基于KPCA-HSMM设备退化状态识别与故障预测方法研究

为消除多通道观测信息冗余,压缩高维故障特征,提出基于KPCA多通道特征信息融合的HSMM设备退化状态识别与故障预测新方法.首先,对采集的单通道振动信号进行小波相关滤波处理,构造单通道振动信号的小波相关特征尺度熵向量,然后,利用KPCA方法对多通道的小波相关特征尺度熵向量进行冗余消除和特征融合,得到多通道的融合小波相关特征尺度熵向量,并以此向量作为HSMM的输入进行训练,建立基于HSMM的设备运行状态分类器与故障预测模型,从而实现设备退化状态识别与故障预测.将其应用到滚动轴承的退化状态识别与故障预测中,验证了该方法的有效性.     

基于连续小波灰度图的变速箱故障诊断

为了诊断汽车变速箱的周期性冲击故障，利用连续小波变换灰度图分别对正常和故障汽车变速箱振动信号进行了分析。结果发现，连续小波灰度图不仅能识别变速箱的正常与故障，准确提取出周期性冲击故障信息，而且能够非常直观形象地表达出信号的细微结果，并进一步显示出故障变速箱中同时存在的两种相同频率的故障信息，从多层次、多方位观察到了分析信号的细微变化。     

基于小波分析的变速箱滚动轴承故障诊断方法的研究

利用小波分析技术将滚动轴承故障振动信号分解到时－频空间,定义了滚动轴承故障振动信号能量分布函数Ｓ（ｔ） ,提出了能量分布函数Ｓ（ｔ） 细化谱诊断变速箱滚动轴承故障的分析方法。在某自行火炮的变速箱上进行了一系列滚动轴承故障诊断实验,实验结果验证了能量分布函数Ｓ（ｔ） 细化谱诊断变速箱滚动轴承故障的有效性     

基于小波分析对变速箱的故障诊断

为确定某型号液力叉车变速箱的故障原因,对其进行故障诊断,简要分析了变速箱内部结构,并计算了各档位情况下各个齿轮和轴承的故障特征频率,搭载实验平台,采集变速箱运转过程中的振动信号,并运用小波阈值去噪法对原始振动信号进行了消噪,接着分别运用小波分析和小波包分析方法对振动信号进行分解,并对相应频段信号进行重构和谱分析,综合两种分析方法的结果,获得变速箱的故障特征频率,确定是输入轴上齿轮存在缺陷。该研究对齿轮及轴承等相关构件的故障诊断有一定的参考意义。     

融合小波分解与时频分析的单通道振动信号盲分离方法

针对单通道振动信号盲源分离是一个病态问题,且传统的振动信号盲源分离方法往往忽略信号的非平稳性的问题,提出了一种融合小波分解与时频分析的单通道振动信号盲源分离方法。首先利用小波分解与重构将单通道信号转化为多通道信号,解决了盲源分离的欠定问题;然后利用基于时频分析的盲源分离算法分析非平稳信号,得到源信号的估计信号,实现了非平稳信号盲源分离。仿真和实验结果表明,该方法可以有效地解决单通道非平稳振动信号的盲源分离问题。     

小波分析在车辆故障诊断中的应用

车辆变速箱振动信号可用小波分析法预处理后，再用小波包能量尺度图分析法识别故障，按此法对BJ212变速箱准确地进行了故障识别，结果表明利用小波分析进行变速箱故障诊断的方法行之有效。     

应用小波变换信息融合诊断航空发动机故障

研究了小波变换的信息融合技术以及将其应用在振动信号处理、故障诊断方面较传统方法的优越性.在分析的理论基础上.对某型航空发动机用不同传感器采集的振动信号进行信息融合,然后提取出噪声掩盖下振动信号中的故障信息,根据航空发动机整机振动的典型故障特征频率,判断该发动机是否发生故障.     

齿轮点蚀的多通道数据融合识别方法

针对齿轮箱振动信号中混杂其他零部件振动频率的问题,提出一种基于小波包分解独立分量分析（wavelet package independent component analysis,简称WPICA）和多维经验模式分解（multivariate empirical mode decomposition,简称MEMD）的齿轮箱齿面点蚀故障信号的多通道数据融合识别方法。首先,利用一种窄带独立分量分析(sub-band decomposition independent component analysis,简称SDICA)方法—WPICA,从水泵机组多通道信号中提取齿轮箱振源,确定齿轮箱振动包含的特征频率成分;其次,借助MEMD分解多通道机组振动信号,将所获得的多维固有模式函数(intrinsic mode function,简称IMF)进行矩阵互信息运算,完成多通道数据的融合;最后,通过定义IMF故障敏感因子,确定故障敏感IMF的阶数并获得了齿轮点蚀故障的特征频率。数据分析结果证明了本研究方法的有效性。     

