Least Square Fitting for Adaptive Wavelet Generation and Automatic Prediction of Defect Size in the Bearing Using Levenberg–Marquardt Backpropagation

In this communication, an attempt has been made to develop an algorithm for automatic prediction of the size of the bearing defect during operation of a machine. Features for the purpose are meticulously designed so as defect commencement and termination events in the signal could be easily spotted. Information on commencement of defect in the signal, in general, is very weak. It is enhanced by approximating the burst in the signal to a wavelet, making use of least squares fitting. Levenberg–Marquardt back propagation network is used for prediction of defect size from defect features. The comparison shows that the Levenberg–Marquardt back propagation network outperforms another network in terms of accuracy. The experimental validation of the proposed scheme is carried out for four different defect sizes each for the inner race, outer race, and roller defect. The maximum deviation in the width measurement result is 5.35% which occurs in the case of bearing with roller defect of width 1.12 mm. The performance evaluation of the method is also carried out using t test. The result of t test validates the accuracy of proposed method in the prediction of defect width.     

基于小波时频框架分解方法的滚动轴承故障诊断

损伤点通过其它元件时引起的周期性冲击是判断滚动轴承局部损伤故障的关键特征信息.针对滚动轴承的振动特点,设计了小波时频框架,利用框架分解方法在匹配信号特征结构,直接提取特征信息方面的优势,分析了滚动轴承的振动信号.根据框架分解结果,在时频联合域内清晰直观地提取了滚动轴承局部损伤故障的周期性冲击特征,识别了滚动体、内圈和外圈的单点缺陷,与小波变换的对比验证了框架分解在检测滚动轴承局部损伤故障方面的有效性.     

小波包络解调在轧机故障早期诊断中的应用

针对轧钢机振动信号频谱成分的多样性和高低频混杂性，利用小波正交分解的多尺度多频带特性将振动信号展开到一系列相邻的小波空间上，使调制现象突显出来易于分析；再借助希尔波特包络分析技术对小波分解后的包含调制信号的分量进行解调，成功地提取出了故障早期特征。通过后期的振动数据跟踪分析，发现轧机轴承的外圈、滚动体相继出现损伤，并逐渐恶化，与停机开箱后结果基本吻合，进一步证实了小波包络解调技术的有效性。说明小波分析和包络解调技术能够有效地提取轧机轴承故障早期的特征，为设备的早期维修决策提供了重要的依据，同时可以避免恶性事故的发生。     

基于数学形态学的分形维数计算及在轴承故障诊断中的应用

滚动轴承故障信号是一种典型的非线性信号,分形几何为描述轴承故障信号的特性提供了一个有力的分析工具。基于数学形态学的分形维数是在Minkowski-Boulingand维数基础上拓展的一种采用形态学操作计算分形维数的新方法。本文较详细的阐述了基于数学形态学的分维数计算方法,对比分析了与传统计盒维数方法的区别与联系,并对实际的滚动轴承正常、滚动体故障、内圈故障和外圈故障信号进行了分析,结果表明,基于数学形态学的分维数计算方法具有计算速度快,估计准确稳定的特点,为准确判断滚动轴承故障状态提供了一种快速有效的新方法。     

应用改进的LMD和小波降噪于滚动轴承故障诊断

局域均值分解(Local Mean Decomposition, LMD)是近年出现的一种新的时频分析方法,在故障诊断领域的应用日益广泛。本文提出一种改进的局域均值分解和小波降噪结合的降噪方法,并与小波变换的信号降噪方法、基于集合经验模态分解（Ensemble empirical mode decomposition, EEMD）和小波的信号降噪方法进行对比,利用信噪比和均方根误差比较降噪效果。再通过滚动轴承内外圈故障信号的频谱分析实例,证明该方法很好地去除混杂在故障信号中的噪声,准确地判断出滚动轴承发生故障的类型及部位。     

基于近场声全息的滚动轴承故障诊断

滚动轴承在工业生产中起着关键作用,对其进行故障诊断研究具有重要意义。目前轴承诊断主要以振动信号分析为基础,而获取振动信号受接触式测量限制,声学故障诊断（ABD）具有非接触式测量的优点,但传统基于单通道的ABD存在测点选择难与局部诊断的不足。联合近场声全息（NAH）和灰度—梯度共生矩阵（GLGCM）并应用于滚动轴承故障诊断,利用NAH重建各轴承运行状态下的声场,得到声源附近重建面处的声像图,再从声像图中提取GLGCM特征,建立声场特性与轴承运行状态的内在联系,结合支持向量机模式分类,实现轴承故障诊断,实验研究证实方法的可行性与有效性。     

