特征成分、满足轴承实时故障监测需求。     

超声检测中的兰姆波层析成像

兰姆波作为超声导波，可以对薄板类结构实现大范围快速的检测。然而，从兰姆波数据中提取定量信息时对检测人员的技术素质提出了很高的要求。文章用兰姆波层析成像仿真实现了铝板中不同缺陷的重建图像。结果表明：采用滤波反投影算法得到的层析图像给出了关于缺陷位置和类型的信息，从而使技术人员可以方便地识别出材料中的缺陷。     

基于索引冗余字典的轴承故障组稀疏分类方法研究

基于声发射信号的高速列车轮对轴承早期故障状态诊断和分类复杂性高,常用的人工神经网络及支持向量机方法在参数设置与多分类问题上存在困难。组稀疏分类(GSRC)仅通过超完备字典下稀疏重构即可实现理想的多分类,在图像、语音分类中成为热点。为将GSRC用于轴承故障识别,设计了一种带索引的复合故障冗余字典,利用样本信号多尺度排列熵构成索引字典的小体积优势预先匹配来缩小故障类范围,以邻近梯度法和最优一阶加速的组LASSO约束优化算法来提高收敛性和计算速度;采用改进EEMD结合变分模态分解自适应的获得各故障类初始原子,以保留故障的非线性特征,同时提出一种原子区间平移稀疏编码方法(Interval Translation Sparse Coding, ITSC)放宽了样本数据截取要求,原子有更好的紧凑性与稀疏性;对七类轴承缺陷试验台跑合声发射信号进行分类,验证了该方法的性能。     

基于时空约束压缩感知的地震数据重建

在实际勘探中,由于环境、设备或人为因素的影响,采集的地震数据中有很多丢失的数据,严重影响了数据的解释工作。针对这一问题,根据地震数据的时空相关性,提出了一种基于时空约束压缩感知的地震数据重建方法。该方法使用内核奇异值分解(KSVD)字典学习算法训练超完备字典作为稀疏变换基,进而利用改进的稀疏自适应匹配追踪算法(SAMP)完成重建。通过初始稀疏性估计和变步长策略,减少了SAMP中收敛所需的迭代次数。利用真实的地震数据和微电阻率成像数据进行实验,将所提出的方法与压缩感知重建算法进行了比较,不仅提高了重建数据的准确性,而且缩短了执行时间。     

基于概率损伤算法的复合材料板空气耦合Lamb波扫描成像

采用非接触空耦传感器在准各向同性复合材料板中激励出单一的Lamb波模态,用于分层缺陷的扫描检测。扫描时,激励和接收传感器置于复合材料板同侧并相对倾斜布置,传感器沿2个正交方向同步线性扫描,得到不同位置的检测信号。对不同扫描路径下的检测信号进行连续小波变换,提取激励频率下的小波系数包络信号,对分层缺陷进行成像。在此基础上,利用概率损伤算法定义损伤指数,结合不同方向的损伤指数实现分层缺陷成像。采用全加法和全乘法对2个正交扫描方向得到的成像结果进行数据融合,实现了分层缺陷的定位和重构。并在成像算法中引入阈值,进一步提高了分层缺陷的定位精度以及重构质量。     

基于电容层析成像系统测量信号稀疏性的两相流流型辨识

提出了基于电容层析成像(ECT)测量电容信号稀疏性的两相流流型辨识算法,该算法首先使用所有流型对应的归一化测量电容值信号构建一个过完备字典,并将待辨识样本通过该过完备字典进行稀疏表示,使其具有稀疏性并满足稀疏重构的基本要求,然后以压缩感知的正交匹配追踪(OMP)算法求取各标准样本对应于完备样本集的稀疏解,最后根据待辨识样本与标准样本稀疏解之间的线性相关程度进行流型辨识。使用该方法对5种典型的两相流流型识别进行了仿真及实验研究,结果表明:该方法的流型正确识别率均高于98%。     

Multi-Helical Path Exploitation in Sparsity-Based Guided-Wave Imaging of Defects in Pipes

In this paper, a defect localization scheme for cylindrical pipes is presented which relies on guided-wave scattering by defects. The proposed scheme is predicated on the use of a sparse array of ultrasonic transducers and the sparse nature of defects on the pipe surface. Two circular rings of transducers, functioning as transmitters and receivers, are used to encompass the region to be inspected. Multiple helical paths exist for waves to travel from the transmitters to the receivers, after being scattered by the defects. Model based dictionary matrices are constructed for each path, relating the signals arriving at the receivers to the locations of potential defects. The resulting linear signal model is inverted by group sparse reconstruction to localize defects present in the pipe. Experimental validations of the proposed multi-helical path exploitation approach are provided for defects on an aluminum pipe.     

利用字典学习方法的声速剖面反演研究

针对经验正交函数(Empirical Orthogonal Function,EOF)建模反演得到的声速剖面(Sound Speed Profile,SSP)估计值分辨率比较低的问题,文章采用字典学习方法中的K-奇异值分解(K-Singular Value Decomposition,K-SVD)算法生成声速剖面的非正...     