矿井提升机变速箱机械故障特征提取与诊断

煤矿井内提升机变速箱发生故障时,传动轴上信号的传播路径复杂,导致振动信号中故障特征提取困难加大,针对利用常规振动信号处理方法从振动信号中将故障特征提取难的问题,提出一种先广泛布置检测点,再分时段检测的方法。首先通过分析检测点的振动烈度逐步缩小故障范围,再利用谐波小波分解方法对小范围内的可疑检测点的振动信号进行三层次分解,最后通过分析a2和a3层信号的频谱,可从振动信号中提取出故障特征。试验结果表明,利用谐波小波信号分解方法分离出振动信号的故障特征信息,判定出Z1或Z2齿轮出现磨损,这与故障真实情况Z1齿轮发生磨损相一致,实现了变速箱机械故障的特征提取与诊断。     

基于信息融合技术的矿井通风故障诊断

为提高故障诊断的准确性,提出了一种多故障特征信息融合的故障诊断方法。该方法的参考信息包括定子电流信号、轴向振动信号和径向振动信号。对采集到的信号进行小波分析,提取出故障小波分析方法。基于每种类型的信息,通过神经网络计算得到初步的结论。为了得到最终结论,采用dempster-shafer evidence theory(以下简称D-S证据理论)组合规则实现信息融合。实验结果表明,采用信息融合技术处理的故障诊断信号进行分析,得出的结论可靠性明显提高。     

GEARBOX FAULT DIAGNOSIS USING ADAPTIVE WAVELET FILTER

Vibration signals from a gearbox are usually noisy. As a result, it is difficult to find early symptoms of a potential failure in a gearbox. Wavelet transform is a powerful tool to disclose transient information in signals. An adaptive wavelet filter based on Morlet wavelet is introduced in this paper. The parameters in the Morlet wavelet function are optimised based on the kurtosis maximisation principle. The wavelet used is adaptive because the parameters are not fixed. The adaptive wavelet filter is found to be very effective in detection of symptoms from vibration signals of a gearbox with early fatigue tooth crack. Two types of discrete wavelet transform (DWT), the decimated with DB4 wavelet and the undecimated with harmonic wavelet, are also used to analyse the same signals for comparison. No periodic impulses appear on any scale in either DWT decomposition.     

基于“阶次-小波”分析的齿轮箱升降速过程故障诊断研究

针对齿轮箱升降速过程振动信号的特点以及阶比分析的缺陷,提出了基于“阶次一小波“分析的齿轮箱故障检测方法。即首先将等时间信号重采样成为等角度信号,然后对等角度信号进行小波分析,最终识别故障。信号经过这种变换之后可以具有同时反映信号的阶比域和角度域的特征。经过仿真表明,该方法具有很好的诊断效果。     

基于改进经验小波变换的行星齿轮箱故障诊断

行星齿轮箱振动信号具有复杂多分量和调幅-调频的特点。幅值解调和频率解调方法能够避免传统Fourier频谱中的复杂边带分析,有效识别故障特征频率。经验小波变换通过对信号Fourier频谱的分割构造一组正交滤波器组,能提取具有紧支撑Fourier频谱的单分量成分,再对单分量成分运用Hilbert变换即可实现信号的解调分析。经验小波变换能够有效分离出调幅-调频成分,不存在模态混叠现象,具有完备的理论基础,自适应性好、算法简单、计算速度快。将改进的经验小波变换应用于行星齿轮箱振动信号的解调分析;提出了一种单分量个数的估算方法,解决了经验小波变换中的Fourier频谱划分问题;给出了对故障敏感的信号分量的选取方法,提高了分析的针对性。将改进方法应用于行星齿轮箱振动仿真信号和实验信号分析,验证了该方法的有效性。     

Gearbox fault diagnosis using empirical mode decomposition and Hilbert spectrum

The empirical mode decomposition (EMD) and Hilbert spectrum are a new method for adaptive analysis of non-linear and non-stationary signals. This paper applies this method to vibration signal analysis for localised gearbox fault diagnosis. We first study the properties of the recently developed B-spline EMD as a filter bank, which is helpful in understanding the mechanisms behind EMD. Then we investigate the effectiveness of the original and the B-spline EMD as well as their corresponding Hilbert spectrum in the fault diagnosis. Vibration signals collected from an automobile gearbox with an incipient tooth crack are used in the investigation. The results show that the EMD algorithms and the Hilbert spectrum perform excellently. They are found to be more effective than the often used continuous wavelet transform in detection of the vibration signatures.     