基于接触模型和峭度最优Laplac小波的滚动轴承量化诊断

研究了滚动轴承损伤量化诊断中的正反问题。通过轴承界面相互作用的动态接触理论及摩擦学系统行为的研究,运用振动传递路径表征物理模型。该模型计及负荷分布、游隙的影响,考虑接触滑移、分离作用,由表面轮廓变化描述局部损伤扩展,由测量信号修正模型参数,实现真实工况下轴承运行与模拟研究的有机结合。通过正问题求解构造峭度最优Laplace小波来提取无量纲指标,进而形成损伤矩阵数据库。将反问题计算转化为多维优化问题,利用灰色关联度寻优求解出与输入值几何最相似的样本点,进而测出轴承损伤的位置和具体尺寸。最后的实例分析表明,本文方法具有较好的精度和鲁棒性,且易于在工程实践中推广。     

基于BiLSTM的滚动轴承故障诊断研究

针对滚动轴承的故障诊断,设计并实现了一种基于双向长短期记忆网络(BiLSTM)的诊断模型.将原始振动信号直接作为模型输入,自动提取滚动轴承故障特征,可以对内圈、滚动体、外圈不同故障类型及不同损伤程度的滚动轴承进行故障识别.该模型通过BiLSTM神经网络自动提取轴承振动信号的深层信息,弥补了传统故障诊断方法需要人工提取特...     

滚动轴承振动信号的小波奇异性故障检测研究

该文以滚动轴承振动信号为分析对象 ,基于小波奇异性分析原理进行滚动轴承故障检测新方法的研究。通过求解待测信号的小波变换极大模来检测和识别信号中奇异点位置和奇异性大小 ,以及对噪声极大模的抑制处理 ,达到抑制或消除噪声的目的 ;最后 ,在剩余小波极大模的基础上进行信号重构 ,展现原待测信号中的故障信号模式。通过对铁路货车车轮用滚柱轴承振动信号的分析表明 ,此方法在大幅度地提高信噪比的同时 ,对由轴承损伤冲击造成的信号突变仍保持了较高的灵敏度和分辨率。为滚动轴承故障检测打下了良好的基础。     

一种基于样本熵的轴承故障诊断方法

运用非线性动力学参数样本熵作为特征,对轴承正常、内圈故障、滚动体故障、外圈故障四种工况的振动信号进行分析识别。针对利用原始振动信号的样本熵只能在一个尺度域进行分析,无法准确区分轴承运行状况的问题,提出一种基于集成经验模式分解与样本熵的轴承故障诊断方法。首先利用集成经验模式分解方法将原始振动信号分解为有限个内蕴模式分量,从中选取包含故障主要信息的前几个内蕴模式分量的样本熵作为特征,然后利用支持向量机进行轴承故障诊断,这样可以在多个尺度对轴承信号进行分析,提高了轴承故障诊断的准确率。通过轴承故障实测信号的诊断实验,证明了该方法的可行性和有效性。     

A New Spectral Average-Based Bearing Fault Diagnostic Approach

The diagnosis of bearing health through the quantification of accelerometer data has been an area of interest for many years and has resulted in numerous signal processing methods and algorithms. This paper proposes a new diagnostic approach that combines envelope analysis, time synchronous resampling, and spectral averaging of vibration signals to extract condition indicators (CIs) used for rolling-element bearing fault diagnosis. First, the accelerometer signal is digitized simultaneously with tachometer signal acquisition. Then, the digitized vibration signal is band pass filtered to retain the information associated with the bearing defects. Finally, the tachometer signal is used to time synchronously resample the vibration data which allows the computation of a spectral average and the extraction of the CIs used for bearing fault diagnosis. The proposed technique is validated using the vibration output of seeded fault steel bearings on a bearing test rig. The result is an effective approach validated to diagnose all four bearing fault types: inner race, outer race, ball, and cage.     

基于噪声辅助多元经验模态分解和多尺度形态学的滚动轴承故障诊断方法

为了从强噪背景中提取滚动轴承微弱故障特征,提出一种基于噪声辅助多元经验模态分解 (Noise Assisted Multivariate Empirical Mode Decomposition,NAMEMD)和数学形态学的滚动轴承故障诊断方法。NAMEMD是新提出的一种基于噪声辅助数据分析方法,其克服了集成经验模态分解的模态混淆和运算量大等问题。本文将NAMEMD与多尺度形态学相结合应用于滚动轴承故障诊断。该方法首先利用NAMEMD将多分量调频调幅故障信号自适应分解为一系列IMF分量;其次,选取能量高的IMF分量求和重构;最后利用多尺度形态学差值滤波器提取信号的故障特征频率。为了验证理论的正确性,进行了仿真试验和轴承故障试验,并与EEMD和包络解调进行了比较,结果表明本文方法在进一步降低模态混叠效应的同时,明显提高了运算速度,对滚动轴承外圈、内圈和滚子故障的检测精度更高,能够清晰地提取出故障信号的故障特征频率。     

Air-Coupled Ultrasonic Signal Processing Method for Detection of Lamination Defects in Molded Composites

In order to improve signal-to-noise ratio (SNR) of air-coupled ultrasonic signal in the detection of lamination defects in molded composite, the pulse compression and wavelet filtering hybrid signal processing method is proposed. The selection principle of parameters of the hybrid signal processing method is studied. The actual detection results of molded composite show that the hybrid method is very effective in improving the SNR of air-coupled ultrasonic signal when selecting reasonable parameters (The experiment results demonstrate that the optimal parameters are 13-bit Barker code sequences signal with three-cycle per sub-pulse, db9 wavelet, six decomposition levels, and soft threshold function.). An improvement in SNR up to 18.81 dB is attained compared with the original received signal. The quantitative accuracy of defects in C-scan image based on the hybrid method is also very high, and defects as small as \(\emptyset \)5 mm can be easily identified.     

