Automatic Identification of Axis Orbit Based on Both Wavelet Moment Invariants and Neural Network

Axis orbit is an important characteristic to be used in the condition monitoring and diagnosis system of rotating machine. The wavelet moment has the invariant to the translation, scaling and rotation. A method, which uses a neural network based on Radial Basis Function (RBF) and wavelet moment invariants to identify the orbit of shaft centerline of rotating machine is discussed in this paper. The principle and its application procedure of the method are introduced in detail. It gives simulation results of automatic identification for three typical axis orbits. It is proved that the method is effective and practicable.

On Fault Diagnosis of Rotating Machinery Using Wavelet Time-division Scale Level Moment

Based on an in-depth study of wavelet gray moment, we proposed a concept of a time-division scale level moment and gave the specific definition; ulteriorly, we discussed the factors which affected the fault diagnosis ability of a time-division scale level moment. The analysis results in the caculation of six typical fault signals show that the time-division scale level moment can be used to display the detailed information of a wavelet gray level image, extract the signal＇s characteristics effectively, and distinguish the vibration fault. Compared to the method of a wave gray moment vector, the method mentioned in this paper can provide higher calculation speed and higher capacity of fault identification, so it is more suitable for online fault diagnosis for rotating machinery.

Wavelet Moment Invariants Extraction of Underwater Laser Vision Image

Wavelet moment invariants are constructed for object recognition based on the global feature and local feature of target, which are brought for the simple background of the underwater objects, complex structure, similar form etc. These invariant features realize the multi-dimension feature extraction of local topology and in- variant transform. Considering translation and scale invariant characteristics were ignored by conventional wavelet moments, some improvements were done in this paper. The cubic B-spline wavelets which are optimally localized in space-frequency and close to the forms of Li's(or Zernike's) polynomial moments were applied for calculating the wavelet moments. To testify superiority of the wavelet moments mentioned in this paper, generalized regres- sion neural network(GRNN) was used to calculate the recognition rates based on wavelet invariant moments and conventional invariant moments respectively. Wavelet moments obtained 100% recognition rate for every object and the conventional moments obtained less classification rate. The result shows that wavelet moment has the ability to identify many types of objects and is suitable for laser image recognition.

Implementation of Texture Based Image Retrieval Using M-band Wavelet Transform

Wavelet transform has attracted attention because it is a very useful tool for signal analyzing. As a fundamental characteristic of an image, texture traits play an important role in the human vision system for recognition and interpretation of images. The paper presents an approach to implement texture-based image retrieval using M-band wavelet transform. Firstly the traditional 2-band wavelet is extended to M-band wavelet transform. Then the wavelet moments are computed by M-band wavelet coefficients in the wavelet domain. The set of wavelet moments forms the feature vector related to the texture distribution of each wavelet images. The distances between the feature vectors describe the similarities of different images. The experimental result shows that the M-band wavelet moment features of the images are effective for image indexing. The retrieval method has lower computational complexity, yet it is capable of giving better retrieval performance for a given medical image database.

The Lifting Scheme Based on the Second Generation Wavelets

The lifting scheme is a custom design construclion of Biorthogonal wavelets, a fast and efficient method to realize wavelet transform,which provides a wider range of application and efficiently reduces the computing time with its particular frame. This paper aims at introducing the second generation wavelets, begins with traditional Mallat algorithms, illustrates the lifting scheme and brings out the detail steps in the construction of Biorthogonal wavelets. Because of isolating the degrees of freedom remaining the biorthogonality relations, we can fully control over the lifting operators to design the wavelet for a particular application, such as increasing the number of the vanishing moments.

On the Use of Wavelet MoM to Solve the EFIE

The recently developed theory of wavelet applied in the Method of Moments (MoM) to solve the electromagnetic field integral equation is presented in this paper. For one dimension problem, we briefly discuss the following aspects: Firstly, two different methods, which are same in essence: the method of the unknown induction current expansion and the method of the integral operator expansion are used to solve the EFIE, Secondly, how to choose the wavelet basis function in wavelet MoM. For two dimension problem, the wavelet MoM is employed and compared with the conventional MoM in CPU time, computational precision and matrix spareness etc. Here, the fast wavelet transform (FWT) is used to compute the matrix elements rapidly and efficiently. Typical numerical results are presented to illustrate the concepts.

Construction of nonseparable orthonormal compactly supported wavelet bases for L^2(R^d)

Suppose M and N are two r×r and s×s dilation matrices,respectively.LetΓM andΓN represent the complete sets of representatives of distinct cosets of the quotient groups M-T Zr/Zr and N-T Zs/Zs,respectively.Two methods for constructing nonseparable Ω-filter banks from M-filter banks and N-filter banks are presented,where Ω is a（r＋s） ×（r＋s） dilation matrix such that one of its complete sets of representatives of distinct cosets of the quotient groups Ω-T Zr＋s/Zr＋s areΓΩ={[γT h,ζ T q] T：γh∈ΓM,ζq∈ΓN}.Specially,Ω can be [MΘ0N],whereΘis a r×s integer matrix with M-1Θbeing also an integer matrix.Moreover,if the constructed filter bank satisfies Lawton＇s condition,which can be easy to verify,then it generates an orthonormal nonseparable Ω-wavelet basis for L2（Rr＋s）.Properties,including Lawton＇s condition,vanishing moments and regularity of the new Ω-filter banks or new Ω-wavelet basis are discussed then.Finally,a class of nonseparable Ω-wavelet basis for L2（Rr＋1） are constructed and three other examples are given to illustrate the results.In particular,when M=N=2,all results obtained in this paper appeared in[1].