NEW METHOD OF EXTRACTING WEAK FAILURE INFORMATION IN GEARBOX BY COMPLEX WAVELET DENOISING

Because the extract of the weak failure information is always the difficulty and focus of fault detection. Aiming for specific statistical properties of complex wavelet coefficients of gearbox vibration signals, a new signal-denoising method which uses local adaptive algorithm based on dual-tree complex wavelet transform （DT-CWT） is introduced to extract weak failure information in gear, especially to extract impulse components. By taking into account the non-Gaussian probability distribution and the statistical dependencies among wavelet coefficients of some signals, and by taking the advantage of near shift-invariance of DT-CWT, the higher signal-to-noise ratio （SNR） than common wavelet denoising methods can be obtained. Experiments of extracting periodic impulses in gearbox vibration signals indicate that the method can extract incipient fault feature and hidden information from heavy noise, and it has an excellent effect on identifying weak feature signals in gearbox vibration signals.     

基于变分模态分解和PSO-SVM的起重机齿轮箱故障诊断

起重机齿轮箱的振动信号具有信噪比低、非线性的特点,需要一定的专业知识和经验才能实现故障诊断。为了实现起重机齿轮箱的智能故障诊断,提出了一种基于变分模态分解(Variation?al modal decomposition,VMD)改进小波降噪和粒子群算法(Particle swarm optimization,PSO)优化支持向量机(Support vector machine,SVM)的智能故障诊断方法。首先,利用VMD将振动信号分解,得到不同尺度的本征模态函数(Intrinsic mode function,IMF),将分解的高频分量进行改进小波降噪后和低频分量完成信号重构;然后,提取重构信号的特征参数构建特征向量,使用核主分量分析(Ker?nel principal component analysis,KPCA)对向量降维处理实现特征信息融合;最后,利用PSO优化后的SVM进行故障识别分类。实验验证表明,基于VMD改进小波信号预处理和PSO算法优化SVM的模型具有很高的识别准确率,能够有效、准确地对起重机齿轮箱的故障类型进行识别和分类。     

基于阶次小波包与粗糙集的轴承复合故障诊断

针对齿轮箱启动过程中振动信号表现为非平稳非高斯特征,传统诊断方法诊断精度不高的现状,将阶次小波包和粗糙集理论引入到轴承的复合故障诊断中,利用计算阶次跟踪算法对瞬态振动信号进行重采样,采用小波包对该信号分解-重构,并对每个频段的能量进行归一化,构成一个特征向量,通过粗糙集理论得到清晰、简明的决策规则.并通过复合故障实例验证了此方法的有效性.     

基于包络加窗同步平均的行星齿轮箱特征提取

行星齿轮箱由于行星轮通过效应、太阳轮与行星架的旋转及时变工况,导致其振动响应存在时变传递路径及非平稳性等特点,且传统的同步平均将不能直接应用于行星齿轮箱。笔者在国外加窗同步平均的基础上提出一种能有效克服时变传递路径及非平稳性的基于包络信号角域加窗同步平均的行星齿轮箱故障特征提取方法。首先,基于谱峭度提取出行星齿轮箱振动信号的包络信号;其次,再利用计算阶比跟踪技术对包络信号进行等角度重采样,行星架每旋转一圈,选择合适的窗函数对角域信号进行多齿宽加窗截取;最后,验证齿轮啮合齿序特征,根据重排齿序对加窗信号进行重构振动分离信号,对振动分离信号进行角域同步平均,提取行星齿轮箱故障特征。行星齿轮箱故障实测信号分析表明,该方法能有效提取行星齿轮箱故障特征。     

小波阈值降噪技术在齿轮箱振动信号处理中的应用研究

阐述一维信号的小波降噪原理及小波阈值降噪方法,用MATLAB软件对齿轮箱振动信号进行降噪处理。利用图像和计算数据说明不同小波函数和不同阈值规则的消噪效果,得出Stein无偏似然估计阈值(Rigrsure阈值)方法对强噪声复杂的齿轮箱振动信号降噪效果最佳。     

Subspace-based gearbox condition monitoring by kernel principal component analysis

Feature extraction is a key step for gearbox condition monitoring. The statistical features of the measured vibrations can be used to characterise gearbox conditions; however, their regularity and sensitivity in pattern space are different and may vary considerably under different operating conditions. This paper addresses the non-linear feature extraction scheme from the time-domain features with wavelet packet preprocessing and frequency-domain features of the vibration signals using the kernel principal component analysis (KPCA). Then two different KPCA-based subspace structures are constructed for representing and classifying the gearbox conditions. The proposed methods can extract the non-linear features of gearbox conditions using KPCA effectively, and perform conveniently with low computational complexity based on subspace methods. Experimental analysis with a fatigue test of an automobile transmission gearbox shows that the KPCA features outperform PCA features in terms of clustering capability, and both the two KPCA-based subspace methods can be effectively applied to gearbox condition monitoring.