增强稀疏编码的超分辨率重建

本文提出一种基于稀疏字典编码的超分辫率方法.该方法有效地建立高、低分辫率图像高频块间的稀疏关联,并将这种关联作为先验知识来指导基于稀疏字典的超分辫率重建.较超完备字典,稀疏字典对先验知识的表达更紧凑、更高效.字典训练过程中,本文选用高频信息作为高分辫率图像的特征,更有效地建立高、低分辫率图像决间的稀疏关联,所需的训练样...     

改进的K-奇异值分解图像去噪算法

针对传统的K-奇异值分解信号利用率不足,采用了稀疏贝叶斯学习预处理图像信号;将正交匹配追踪与改进之后的最速下降理论相结合;因噪声原子存在于字典更新之后得到的字典中,所以结合Bartlett检验法将噪声原子裁剪掉。实验结果表明,此方法相对于小波阈值去噪法、基于离散余弦变换字典稀疏表示等去噪方法能够更好地滤除噪声,保留图像边缘信息,获得更高的峰值信噪比,得到图像视觉效果更佳。     

Denoising Medical Images Using Deep Learning in IoT Environment

Medical Resonance Imaging (MRI) is a noninvasive, nonradioactive, and meticulous diagnostic modality capability in the field of medical imaging. However, the efficiency of MR image reconstruction is affected by its bulky image sets and slow process implementation. Therefore, to obtain a high-quality reconstructed image we presented a sparse aware noise removal technique that uses convolution neural network (SANR_CNN) for eliminating noise and improving the MR image reconstruction quality. The proposed noise removal or denoising technique adopts a fast CNN architecture that aids in training larger datasets with improved quality, and SARN algorithm is used for building a dictionary learning technique for denoising large image datasets. The proposed SANR_CNN model also preserves the details and edges in the image during reconstruction. An experiment was conducted to analyze the performance of SANR_CNN in a few existing models in regard with peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). The proposed SANR_CNN model achieved higher PSNR, SSIM, and MSE efficiency than the other noise removal techniques. The proposed architecture also provides transmission of these denoised medical images through secured IoT architecture.     

Droplet Image Super Resolution Based on Sparse Representation and Kernel Regression

Microgravity and containerless conditions, which are produced via electrostatic levitation combined with a drop tube, are important when studying the intrinsic properties of new metastable materials. Generally, temperature and image sensors can be used to measure the changes of sample temperature, morphology and volume. Then, the specific heat, surface tension, viscosity changes and sample density can be obtained. Considering that the falling speed of the material sample droplet is approximately 31.3 m/s when it reaches the bottom of a 50-meter-high drop tube, a high-speed camera with a collection rate of up to 10⁶ frames/s is required to image the falling droplet. However, at the high-speed mode, very few pixels, approximately 48-120, will be obtained in each exposure time, which results in low image quality. Super-resolution image reconstruction is an algorithm that provides finer details than the sampling grid of a given imaging device by increasing the number of pixels per unit area in the image. In this work, we demonstrate the application of single image-resolution reconstruction in the microgravity and electrostatic levitation for the first time. Here, using the image super-resolution method based on sparse representation, a low-resolution droplet image can be reconstructed. Employed Yang’s related dictionary model, high- and low-resolution image patches were combined with dictionary training, and high- and low-resolution-related dictionaries were obtained. The online double-sparse dictionary training algorithm was used in the study of related dictionaries and overcome the shortcomings of the traditional training algorithm with small image patch. During the stage of image reconstruction, the algorithm of kernel regression is added, which effectively overcomes the shortcomings of the Yang image’s edge blurs.     

Fast Scanning Probe Microscopy via Machine Learning: Non‐Rectangular Scans with Compressed Sensing and Gaussian Process Optimization

Fast scanning probe microscopy enabled via machine learning allows for a broad range of nanoscale, temporally resolved physics to be uncovered. However, such examples for functional imaging are few in number. Here, using piezoresponse force microscopy (PFM) as a model application, a factor of 5.8 reduction in data collection using a combination of sparse spiral scanning with compressive sensing and Gaussian process regression reconstruction is demonstrated. It is found that even extremely sparse spiral scans offer strong reconstructions with less than 6% error for Gaussian process regression reconstructions. Further, the error associated with each reconstructive technique per reconstruction iteration is analyzed, finding the error is similar past ≈15 iterations, while at initial iterations Gaussian process regression outperforms compressive sensing. This study highlights the capabilities of reconstruction techniques when applied to sparse data, particularly sparse spiral PFM scans, with broad applications in scanning probe and electron microscopies.     

光滑逼近超完备稀疏表示的图像超分辨率重构

为改善单帧降质图像的分辨率水平,提出了一种新的基于稀疏表示的学习法超分辨率图像重构方法。针对信号在既定的欠定超完备字典下的非稀疏性问题,采用光滑的递减函数逼近L0范数以避免对稀疏度先验的依赖,从而实现待重构图像块的有效稀疏表示,同时通过梯度下降的迭代优化获得稳定的收敛解。与双立方插值相比,图像的三倍超分辨实验显示,图像峰值信噪比(PSNR)提高2dB,框架相似性(SSIM)改善0.04,重构图像剔除了更多的模糊退化及边缘伪迹。该方法适于单帧降质图像的超分辨率增强。