A New Content Based Image Retrieval Model Based on Wavelet Transform

Searching interested images based on visual properties of images is a challenging problem and it has received considerable attention from researchers in the fields like image processing, computer vision and multimedia systems in the last 20 years. While the importance and the effect of the image features like color, texture and shape have been taken into account in many papers, there have not been many studies on the importance of the color spaces on the performance of Content Based Image Retrieval (CBIR) systems. In this paper we first experimentally study the effect of choosing color space on the performance of content based image retrieval using Wavelet decomposition of each color channel. To this end, the retrieval results of different color spaces like RGB, YUV, HSV, YCbCr and Lab are analyzed. Then as a result a new Content Based Retrieval model using Wavelet Transform in Lab color space and Color Moments is proposed. In order to increase the efficiency of the proposed model some division schemes are taken into account which improves the performance of the proposed model. The proposed model tackles one of the important restrictions in content based image retrieval, namely, the challenge between the accuracy of retrieval and its time complexity. The experimental results on two databases [19] [24] demonstrate the superiority of the proposed model compared to existing models.

Methodology of Wavelets in Relativistic Heavy Ion Collisions in One Dimensional Phase Space (<i>η</i>-Space)

An attempt has been made to apply the wavelet methodology for the study of the results of the chaotic behavior of multiparticle production in relativistic heavy ion collisions. We reviewed the data that describes the collisions of relativistic heavy ion for the case η-space in 1-D phase space of variable. We compared the experimental data and UrQMD data using wavelet coherency. We discussed the results of the comparison.

复数小波包能量矩熵的深度GRU轴承故障预测

为了准确及时的表征轴承的性能退化,实现有效的早期故障预测,提出了一种基于复数小波包能量矩熵的深度门控回归单元轴承早期故障预测方法。首先,将复数小波包能量矩熵定义为一种新的监测指标,用来表征其承载性能的退化。其次,构造了深门控回归单元网络,捕获了所定义的监测指标中隐藏的线性映射关系。最后,提出了一种基于学习速率衰减策略的改进训练算法,以提高所构建的深度模型的预测能力。通过两个实验结果分析可知提出方法具有更高的灵敏度和准确度。

DSQ水管倾斜仪信号随机噪声压制研究

基于自适应噪声完备集合经验模态分解CEEMDAN和小波去噪,提出一种DSQ水管倾斜仪信号随机噪声压制方法。首先将信号进行CEEMDAN分解,得到若干个本征模态函数IMF,分解数量随不同信号噪声动态变化;然后计算每条IMF和原信号的相关性系数,对处于系数阈值范围内的IMF作小波变换处理;最后执行线性重构,得到去噪后的信号。仿真和实际去噪实验结果表明,随机噪声压制效果明显,信号有效成分保留比率较高,优于其他同类方法。

土体障碍物超声探测信号小波包特征分析方法

利用小波包分解方法,对土体中障碍物的超声探测信号进行分析。选用sym8小波基函数进行6层小波包分解,并截取信号能量集中的前16个频带进行细致分析,从小波包频带能量、小波包频带能量熵、小波包频带能量矩三个角度对信号进行对比。结果显示,存在障碍物位置处信号和不存在障碍物位置处信号的小波包频带能量熵大致相等,不能作为信号识别及障碍物判断的方法,而小波包频带能量和小波包频带能量矩在部分频带上差异明显,可以作为信号识别及判断的方法。

1957—2022年辽河流域降雨时空演变规律分析

为响应水利部对海河流域“23·7”流域性特大洪水暴露短板所提意见,加快构建雨水情监测预报“三道防线”工作,精准监测并分析流域暴雨时空分布,本研究基于辽河流域30座国家雨量站点1957—2022年共66年逐日降雨实测数据,采用Mann-kendall检验、小波分析、空间矩评价等方法,以年降雨量为周期对辽河流域降雨的时空演变特征进行定量分析。结果表明,辽河流域年降雨量波动显著,年际、年代变幅分别为-50.5%~73.4%、-19.4%~32.7%;研究期间降雨量整体呈现出缓慢下降的趋势,趋势率为-2.2mm/10a;时间分布上仅有3段时间具有显著周期性,分别为1960—1982年、1988—1995年及2005—2014年。空间分布上差异显著,流域上游降雨普遍集中,下游降雨较为分散,研究期间降雨中心逐渐向下游转移且降雨越发集中。研究成果可为辽河流域加强雨水情监测预报“第二道防线”建设提供数据支撑。