基于局部均值分解和极值延拓的旋转机械故障特征提取方法

局部均值分解对非平稳、非线性故障信号进行平稳化处理时表现出特有的分析能力,能够有效获得故障信号的时频特征,然而局部均值分解过程中存在的端点效应严重影响信号的分解效果。针对这一问题,提出了一 种基于局部均值分解和极值延拓的旋转机械故障提取方法。首先采用极值延拓方法处理信号的两个端点,左、右端点均分别延拓2个极大值和2个极小值,然后对延拓后的信号进行局部均值分解,提取信号中包含的故障特征。仿真结果表明,经过极值点延拓后,局部均值分解过程中的端点效应得到了有效抑制,最后以轴承内圈故障为例在 实验平台进行了实验研究,实验结果表明,该方法能有效提取出旋转机械故障特征。     

Measurement of the size and spacing of standard wire sieves using an image processing system and wavelet transform

A new methodology using image processing and wavelet transform is investigated to measure the size of the wire sieves and their spacing. Wire sieves are used in pharmaceuticals/chemical industries for filtering the grains of chemical powder. Experimental results show measurement that the diameter and spacing of the wire in the sieves can be measured with the accuracy of 1um and uncertainty of 2 μm at 95% confidence level. The method is found suitable for detecting any missing wire or defect like bending or kink in the wire. In this techniques, wavelet transform (Symlet wavelet) analyses the image of sieve in such a way that the discontinuity (cracks, defects, nonuniformity) can be detected more precisely and the spacing/ wire diameter can be measured accurately. This method provides quite can fast and accurate results with ease, in comparison to the existing methods.     

经验模态分解和空间滤波在两相流速度测量中的应用

在利用空间滤波和电容传感器测量两相流速度时,需要准确测量电容传感器输出信号的带宽.针对此问题提出一种利用经验模态分解算法来测量传感器带宽的方法.文章首先介绍电容传感器的空间滤波效应和经验模态分解的基本原理,并给出固体速度和电容传感器输出信号带宽之间的关系.然后将经验模态分解和平滑滤波器结合对测量信号进行平滑处理,测量处...     

改进的EMD结合重复降噪在故障诊断中的应用

滚动轴承的故障信号采集中往往含有大量的噪声信号。对采集信号进行小波包降噪后,利用经验模态分解(empirical mode decomposition,EMD)得到若干个固有模态函数(intrinsic mode function,IMF)。计算各个IMF与去噪后信号的相关系数以此确定哪几个IMF是待分析信号的有效集,根据有效集中IMF的突变程度来选择不同消失矩的db系小波进行小波降噪。对IMF进行边际谱分析来判断滚动轴承哪个部位发生故障。该方法有效地去除了混杂在故障信号中的噪声,提高了信噪比,准确地判断出滚动轴承发生故障的部位。     

基于改进奇异值分解和经验模式分解的滚动轴承早期微弱故障特征提取

针对滚动轴承早期微弱故障特征难以提取的问题,提出了改进奇异值分解(SVD)和经验模式分解(EMD)的滚动轴承早期微弱故障特征提取方法。首先用多分辨奇异值分解将信号分成具有不同分辨率的近似和细节信号,然后对近似信号用奇异值差分谱进行消噪,对消噪后的信号进行经验模态分解,将得到的各本征模函数分量进行希尔伯特包络解调,从而获得滚动轴承故障特征信息,最后通过对滚动轴承早期内圈故障的诊断实验证明了该方法的有效性     

A Study on the Weak Signal Detection System Applied to the High Field Research Based on the Digital Lock-In Technique and Wavelet Filter

An improved digital lock-in technique with a wavelet filter is developed for the weak signals detection. A simulated signal modulated with a frequency of 40 kHz and contaminated by white noise is constructed to estimate the performance of the system. In this study, the selection of the wavelet filter parameters, such as the decomposition level, the wavelet basis and the threshold strategy is discussed. Finally, the performance of the system in different conditions is presented.     

小波分析—AR谱及其工程应用

小波分析能将信号划分到不同频段内,实现微弱故障信号的分离和提取。AR谱不信号经小波变换后采样点变少的限制,得到准确的故障频率值。本文充分运用这两者的优点,对某厂轧钢机主传动减速机振动信号进行分析,发现高速轴工作侧轴承出现故障征兆。