电力线除冰机器人基于粒子群优化的小波神经网络障碍物识别方法

由于除冰机器人工作在覆冰的电力线上,障碍物的识别存在着各类障碍物区分较难,准确率较低等不足。为提高机器人自主识别能力,设计一种自适应阀值的小波变换边缘提取算法来提取出障碍物的图像边缘,并针对电力线障碍物结构特点,在障碍物边缘提取过程中设计一种基于电力线位置约束的有效剔除部分干扰背景的方法;引入小波矩,通过提取边缘图像的小波矩作为障碍物的特征匹配数据;根据神经网络和粒子群算法的原理,设计一种粒子群优化的小波神经网络进行障碍物的识别分类,该方法用粒子群算法取代传统的梯度下降法,并改进惯性权重因子,优化小波网络的各个参数。试验结果表明所提出的方法对电力线上防震锤、悬垂线夹和耐张线夹等障碍物能够有效地识别,并具有比普通识别方法更高的识别精度。

基于能量-小波矩特征分析的油纸绝缘气隙放电过程划分

基于油纸绝缘气隙放电模型,采用恒压法在实验室对其进行局部放电发展特性实验。论文研究了放电发展过程中放电能量的变化规律,并引入放电重复率n提出了每秒平均放电能量Wasec这一新特征量,很好地描述了气隙放电的发展过程。借鉴PRPD谱图构建思想,引入放电发生的工频相位φ,构造基于放电能量的φ-w-n三维统计图谱,进而得到基于放电能量-相位(w-φ)的局部放电二维灰度图像。鉴于传统矩特征参量的不足,将小波理论引入局部放电灰度图像矩特征的提取过程中,提取了放电产生、发展到最终击穿共62组样本点,得到不同尺度因子和位移因子参数下的小波矩特征值。根据提取到的不同放电时刻的小波矩特征值,在无先验知识的条件下采用模糊C-均值聚类的方法将整个放电过程划分为放电产生和震荡发展阶段、微弱放电阶段、放电爆发阶段以及放电预击穿阶段。

基于检索的人体运动识别和模拟

运动识别和模拟是人体运动分析中重要的研究内容·实现了以检索为基础的实验性的运动分析系统·小波矩具有平移、旋转和缩放不变性,能够提取局部多层次特征,被用来作为特征描述运动序列以及动作·根据相似性实现运动识别,利用动态时间变形(DTW)实现序列的动作匹配,在poser建模、依据正多面体分割的金字塔模型得到多视点投影视频的数据库中进行识别和匹配,并以三维模型的形式显示出来·实验结果可以模拟人体运动以及为进一步分析提供初始分析数据·

基于几何形状和小波矩的静脉特征提取与匹配

针对手背静脉识别系统的特征提取与匹配算法研究问题,提出了一种粗匹配与细匹配结合的方法.该方法通过分析图像特征描述符特性,考虑静脉图像的全局信息,确定提取具有平移、旋转、比例和仿射不变性的边界和区域的形状特征进行粗匹配;为了考虑局部特征使形状描述符具有良好的易分辨能力,依据小波矩具有小波多尺度分析和不变矩的优点,确定了基于小波矩的匹配为细匹配的方案,实验结果表明识别率得到了明显提高.

基于小波矩的高压输电线路除冰机器人障碍智能视觉识别方法

针对220kV单分裂线路的结构特点,提出了一种基于小波矩的障碍物智能视觉识别方法.该方法采用Ostu算法二值化图像,采用小波模极大值算法提取图像边缘.通过提取障碍物边缘图像的小波矩,来得到一组局部最优的小波矩特征值,并在此基础上用小波神经网络进行障碍物的识别与分类.实验结果表明:所提出的方法能有效地识别高压输电线上的防震锤、悬垂线夹、耐张线夹等障碍物,并具有比普通3层BP神经网络方法更高的精度和更快的收敛速度.

不变矩在模式识别中的应用研究

矩作为模式的特征在二维图象模式识别中应用很广。该文根据Hu矩、Zernike矩、Pseudo-zernike矩、Legendra矩、旋转矩和复数矩的原始表达式,归纳出适用于计算机处理的矩的一般表达式。接着,引出三次B样条小波矩,依照矩的一般表达式与Zernike矩比较它们作为模式特征的辨别力和可靠性,得出与前人不一样的结论。最后,以实验验证之。

基于小波矩的抗几何攻击数字图像水印算法研究

针对旋转、缩放和平移等几何攻击破坏水印检测同步,从而导致水印检测失败等问题,利用归一化图像的缩放、平移不变性及小波矩的旋转不变特性,结合奇偶量化技术,提出了一种有效抵抗几何攻击的数字图像水印新算法。首先利用图像归一化技术将原始载体映射到几何不变空间内;然后计算归一化图像的小波矩,并选取部分稳定的低阶小波矩用于水印嵌入;最后利用奇偶量化方法将水印信息嵌入到所选小波矩的不变量内。仿真实验结果表明,该图像水印方案不仅具有良好的透明性,而且具有较强的抵抗常规信号处理、几何攻击、联合攻击等能力。